Projects
| # | Title | Team Members | TA | Professor | Documents | Sponsor |
|---|---|---|---|---|---|---|
| 1 | Automated IC Card Dispenser System for Residential College |
Dongshen Ye Jonathan Chu Zhirong Chen Zicheng Ma |
design_document1.pdf final_paper1.pdf final_paper2.pdf final_paper3.pdf proposal1.pdf video1.mp4 |
Meng Zhang | ||
| # Team Members - Zhirong Chen (zhirong4) - Xiaoyang Chu (xzhu458) - Zicheng Ma (zma17) - Dongshen Ye (dye7) # Problem Students residing in residential colleges at the IZJU campus encounter issues when they inadvertently lock their ID cards inside their dormitories, particularly after showering at night. These students require a temporary IC card that exclusively grants access to their dormitory doors. However, staff availability is limited late at night to issue such IC cards. Consequently, an automated IC card dispenser is necessary to provide temporary IC cards to students. # Solution Overview The automated IC card dispenser system will authenticate students’ identities by scanning QR codes on their cell phones. Upon identity verification, the system's embedded software will retrieve the student's dormitory details. Subsequently, the mechanical system will select an IC card, program it with access information, and dispense it. Concurrently, the system will log the borrower's details. Once students return the temporary IC cards, the mechanical system will retrieve them, erase the stored data, and the software will log the cards as returned. # Solution Components ## KIOSK Software The software will encompass the user interface (UI), interaction with the central server, and integration with the recycling mechanical system. ## Recycling Mechanical System The recycling mechanical system will comprise a card storage box, a conveyance system for card transportation from the storage box to the reading and exit points, and an IC card reader/writer. ## Web User Interface The web user interface will facilitate interactions between users and administrators. Users can authenticate via the interface, while administrators can monitor terminal status and exercise remote control. ## Server System The backend software will be responsible for user authentication and authorizing the terminal to issue a new card. # Criteria for Success Robustness: The system should operate continuously 24x7 without significant issues or maintenance requirements. The recycling system's error rate should not exceed 1/500, and the system must detect errors and notify administrators promptly. Efficiency: The system should handle user requests swiftly and effectively. Security: Data transmission between terminals and the server must be secure and resistant to prevalent hacking techniques. Compatibility: The system should be compatible with existing authorization and access control systems. # Distribution of Work Zhirong Chen Design the backend server software system. Xiaoyang Chu Design the KIOSK terminal software system. Zicheng Ma Design the CV algorithm and user software system. Dongshen Ye Design the card dispensing/recycling mechanical system. |
||||||
| 2 | Smart Power Routing |
Jiabao Shen Jingjing Qiu Xiaoyi Han Yunfei Lyu |
design_document1.pdf final_paper1.pdf final_paper2.pdf proposal1.pdf |
Timothy Lee | ||
| # TEAM MEMBERS Yunfei Lyu 3200111297 Jingjing Qiu 3200110900 Jiabao Shen 3200112328 Xiaoyi Han 3200112425 # PROBLEM Our "Smart Power Routing" project addresses the challenge of efficiently distributing and utilizing power among devices with varying needs, such as a lightbulb and a fan. Traditional systems struggle with dynamically managing power supply due to changing user demands and device requirements, often leading to energy waste and inconsistent device functionality. Our solution is a dynamic power management system that intelligently adapts voltage supply in real-time, responding to user interactions like switching devices or manual power generation. This project aims to demonstrate the practicality of smart power management in real-world scenarios, offering an accessible and engaging illustration of these principles for a broad audience. # SOLUTION OVERVIEW Our smart routing system manages and stores energy from electrical outlets and manual inputs — such as hand-crank generators and a pneumatic turbine — into a battery. After receiving power information from the sensor, it then dynamically allocates power to a fan and lightbulb in response to user interactions. The system's adaptability is managed by a microcontroller, which ensures efficient energy distribution and maintains device operation through variable conditions. # SOLUTION COMPONENTS ## SUBSYSTEM 1: Energy Harvesting and Storage This subsystem combines power from electrical sockets and manual energy generation methods, storing it in a battery for stable supply. It utilizes hand-crank generators and a pneumatic turbine, powered by a hand-squeezed air pump, to capture and convert mechanical energy into electrical energy. Diodes and charge controllers ensure efficient energy flow into the battery, safeguarding against overcharging and power backflow. ## SUBSYSTEM 2: User Interaction Interface Switches and buttons serve as physical input devices. This user interaction interface captures user inputs, such as toggling the state of the socket, light, and fan, or activating the hand generator and turbine. ## SUBSYSTEM 3: Power Sensing and Load Management The power requirements of the fan and lightbulb are constantly monitored by current sensors, informing the microcontroller of any fluctuations in power consumption. This data allows the system to adjust power distribution in real-time, maintaining an uninterrupted operation of the connected devices. ## SUBSYSTEM 4: Microcontroller and Power Adjustment A microcontroller serves as the brain of the operation, processing sensor inputs and user interactions to manage the power flow effectively. It commands solid-state relays or transistor-based circuits to regulate the power supplied to the fan and lightbulb, ensuring their continuous operation. ## SUBSYSTEM 5: Display and Monitoring An LED screen displays battery storage condition and real-time power usage for both the fan and lightbulb, providing a visual representation of the system’s efficiency and the power dynamics between the devices and the power sources. # CRITERION FOR SUCCESS - Reliability: The system should consistently provide uninterrupted power to both the fan and the lightbulb regardless of user interactions, such as turning switches on and off and the presence of manual power generation from hand cranks or turbine inputs. - Efficiency: It should maximize the energy harvested from manual inputs and minimize losses during power conversion and distribution. - Good Visualization: The project should successfully demonstrate the principles of smart power routing in a way that is understandable and engaging for viewers, with clear displays of current power and battery condition. - Safety: The energy storage and distribution system must operate safely at all times, with built-in safeguards against overcharging, power backflow, and other potential hazards. - Durability and Maintenance: The system should be built to last, with easy maintenance and robust construction to withstand frequent use, especially by those unfamiliar with the system. # DESTRIBUTION OF WORK ## Yunfei Lyu - Project Manager and Quality Assurance - Responsibilities: Yunfei will oversee the project as the manager, coordinating project timelines, resource distribution, and team communication. Yunfei is also tasked with ensuring the overall quality of the project, focusing on both hardware and software components to meet the established reliability and safety standards. ## Jingjing Qiu - Software Development - Responsibilities: Jingjing will be responsible for developing the control software and energy management algorithm. The role involves coding the software to process input signals and dynamically adjust outputs, as well as implementing data logging capabilities. ## Jiabao Shen - Hardware Design and Safety Concerns - Responsibilities: Jiabao will spearhead the design and assembly of the hardware components, which includes crafting a smart voltage regulation system and ensuring the hardware is durable and easy to maintain. Additionally, Jiabao will be responsible for integrating safety features such as circuit breakers and surge protectors. ## Xiaoyi Han - User Interface and Interaction - Responsibilities: Xiaoyi's focus will be on enhancing user experience by developing an intuitive user interface (if applicable) and ensuring that the functional demonstration table is user-friendly and engaging. This role also entails testing the system's user interaction components for effectiveness and ease of use. |
||||||
| 3 | AR Sandbox |
Haowen Zheng Haoze Gao Qiran Pan Yiheng Zhang |
design_document1.pdf final_paper1.pdf final_paper2.pdf proposal1.pdf proposal2.pdf |
Timothy Lee | ||
| ## Team members Haoze Gao, haozeg2 Haowen Zheng, haowenz5 Qiran Pan, qiranp2 Yiheng Zhang, yihengz5 ## Title Of Project AR Sandbox Redesign ## Problem Introducing a smart sandbox with augmented reality (AR) capabilities that projects contour maps in real-time onto the sand surface, making geography education for children not only informative but also significantly more enjoyable. However, currently available educational sandboxes are mostly cumbersome and limited to public spaces like activity centers rather than serving as personalized learning tools. Furthermore, the existing AR projectors designed for sandboxes exhibit primitive features, characterized by a notably low refresh rate and harsh direct light. We are committed to addressing these drawbacks and are working towards the development of a new and improved AR sandbox. This innovative solution aims to overcome the limitations of bulkiness, offering a more accessible and personal learning experience. Additionally, we are focused on enhancing the AR functionality to deliver a smoother experience with higher refresh rates and reduced glare, ensuring a more comfortable and engaging educational tool for children. ## Solution Overview We would develop a next-generation sandbox with augmented reality (AR) projection and interaction capabilities. In comparison to the popular versions available in the market, our AR projector is set to achieve a higher refresh rate, easier control without external touch screen, and the overall structure will be designed to be foldable while ensuring both high load-bearing capacity and stability. ## Solution Components ### Sensor Subsystem - **RGBD** camera (ToF or structured light) and associated software for acquiring RGB image and processing depth information ### Processing Subsystem With the use of GPU acceleration - **Human body detection** to overcome the interference from human hands and head. With this to enable multi-user collaboration - **User Interface** with gesture control. Use hand gestures to interact with the screen projected on sand. - **Real-time topography rendering**: Constructing topography map from depth information with GPU acceleration ### Display Subsystem - Displaying on sand requires high luminance projector and associated **calibration software**. The software needs to track for image alignment ### Structure Subsystem - The sand table should be made of materials and designs with sufficient strength to carry sand and prevent people from damaging the wall of the sand table when in use. - The sand table will be foldable, which will reduce the volume and facilitate carrying and storage. - The sand table can be separated from the sand while folding, which will make the sand table more conducive to cleaning, increasing durability, and conducive to rapid deployment in different use scenarios. - We will add an additional vibration device so that the sand surface can be quickly restored to level when necessary. ## Criterion For Success For our criteria for success, we outline the following requirements: 1. Physical Structure: The sandbox must have a robust physical structure capable of fully supporting the weight of the sand without any leakage. It should also withstand lateral forces of around 40kg exerted by children pulling on the sides of the sandbox. 2. AR Projector: The projector should be capable of accurately projecting contour maps onto the sandbox with more than 1 people playing with sand at a refresh rate of higher than 30fps. To verify the correctness of the contour maps, we will artificially create distinctive landforms such as ridges, valleys, and saddles, and compare them with the projected contour maps to ensure accurate alignment. |
||||||
| 4 | Actions to Mosquitoes |
Lumeng Xu Peiqi Cai Xiangmei Chen Yang Dai |
design_document1.pdf design_document2.pdf final_paper1.pdf final_paper2.pdf proposal1.pdf |
Said Mikki | ||
| # Team Members Xiangmei Chen [xc47] Peiqi Cai [peiqic3] Yang Dai [yangdai2] Lumeng Xu [lumengx2] # Title Actions to Mosquitoes # Problem Many of us get bitten by mosquitoes without notice. We come up with a device that can distinguish by sound whether a mosquito exist in a given area and take actions to keep it away. Solutions existing in the market include mosquito spray, insect-repelling lamp, and mosquito-repellent incense. However, they work continuously, and people may get uncomfortable with its smell. It would be less disturbing and resource saving if the device only reacts when a mosquito approaches. # Solution Overview In order to have in-time response of mosquitoes, we first need a device to detect sounds of mosquitoes. After the sound is collected, we need to process the signal to tell if a mosquito presents. If the presence is true, an actuator will take actions to keep the mosquitoes away. # Solution Components [Sound Detecting Subsystem] A sound detecting device, could be high accuracy microphone that can capture the sound of mosquitoes since they produce a characteristic buzzing sound when they fly, which varies depending on the species and gender. The frequency of the sound that the system capturing can be set to the range of frequencies of the mosquitoes to further improve accuracy. [Signal Processing Subsystem] A signal processor that can analyze the sound and identify the presence and type of mosquitoes. The signal processor could use a machine learning or other algorithms, or a frequency filter to distinguish the mosquito sound from other noises. [Mechanical Subsystem] An actuator that can take actions to keep the mosquitoes away. Depending on the desired effect, the actuator could emit a high-frequency sound that repels mosquitoes, a chemical spray that kills or deters them, or a device that could emit gas or light of specific wavelength that attract them and knock them down. # Criterion for Success Detection Accuracy: The device should be able to accurately detect the distinctive sound of mosquito wings flapping with a high degree of precision to minimize false positives (e.g., from other insects or ambient noise) and false negatives (failure to detect mosquitoes). Responsiveness: Upon detecting a mosquito, the device should promptly activate the mechanical components to deter or eliminate the mosquito within a predefined time frame, ensuring efficient protection. Coverage Area: The device must effectively monitor and protect a defined area, such as a standard-sized room, from mosquitoes, with clear specifications on its effective range. User Interface: If applicable, any software interface for the device should be user-friendly and allow users to easily adjust settings, such as detection sensitivity or deterrent mechanisms. Energy Efficiency: The device should operate efficiently, using a reasonable amount of power, and if battery-operated, should have a battery life that is practical for typical use cases (e.g., overnight use in a residential setting). Safety: The device and its deterrent methods (such as acoustic waves or mosquito sprays) should be safe for use in the intended environment, not posing health risks to humans or pets. # Distribution of Work Peiqi Cai [EE]: Responsible for the design and implementation of the microphone array and any other necessary sensors that are part of the hardware which collects the mosquito sounds. This will include circuit design, component selection, and integration of the sensors with the rest of the system. Lumeng Xu [ECE]: Develop the signal processing software that analyzes the audio data from the hardware to distinguish mosquito sounds. This includes writing the algorithm, possibly utilizing machine learning, and ensuring it can run efficiently in real-time. Yang Dai [ECE]: In charge of the overall system integration, ensuring that the hardware and software components communicate effectively. This student will also be responsible for the user interface, if applicable, and making sure that the software is user-friendly and robust. Xiangmei Chen [ME]: Design and test the mechanical components that take action to repel or eliminate mosquitoes. This could involve the design of the enclosure that houses the electronics, any moving parts for the actuation mechanism, and the dispersion system for the repellent if a spray is used. She will also ensure that the physical design adheres to safety and ergonomic standards. |
||||||
| 5 | Display for ODEs |
Kejia Hu Qianhe Ye Qirong Xia Zhuohao Li |
design_document1.pdf final_paper1.pdf final_paper2.pdf proposal1.pdf |
Pavel Loskot | ||
| # TEAM MEMBERS - Qirong Xia (qirongx2) - Kejia Hu (kejiahu2) - Qianhe Ye (qianhey2) - Zhuohao Li (zhuohao5) # PROBLEM Many physical systems involve interactions between multiple variables that can be difficult to conceptualize in a 2D space. Visualizing these solutions in 3D allows a more intuitive understanding of the behavior over time or across different conditions. Additionally, for problems involving spatial dimensions, a 3D visualization can illustrate how variables change not just over time but also across different points in space. # SOLUTION OVERVIEW Our project aims to create a 3D real-time visualization of a time-varying 2D Ordinary Differential Equation (ODE) function. This visualization platform will dynamically represent the changing behavior of the function over time. Additionally, we will project the color to the surface from either the top or below, adding another dimension of visual interpretation. Our design has three subsystems and one optional subsystem. The **User Interface module** will get the ODE from the user calculate the solution for it and transmit the data to the Dynamic Stick Control module. This subsystem will get the ODE solution from the User Interface Module and then convert the information to languages that the mechanical devices can understand. Our **Mechanical module** adjusts the height of the stick based on the signal transmitted from the Dynamic Stick Control module. Additionally, this module will use a **Lycra fabric** to cover the top of the grid-like sticks to create a smooth visualization surface for displaying the ODE. Finally, if the time is available, we will design a Surface Coloring and Projection Module which will project images to the canvas either from the top or below. # SOLUTION COMPONENTS ## USER INTERFACE SUBSYSTEM The User Interface (UI) module serves as the interface between the user and the ODE visualization system. It receives input ODE equations from the user, calculates the solution for them, and transmits the data to the Dynamic Stick Control module for visualization. To realize this function, firstly, we need a Graphical User Interface (GUI) which contains components such as text input fields, buttons, sliders, and dropdown menus for user interaction, allowing users to input ODE equations through a graphical interface. Secondly, once the user inputs the ODE equations, the module utilizes an ODE solver algorithm to compute the solution. This may involve numerical integration techniques such as Euler's method, Runge-Kutta method, or other numerical approaches depending on the complexity and accuracy requirements of the ODE. Thirdly, after computing the solution, the UI module transmits the data, including the time-varying solutions of the ODE variables, to the Dynamic Stick Control module for visualization. The transmission occurs through a wired communication interface. Lastly, the UI module will provide feedback to the user regarding the status of the computation, such as progress indicators or error messages in case of invalid input or computation failures. ## DYNAMIC-STICK CONTROL SUBSYSTEM The control subsystem first interprets the solution of ODE from the User Interface subsystem. Then the system translates the solutions of the ODE into control commands that can be executed by the mechanical subsystem. This involves mapping the mathematical solutions to physical actions, such as the movement of the sticks. Besides this, the control subsystem also gets feedback from the mechanical subsystem, comparing the actual outcomes with the desired outcomes, and tuning the outputs accordingly. To implement the control logic, we plan to use the Arduino development board or an low-power Intel FPGA (DE10-Lite). ## MECHANICAL SUBSYSTEM The mechanical subsystem is composed of sticks that can dynamically move up and down based on the displayed solution. Lycra fabric is affixed to the top of each stick to make the visualization smooth. The mechanical subsystem gets inputs from the control subsystem, performing the actions as dictated by the control commands, and feedback to the control subsystem for further tuning. The system maintains the precision and accuracy of the motions by following the control commands from the control system as closely as possible. It should also be robust and minimize the small vibrations and noise from the environment. ## SURFACE COLORING AND PROJECTION SUBSYSTEM (OPTIONAL) The coloring and projection subsystem is on the top of the device. It continuously measures the height of each stick in real-time, which can be achieved by incorporating ultrasonic sensors in the subsystem to sense the distance. To achieve accurate and rapid coloring, the subsystem also needs to prevent noise from affecting the sensor's operation. The data collected from the sensors is processed to identify the status of the mechanical system. Given the processed sensing data, the subsystem employs a logic to assign colors based on the height of the sticks. For example, the highest sticks could be assigned to the color red, while the saddle points are assigned to the color blue. As the height of the sticks changes, the subsystem must dynamically adjust the projections in real time to reflect these changes. We plan to implement this feature if time is available since it requires an independent control system to implement the logic. # Criterion for Success The success of our project will be determined by the following high-level goals: 1. **Functional User Interface (UI) Subsystem**: The UI should be intuitive and user-friendly, allowing users to input ODE equations easily and see the status of computations. It should effectively communicate with the Dynamic Stick Control subsystem to transmit ODE solutions accurately and efficiently. 2. **Accurate Dynamic-Stick Control Subsystem**: This subsystem needs to accurately interpret and translate ODE solutions into precise mechanical movements. The control system, whether using an Arduino or FPGA, should provide reliable and real-time response to the computations received from the UI. 3. **Robust Mechanical Subsystem**: The mechanical setup, involving the dynamic sticks and Lycra fabric, must respond accurately to the control signals. It should be sturdy, minimize vibrations and noise, and accurately reflect the ODE solutions in a 3D format. 4. **Overall Integration and Performance**: All subsystems must work harmoniously to create a seamless and real-time 3D visualization of the ODE solutions. The system should be stable, efficient, and provide a clear and accurate representation of the ODE dynamics. # Distribution of Work The work distribution among team members is planned as follows, considering their majors and skills: - **Qirong Xia (qirongx2)**:As an electrical engineering student, Qirong will lead the electrical design and, if time allows, lead the development of the Surface Coloring and Projection subsystem, focusing on sensor integration and real-time color projection. - **Kejia Hu (kejiahu2)**: With expertise in electrical engineering, Kejia will be responsible for the Dynamic-Stick Control subsystem, including programming the Arduino or FPGA for accurate control and feedback mechanisms. - **Qianhe Ye (qianhey2)**: As a mechanical engineering student, Qianhe will lead the design and construction of the Mechanical subsystem, ensuring the precision and robustness of the stick movements and fabric setup. - **Zhuohao Li (zhuohao5)**: With a background in computer engineering, Zhuohao will focus on developing the User Interface subsystem, including the GUI design and integration with the ODE solver algorithm. The project's complexity is justified by the diverse skills of the team members. The combination of expertise in computer, electrical, and mechanical engineering is essential for tackling the various challenges presented by this interdisciplinary project. Each member's skill set is aligned with their respective subsystem, ensuring a well-rounded approach to achieving the project's goals. |
||||||
| 6 | Submarine Model |
Wenpeng Zhang Yikai Xu Yiqin Li Zhicong Zhang |
design_document1.pdf design_document2.pdf final_paper1.pdf final_paper2.pdf proposal2.pdf proposal1.pdf |
Pavel Loskot | ||
| Zhicong Zhang Yikai Xu yikaixu3 Yiqin Li yiqinli2 Wenpeng Zhang wenpeng4 Submarine Model Request For Approval **Problem** Moving on the ground or on the water, or in the air is relatively easy. This may not be the case when moving in the water. A remote-controlled submarine model can be used to simulate the performance of real submarines in a complex environment, showing the working principles of submarines to help understanding submarine technology and marine science. **Solution overview** Our solution involves implementing the functionality of a submarine through a remote-control system, an automatic stabilization and dynamic system, and drainage system. Additionally, we require an electronic control MCU to process remote control commands sent from a distance and handle signals from sensors to achieve submarine balance. Our novelty lies in balance in complex underwater environment and avoiding collision. **Solution component** Sensor Subsystem: 1. Pressure and infrared distance sensors: Measure the depth and object distance at which the submarine is operating. 2. Motion sensors: Monitor the speed and acceleration of the submarine's three-dimensional motion. Processing Subsystem: 1. Main Controller (Microcontroller): Responsible for processing and interpreting sensor data, controlling the submarine's movement and operations. 2. Communication Module: Facilitates data communication with an external base or command center, conveying submarine status and mission information. 3. Automatic Stabilization Module: Utilize sensor data and apply PID control algorithms to realize automatic stabilization. Power Subsystem: 1.Battery and electric Motors: Control the propulsion and maneuvering of the submarine to adapt to different depths and aquatic conditions. Mechanical Subsystem: 1. Cabin: Used to the house rest of the subsystems and keep water out. 2. Water storage tank: Control the total weight of the submarine. **Criterion for success** 1. Effective waterproof functionality. 2. [novelty] System's stability. Maintain the hull's balance under different water conditions. 3. Stable ascension and descent. 4. Forward/backward movements. 5. Various operational modes. Each performs at different applications. Such as Obstacle avoidance, cruise control, etc. (optional) **Distribution of Work** Zhicong Zhang: Mechanical part Yikai Xu: Remote controlling and MCU part Yiqin Li: Electricals part and control system part Wenpeng Zhang: Software part |
||||||
| 7 | Drone Delivery System for Takeaway Business |
Ximo Wang Yanbing Yang Yang Chen Yuzheng Zhu |
design_document1.pdf design_document2.pdf final_paper1.pdf final_paper2.pdf final_paper3.pdf proposal1.pdf |
Jiahuan Cui | ||
| **Team Member (NetId)** - Ximo Wang (ximow2) - Yanbing Yang (yanbing7) - Yang Chen (yangc7) - Yuzheng Zhu (yz83) **Problem** We are going to design and realize an airway delivery system with drone, container and cloud server. Delivery of light weight, medium range, fast response with a city is a strong demand especially during rush hour. Traditional airway delivery drones with GPS guiding are not precise enough for landing in limited space. Existing delivery drones on market requires the manual operation during picking and placing the goods. **Solution Overview** The basic parts of our solution are delivery drone and automatic containers. The drone can communicate with container to fetch the delivery information while picking up goods. An app connects the container, cloud server and costumer is designed as well. **Solution Components (Also Distribution of Work)** - Light Delivery Drone (Yanbing) Design and manufacture a quadrotor UAV with special structure for transition between picking-up mode and shipping mode. The drone will realize the function of self-navigation, precise landing, automatic obstacle avoidance, RTK communication and cloud server connection. - Navigation System with RTK (Ximo) Real-Time Kinematics operates by augmenting the standard Global Navigation Satellite System positioning technique with real-time correction data. The device applies corrections to its own GNSS calculations, resulting in highly accurate positioning with centimeter-level precision. Using this method, our UAV can find the accurate position of container when landing. - Automatic Container (Yuzheng) The container needs to interface with the drone, responsible for automatically storing objects delivered to the landing pad by the drone into the container. It also handles transporting goods placed in the locker by the merchant to the landing pad for the drone to pick up and deliver. - Communication System (Yang) Our drone needs to communicate with both container and cloud. In this way, user can send delivery request and know the progress of the delivery, even the current location of the drone. The container would also know the status of the drone and resend message if possible. **Criterion for Success** Our solution can accurately deliver the requested good from one location to the destination without manual operations. The drone can pick up the package and deliver it to the destination independently. What the user needs to do is just put the package into the container and get their package from the container. **Alternatives** Foodpanda has piloted food deliveries in Singapore using multirotor drones from ST Engineering and in Pakistan using VTOL drones from Woot Tech. Flytrex has delivered over 55K orders by drone in three towns in North Carolina and Texas since 2022, including Starbucks coffee, Walmart, Chick-fil-A, Papa John's pizza and more. Our solution differs from existing solutions since it’s more convenient and cheaper. The drone and the delivery container are integrated, with the container serving both as a storage unit and a landing pad. Both merchants and customers need only to concentrate on the order itself. Placing an order through the program is all that's required, as all decision-making, delivery, and interfacing are fully automated. We use low-cost standard components to reduce expenses. |
||||||
| 8 | Particle Image Velocimetry |
Brant Qian Hanfei Yao Yihui Chen Yueming Yuan |
design_document1.pdf design_document2.pdf final_paper1.pdf final_paper2.pdf proposal1.pdf proposal2.pdf |
Timothy Lee | ||
| # Team Members: - Yihui Chen (yuhuic3) - Hanfei Yao (hanfeiy3) - Yueming Yuan (yy28) - Siyuan Qian (siyuanq4) # Problem Understanding how fluids move is crucial for many scientific and engineering applications. However, traditional methods to visualize fluid flow are complicated and not easy for everyone to grasp. We need a simple and accessible solution for visualizing fluid dynamics. We need to design a device that can demonstrate particle image velocimetry. The device can demonstrate in a simple way that children can easily understand and interact with. Low cost, easy maintenance, durable. # Solution Overview The proposed Fluid Velocity Measurement System is a comprehensive solution comprising distinct subsystems for accurate and real-time measurements. Within the system, the Fluid Channel Subsystem ensures continuous fluid circulation through a sophisticated piping system driven by manually operated pumps. The Laser and Optical Subsystem incorporates an adjustable laser source and optical components, such as lenses and mirrors, to illuminate and capture clear images of particles within the fluid. The Particle Injection Subsystem generates and evenly disperses trackable particles for enhanced visibility. The Image Acquisition Subsystem, equipped with a digital camera, captures and aligns particle images, forwarding them to an Image Processing System for precise velocity calculations. The Remote Access and Control Subsystem allows an instructor to control the device remotely with a simple application. The hands-free Voice Control Subsystem allows children to interact with the device safely and conveniently. The User Interface and Data Visualization Subsystem offers a user-friendly platform with a display for real-time fluid images and velocity field visualizations, enabling efficient monitoring and analysis of fluid dynamics. This holistic solution caters to applications demanding accurate and timely fluid velocity information without duplicating details from the specified components. Our PIV device also can provide some fun parts to help them understand how it works and rise their interests in fluid dynamics. # Solution Components ## Flowing System: Transparent container that allows fluid flow through. There are small manually operated pumps that ensure that the fluid circulates through the channel. We can measure and control flow rate of the fluid. ## Particle Injection System: A particle generator produces small particles that can be followed in a fluid, such as brightly colored markers. The particle injector introduces particles into the fluid channel, ensuring that they are evenly distributed and can be illuminated by the laser. ## Illumination System: A laser source that provides a laser beam for illuminating particles in the fluid and ensures that the laser source is position adjustable. And contains an optical system including lenses, mirrors, and filters for creating a clear spot and image. ## Image Acquisition System: A camera is used to capture images of the particles in the fluid, sending the captured pictures to an image processing system, which, is used to calculate the particle velocity. At the same time the camera makes sure to align the particles in the fluid channel. The camera should have high spatial resolution, high sensitivity, short and accurate inter-frame time, and sometimes high frame rates. ## Remote Access and Control System: A network module implemented with Raspberry Pi to enable remote access and control of the PIV. Web-based interface or a simple application that can connect to the Raspberry Pi, allowing users, e.g., instructors, to monitor and control the system remotely. ## Voice Control System A voice-controlled interface in the Raspberry Pi to enable it to understand and respond to simple verbal instructions. This subcomponent will enhance the user interaction with the PIV system, allowing for hands-free operation and accessibility. ## Interactive User Interface: A graphical user interface (GUI) on the Raspberry Pi, allowing users to control various aspects of the PIV system, view real-time data, and adjust settings as needed. The GUI may include features like starting/terminating experiments, adjusting flow rate, controlling laser and camera settings, and visualizing real-time fluid flow patterns. ## Data Visualization System A comprehensive data visualization interface on the Raspberry Pi, specifically tailored to the PIV. This interface will enable users to visualize the velocity of particles within the fluid in real time, providing an intuitive and interactive way to understand complex fluid dynamics. # Criterion for Success ## User-Friendly and Affordable: Easily understandable, especially for children. Cost-effective with readily available materials. ## Reliable and Low Maintenance: Durable, requiring minimal maintenance. Accurate fluid velocity measurements. ## Real-time Visualization: User Interface provides real-time fluid images and velocity field visualizations. ## Adjustability and Safety: Laser and optical components and the remote and voice control interfaces are adjustable and incorporate safety features. ## Educational and Compatible: Effective educational tool for fluid dynamics understanding. Compatible with common operating systems and allows data export. ## Interactive and Hands-On Experience: Able to have hands-on interaction for a more engaging experience. Provides a fun, interactive, and convenient way to learn about fluid dynamics. # Distribution of work ME Student Yihui Chen Do Camera calibration and Laser camera synchronization. Do Basic image processing. ME Student Hanfei Yao Do Particle material selection and Container and channel design Carry out unit tests to ensure device’s accuracy and efficiency. ECE Student Siyuan Qian Implement remote access control. Implement the voice-controlled interface. Do data visualization. ECE Student Yueming Yuan Implement the interactive user interface. Do data visualization. |
||||||
| 9 | Image acquisition, 3D reconstruction and a visual interactive digital heritage system |
Chuanrui Chen Denglin Cheng Qianyan Shen Ziying Li |
design_document1.pdf design_document2.pdf final_paper1.pdf final_paper2.pdf proposal1.pdf |
Shurun Tan | ||
| Spring 2024 ECE445 RFA Image acquisition, 3D reconstruction and a visual interactive digital heritage system # TEAM MEMBERS: - Qianyan Shen (qianyan2) - Ziying Li (ziyingl4) - Chuanrui Chen (cc86) - Denglin Cheng (denglin3) # Problem Cultural artifacts possess significant historical, cultural, and artistic value. However, due to the passage of time and the impact of natural deterioration, many artifacts face risks of damage, loss, or decay. Additionally, for history enthusiasts and researchers worldwide, detailed information about specific artifacts is not readily accessible. Traditional photographs often fail to capture the intricate details of artifacts, hampering comprehensive research and preservation efforts. Furthermore, the absence of user-friendly interactive interfaces limits the interaction between enthusiasts and artifacts, impeding immersive experiences in virtual exploration of cultural heritage. Therefore, our team aims to develop a system that can generate realistic 3D models of cultural artifacts and provide users with a user-friendly interactive interface for immersive exploration. # Solution Overview Our system will use advanced scanning and 3D reconstruction techniques to capture the detailed geometry of cultural artifacts. This will be achieved through a series of subsystems including a Stabilized Scanning Subsystem, 3D Reconstruction Subsystem, Database Subsystem, and Interactive Interface Subsystem. Please refer to the following subsystem descriptions for more detailed information. # Solution Components ## Stabilized Scanning Subsystem This subsystem aims to capture detailed 3D data of the workpiece with high precision and low noise by coordinating a self-stabilizing three-axis gimbal centered around the STM32 microcontroller. We intend to use solidworks to build the three axis parts of the gimbal respectively, and print them out with a high-precision 3D printer, and then use the brushless motor to connect these parts, and control them with the STM32 code, so that it can achieve real-time angular correction, so that in the process of scanning can be done to achieve the lens anti-shake, reduce motion blur. ## 3D Reconstruction Subsystem This subsystem aims to obtain a point cloud through RGBD images and perform 3D reconstruction using the point cloud. We first use a depth camera to capture RGBD images of an object from different angles and preprocess the raw images by denoising and repairing. Then, we proceed with point cloud acquisition, registration, and reconstruction to obtain a 3D model. To begin, we calibrate the camera to obtain the lens parameters. We then convert the 2D coordinate system of the depth image to a 3D point cloud and map the pixel colors from the RGB image to the 3D point cloud. Afterward, we process the obtained point cloud by applying denoising and sampling techniques, facilitating subsequent registration and reconstruction steps. By repeating these processes, we obtain point clouds from different angles, and we perform precise registration using the ICP （Iterative Closest Point） method to align them in a unified coordinate system. Finally, the 3D reconstruction is completed using the Poisson reconstruction algorithm or other techniques. ## Database Subsystem This subsystem aims to store the basic information of the artifacts, including dynasties, historical backgrounds, stories, etc., and at the same time saving the generated complex 3D model data. With database system, users can upload the information of artifacts from all over the world to the database, and can also retrive and view the artifacts from exotic countries. When a user wants to retrieve an artifact, the database will find the corresponding information from its own stored data according to the search item entered by the user and display it through the Interactive Interface Subsystem for users to view artifacts from around the globe. ## Interactive Interface Subsystem This subsystem aims to provide a user-friendly interface that facilitates database interaction and basic visualization capabilities, delivering a visually pleasing experience to users and catering to their close-range viewing needs. We aim to present brief introductions of multiple cultural artifacts on the interface, including physical photos, names, dynasties, and more. Upon selection, users can access the corresponding detailed information and the reconstructed 3D model by linking to the database. Specifically, we render the obtained 3D models and offer features such as rotation and scaling for users to observe the artifact's details. Additionally, the interface can include a filtering function to provide users with a certain degree of personalized service in selecting artifacts. # Criterion for Success Successfully captures information about the appearance of artifacts without requiring the user to manually adjust examples or angles to minimize the noise. Accurate and detailed 3D scanning and reconstruction of artifacts. A database subsystem for effective data management and data retrieval. A user-friendly interactive interface provides an immersive experience in cultural heritage exploration. # Divisions Of Labor And Responsibilities Denglin Cheng is responsible for the modeling of the Stabilized Scanning Subsystem, 3D printing, and the design of the control circuits in the STM32, as well as the final assembly and debugging of the gimbal to ensure smooth scanning of the depth camera. Qianyan Shen is responsible for RGBD image preprocessing, point cloud acquisition, alignment, and 3D reconstruction. Ziying Li is responsible for enabling database system to store and retrive data and interact with front-end. Chuanrui Chen is responsible for the specific design and implementation of the UI interface, requiring her to understand and utilize the database interface. She also assists in the acquisition of point clouds from RGBD images and the design of the control circuits in the STM32. |
||||||
| 10 | Smart Laundry FoldBot |
Channing Liu Jiadong Hong Jialin Shang Weijie Liang |
design_document1.pdf design_document2.pdf final_paper1.pdf final_paper2.pdf final_paper3.pdf final_paper4.pdf proposal1.pdf |
Yu Lin | ||
| # Smart Laundry FoldBot RFA ## Team Member Jiadong Hong EE Qianqi Liu ME Jialin Shang CompE Weijie Liang CompE ## Problem Laundry folding, a seemingly mundane task, can be surprisingly time-consuming, tedious, and even physically demanding. This project aims to enhance our overall well-being and quality of life by addressing the challenges associated with this commonplace but often underestimated activity. By alleviating the burden of laundry folding, the system we propose aims to liberate individuals to focus on more meaningful pursuits, contributing to a more harmonious and productive home environment. The primary challenge lies in developing a sophisticated machine capable of efficiently automating the clothing recognition and folding process. The system should integrate advanced computer vision capabilities to accurately identify and categorize different types of clothing items, such as shirts, pants, dresses, and more. Moreover, it must be adaptable to varying sizes and clothing styles, ensuring the folding process accommodates the diverse range of garments found in typical households. ## Solution Overview Our system automates laundry folding through: **Core Boards:** Four motorized boards fold clothing sequentially—Left, Right, Lower, and Upper—for precision. The Upper Board aids in easy clothing removal. **Expansion Plates:** Three adjustable plates adapt to clothing sizes, ensuring comprehensive folding for different dimensions. **CV Assistance:** We would use advanced computer vision for accurate clothing recognition and spatial understanding. **Kinetic Control System:** We would employ Reinforcement Learning for optimal folding and Exception-handling Algorithms for real-time adaptation. Our Automated Clothing Recognition and Folding System integrates these components, providing an efficient and user-friendly solution for a more harmonious and productive home environment. ## Solution Components ### Core Boards This component is essentially the primary folding mechanism, consisting of four specialized boards, each powered by an electric motor. These boards are designed to fold 180 degrees, enabling the sequential folding of clothing placed on them. The four boards are: #### a. Left Core Board: \- Positioned on the left side. \- Folds 180 degrees to the right. \- This action folds the left portion of the clothing (e.g., the left side of a shirt). #### b. Right Core Board: \- Located on the right side. \- Folds 180 degrees to the left. \- This mirrors the left core board's action, folding the right portion of the clothing. #### c. Center Lower Core Board: \- Situated below the central part of the clothing. \- Folds upwards 180 degrees. \- This folding step works on the lower part of the clothing, bringing it upwards and typically folding the garment in half. #### d. Center Upper Core Board: \- Located above the central part of the clothing. \- Also folds upwards 180 degrees. \- Completes the folding process by folding the upper portion of the garment. At this stage, the clothes are fully folded. \- This board may interact with an external system, such as a conveyor belt, to move the folded clothing away from the machine. ### Expansion Plates This component provides the system with the flexibility to handle various sizes and types of clothing. It comprises three adjustable plates: #### a. Left Expansion Plate: \- Adjacent to the left core board. \- Capable of extending or retracting to accommodate different clothing sizes. \- Specifically, it adjusts for clothing parts that extend beyond the left core board, like long sleeves, folding them appropriately. #### b. Right Expansion Plate: \- Positioned next to the right core board. \- Functions similarly to the left expansion plate but on the right side. \- Adjusts for the parts of the clothing that exceed the right core board. #### c. Lower Expansion Plate: \- Located below the central lower core board. \- Operates under the same principle as the other expansion plates. \- Adjusts for clothing parts that extend beyond the central lower core board, ensuring a complete and neat fold. ### CV Assistance #### **Object Detection:** Utilize sophisticated object detection algorithms, notably YOLO (You Only Look Once) or Faster R-CNN, to discern the spatial coordinates and categorical attributes of clothing articles. This facilitates a nuanced understanding of the depicted garments. #### **Image Segmentation:** Apply cutting-edge image segmentation methodologies, exemplified by Mask R-CNN or SAM, to differentiate various clothing items. This process effectively isolates clothing articles from the background, providing clear delineations that contribute to a detailed understanding of their spatial relationships and visual attributes. ### Kinetic Control System #### **Optimization Algorithms:** Reinforcement Learning: Adopt methodologies rooted in reinforcement learning paradigms, including Deep Reinforcement Learning (DRL), to facilitate the acquisition of optimal folding strategies through iterative learning mechanisms. #### **Exception Handling Algorithms:** Model Predictive Control (MPC): Implement MPC strategies for real-time adaptation of robotic arm dynamics, ensuring the accommodation of anomalous scenarios during the unfolding intricacies of clothing folding. Sliding Mode Control: Harness the robust attributes of sliding mode control mechanisms to mitigate uncertainties and adapt to dynamic variations encountered during the operational course. ## Criterion for Success The success of the Automated Clothing Recognition and Folding System will be measured based on the achievement of the following key criteria: **Precision in Folding:** The system must consistently fold various types of clothing items with a high degree of precision, resulting in neatly organized garments. **Integration of CV and Kinetic Control:** The successful integration of computer vision techniques for accurate clothing recognition (CV Assistance) and kinetic control algorithms (Kinetic Control System) to achieve optimal folding strategies. **User-Friendly Interface:** The interface must be intuitive and user-friendly, allowing users to interact easily with the system and monitor the folding process. **Safety:** Implementation of safety features is crucial to prevent accidents or damage to clothing items, ensuring a secure and risk-free operation. |
||||||
| 11 | Automated Chinese Traditional Chimes with Song |
Luting Lei Siyi Li Tianle Wu Xiaoxiao Pan |
design_document1.pdf design_document2.pdf final_paper1.pdf final_paper2.pdf final_paper3.pdf proposal2.docx |
Yu Lin | ||
| # Team Members - Tianle Wu (tianle3) - Luting Lei (lutingl2) - Siyi Li (siyili4) - Xiaoxiao Pan (xp8) # Problem Few people play Chinese traditional Chimes, and they're often stuck in traditional music, which seems to be a barrier of traditional instruments. Additionally, there are few research on blending modern music with Chinese traditional genres. By addressing these issues, the project is an invention contributes to Chinese traditional music instrument in a modern context and innovatively researches the possible music style transformation between model music and traditional Chinese music. # Solution Overview The project aims to revive the melody played by smartphones in the Chinese traditional Chimes. We will first recognize a melody from a smartphone and generate the adapted melody for chimes, then transform the melody to signals, and then control a mechanical design to ring the chimes with the motor. # Solution Components - Melody Recognition and Generating Model: The model will be trained to automatically recognize the main melody from a period of sound played by the smartphone and adapt to Chinese traditional style for chimes. - Electrical Control System: The system will transform the generated melody to location and time signals （for different pitches and rhythms) and build a microcontroller. - Mechanical System: A hammer structure hanging horizontally at the top of a series of chimes controlled by a motor. It will ring the corresponding chimes controlled by the electrical control system. # Criteria for Success - Training a machine learning model that could correctly recognize the melody from a smartphone (with noise). Apply the algorithm to adapt the recognized melody for chimes play. - Generating correct position and time signals and successfully controlling motor operation. - Easy and flexible structure for hammer ringing every chime. - Make the adapted music pleasant and make the whole structure as simple as possible. |
||||||
| 12 | A micro-penetrometer for snow and soil structural analysis |
Chenghao Mo Chenxian Meng Xing Shen Zheyan Wu |
design_document1.pdf design_document2.pdf final_paper1.pdf final_paper2.pdf other2.pdf |
Shurun Tan | ||
| # Problem When it comes to the disaster like avalanche bulletin and forest fires, we should investigate the landform with a specific technique. Also, this technique can deal with the snow profiling, ski track characterization or snow runaway characterization in snow. Understanding the structural integrity of soil and snow is vital for environmental management, agricultural practices, and civil engineering projects. Soil structure analysis informs us about the risk of erosion, the soil's ability to support plant life, and the stability of structures built upon it. Our project aims to fill the gap in on-site, accurate analysis of these structures and specifically designed for operation at low temperatures. By developing a portable and precise micro-penetrometer, we enable immediate, data-driven decision-making that can enhance safety, productivity, and environmental stewardship. # Solution Overview The main challenge of our project is to design an automated electronic control system capable of continuously drilling into different terrains, such as soil and snow, and using highly sensitive sensors at each location to record the penetration force and analyze the microstructural properties. The instrument must maintain a constant velocity during penetration, which requires a precise control mechanism. In addition, we need to design a mechanical system that is portable and field deployable to ensure operation in potentially harsh environmental conditions. We also need a software system to record real-time sensor data for subsequent analysis. Achieving such a high level of performance in a small, energy-efficient package that can withstand the rigors of varying ground conditions is a complex engineering task. It requires innovative approaches and collaborative efforts in mechanical, electrical and computer engineering to overcome these technical challenges. # Solution Components ## Control subsystem - piezo-electric force sensor with high accuracy to measure the penetration force at each location - the encoder of the motor ensures high accuracy in the vertical position - implement a feedback mechanism to adjust the drilling speed based on the resistance encountered. This will ensure optimal penetration regardless of varying soil or snow densities. ## Mechanical subsystem - the encoder of the motor ensures high accuracy in the vertical position - small brush can remove the snow from the gear teeth to avoid jamming of the motor and the rod - ski pols can be added to the measure unit to make the position stable - Li-Polymer battery to ensure the power of entire day - Aluminium profile to make the weight as light as possible so that it can be portable ## Software subsystem - Real-time data processing: To handle sensor input and control commands efficiently. - Data analysis algorithms: For interpreting penetration resistance and other measurements. - User interface: To display data and controls in an easily understandable format. - Data storage and export: For recording and sharing the collected data. - Potential integration of machine learning: For advanced pattern recognition in soil or snow structures. # Criterion for success There are three main criteria for the success of our project. The first is whether the device is portable. Compared to other similar products on the market today, we think that it’s successful if our device can be carried by one person on their back or by hand. The second criterion is to be able to ensure that the drill bit moves smoothly at a uniform speed through more precise electromechanical control. The final criterion is to have an algorithm that can read the snow or soil data within a reasonable margin of error. |
||||||
| 13 | Epicast: Augmented Board Game |
Di Wu Jianli Jin Yueshen Li Zihao Zhu |
design_document1.pdf design_document2.pdf final_paper1.pdf final_paper2.pdf other1.pdf proposal1.pdf |
Yushi Cheng | ||
| # RFA ## Team Member - Yueshen Li, yueshen7 - Jianli Jin, jianlij2 - Di Wu, diw10 - Zihao Zhu, zihao9 ## Title Epicast: Augmented Board Game ## Problem Dungeons & Dragons (D&D) is a game that thrives on the breadth of imagination and the depth of interaction. It empowers players to construct elaborate worlds and characters that stem from the vast expanse of their creativity. This unfettered freedom not only offers a canvas for creation and interaction but also makes each gameplay experience profoundly personal and distinct. However, the richness of these imagined scenes and environments is often bottlenecked by the need for verbal expression and lacks an intuitive, sensory display. This limitation hampers the visualization of the game's full potential, presenting a hurdle for some players and constricting the game's broader allure. In addition, the Dungeon Master (DM) which is one of the players serving as the game's narrative architect, is often burdened with extensive preparatory work, juggling game mechanics with storytelling, which can be arduous and time-consuming. ## Solution Overview "Project Epicast" is a comprehensive system designed to enhance the Dungeons & Dragons gaming experience. Central to this system is a GPT-powered AI that serves as an automated Dungeon Master, guiding gameplay with intelligent narrative creation and player interaction. The visual aspect is handled by an overhead projector, capable of displaying intricate game scenes, animations, and simulating actions such as dice rolls directly onto the gaming surface. Its height is adjustable for optimal image quality. Gesture recognition is enabled through a sophisticated camera, allowing for intuitive control and the ability to capture memorable moments. Audio immersion is provided by integrated speakers and microphones for voice commands, narrative flow, and dynamic sound effects. Completing the sensory experience are ambient lights that adjust to the game's mood, providing synchronized lighting effects. Lastly, while our focus is on enhancing the D&D experience, it's important to recognize that our board game experience-augmenting module has widespread applications. The demand for immersive, enriched board game interactions extends beyond D&D. Our target example of D&D serves as an ideal prototype for a broader market of board games seeking similar enhancements for a more engaging player experience. ## Solution Components ### [Real-time Data Processing System] Real-time data processing system is used to capture, process and generate data in Real time. It consists of a data transmission module, a sophisticated camera, a projector, an integrated speaker and microphone, and an ambient light set. - Data transmission module is responsible for transmitting the data obtained from sensors to the processing unit of the system. And it should be responsible for transmitting the next instructions of sensors from processing unit and some data that sensors need to express. This can be done through a wired or wireless connection. - Camera is the core component of the real-time data processing system, used to capture image or video data. Those data will contain vital information like people’s hand gestures. The camera can be an ordinary USB camera, or it can be a high-resolution, high-speed industrial-grade camera. - Projector is another core component of the real-time data processing system. Projection is a technique for projecting an image or video onto an object or plane. In our setting, the projector needs to project images on a wall or slab to inform players of the game status. And the processing unit should send those related data to projector in real time. Same as Camera, the projector can be an ordinary USB camera, or it can be a high-resolution, high-speed industrial-grade camera. - Microphone will gather the voice of people and transform them into digital audio, and speaker will transform the digital data sent by processing unit to real voice. An intergrated speaker and microphone will deal with voice input and output of our whole model. - Ambient light set is used to provide ambient light source, provide sufficient lighting conditions that can adjust to the game's mood. So that the light set will provide synchronized lighting effects to enhance the player’s experience. Also, the light set may help to improve the visibility and recognition ability of the image according to the camera feedback and improve the recognition accuracy and accuracy of the real-time recognition system. ### [GPT-Core DM System] GPT-Core DM system acts as an assistant to Dungeon Masters (DM), providing support and assistance during gameplay. Through modeling and data training, GPT-Core as Dungeon Masters assistant should perform the following some basic functions and complete the game: - **Generate adventure missions and plot**: The DM can provide some key information to GPT-Core, such as mission type, location, character, etc., and GPT-Core can then generate a complete adventure mission with a reasonable game plot including enemies, puzzles, rewards, etc. - **Generate player’s character and NPC (Non-Player Character)**: The DM can use GPT-Core to ask players’ requirement of their willing characters, and then generate out their corresponding characters with balanced properties such as their backstory, personality traits, goals, etc. Also, GPT-Core can generate and provide detailed information of many NPCs easily to enhance game quality. - **Generate other detailed information**: DM can use GPT-Core to generate any detailed information, for an environment such as the layout of the room, decoration, smell, etc. And GPT-Core can generate vivid descriptions of the environment, allowing the player to better engage with the game world. Also, for interaction of player’s character and NPCs, GPT-Core may help to provide detailed descriptions of NPCs’ reactions according to player’s operations. That will make user immerse into game better. ### [Sensor Assistance System] Most of the time, we need to adjust projector orientation to let it project the screen to place we want or the camara’s orientation to make players’ hand gesture be captured. Design in mechanical engineering involves the physical structure and installation of the projector and the camera. Here are some common design considerations: - **Mounting bracket**: To securely mount the projector and camera in the desired position, a suitable bracket or mounting bracket needs to be designed. These brackets should be able to adapt to different mounting environments and provide adjustable features to fine-tune projection angles and positions. - **Adjustment mechanism**: To facilitate adjustment and alignment of the projector and camera, adjustable mechanisms such as rotation and tilt mechanisms can be designed to adjust under different projection angles and positions. - **Cooling system**: Projector and camera, especially projector, will generate heat during operation, so an effective cooling system may be necessary to be designed to ensure the stable operation of the projector and prevent overheating. - **Dust and protection**: To protect the projector and camera from dust, moisture and other external factors, it is necessary to design appropriate dust and protection measures, such as filters, seals, etc. - Other possible small mechanisms can be provided further to assist the rest sensors... ## Criterion for Success - Hand gesture and audio detections based on AI model are applied to depict players’ action. - Split game sense projector region and gesture detect region which are supposed to be a multi-module integrated hardware system ought to improve game experience. - Create a Dungeon Master AI using GPT as a core. - Create a better experience with a free-moving projector and several ambient lights. ## Distribution of Work - Yueshen Li will work on identification module and real-time signal transition system - Jianli Jin will work on GPT-DM model building and data training - Di Wu will work on hardware appliance construction and data logging system - Zihao Zhu will work on realistic design and extension module combination. |
||||||
| 14 | Bird-Watching Telescope with Real-Time Bird Identification |
Haoxuan Du Junhao Zhu Tiancheng Lyu Yuhao Wang |
design_document1.pdf design_document2.pdf final_paper1.pdf final_paper2.pdf final_paper3.pdf proposal1.pdf |
Huan Hu | ||
| # **FEATURED PROJECT** ## **Bird-Watching Telescope with Real-Time Bird Identification** ### **PROBLEM:** When observing wild birds at a distance with a handheld telescope, due to the agility of the birds, before one can carefully identify or record the characteristics of the birds (appearance and call), they often fly away, making it difficult to determine the species. A smart telescope is needed to greatly assist bird watchers, especially beginners, and provide real-time identification of birds. ### **SOLUTION OVERVIEW:** The Bird-Watching Telescope is designed to help birdwatchers record the characteristics and identify the species of the bird immediately. The Bird-Watching Telescope integrates a camera, telescope, laser ranger, bird identification software on mobile phones developed by our team, and other functional circuits. Users can deploy the telescope wherever they want, and wait until a bird appears. After manual aiming and autofocus, the bird identification software will automatically identify the species of the bird. ### **SOLUTION COMPONENTS:** #### **Telescope Modules :** - The primary telescope able to tune the focus by hand, with space assigned for later electrical components beforehand. #### **Recording, Transmission & Annotation Modules:** - Real-time video recording through ocular lens, simple preprocessing to make it easier to transmit to mobile phone with Bluetooth. - LCD part to play the result sent from mobile phone in the oscular lens. #### **Identification Modules:** - Bird identification program, including video preprocessing, visual classification, identification result annotation signals. #### **Red-dot Focus Modules:** - The mechanical structure that can adjust the lens spacing, and the red-dot device. - Simple program to adjust the lens spacing with distance of the red-dot, which is put on the telescope. ### **CRITERION FOR SUCCESS:** - Functionality: This smart telescope can record through ocular lens, transmit recordings to mobile phone to process the identification. Identification results will be displayed via LCD screen on viewfinder and saved on mobile phone for users' convenience. An automated red-dot focus system can fine-tune the focus itself. - User experience: The user can obtain real-time information of bird species information while keep their eye on the telescope, regardless of their previous knowledge. They may also have the telescope self-finetune the focus onto birds using red-dot. - Environmental parameter detection: The smart telescope can get the recording of the birds from the ocular lens. For the red-dot finetune function, it can also get the distance between the red-dot and itself. - Processing stability: The identification processing part will be done on mobile phone offline to ensure speed, while the red-dot finetune will be just process and done on the telescope. - Program Package Update: The update can be simply done on mobile phone, which is very flexible and convenient, ready for future update when there are better programs or more bird species. ### **DISTRIBUTION OF WORK:** - ME STUDENT WANG YUHAO: Model the machine housing for the telescope with lens. Design the mechanical structure that can adjust the lens spacing. Manage the cooperation between software and hardware parts through the whole project from view of mechanical engineering. - ME STUDENT LV TIANCHENG: Model the machine housing for the telescope with lens, and assign the location for electrical components. Design the mechanical structure that can adjust the lens spacing. Assist the parameter adjustment of hardware parts with software parts. - ECE STUDENT ZHU JUNHAO: Responsible for software part. Struct and code the programs, later adjust parameter in tests for bird identification program & Red-dot focus fine tuning program. Solder the electrical circuits and assemble the physical product. - ECE STUDENT DU HAOXUAN: Mainly responsible for software part. Struct and code the bird identification program & Red-dot focus fine tuning program. Manage the cooperation between software and hardware part through the whole project from view of computer engineering. |
||||||
| 15 | Automated Pour-over Coffee Machine with Imitation Learning |
Jie Wang Jingyuan Huang Rucheng Ke William Qiu |
design_document3.pdf final_paper2.pdf final_paper3.pdf photo1.jpg proposal2.pdf |
Said Mikki | ||
| # RFA for Automated Pour-over Coffee Machine with Imitation Learning # Problem The art of pour-over coffee brewing, famous for its complex flavor and high quality, is heavily dependent on the skills and experience of a barista. This craftsmanship leads to variability in coffee quality due to human inconsistency. Additionally, it is challenging for common coffee enthusiasts to replicate professional barista techniques at home or in non-specialized settings. # Solution Overview We propose the development of **an intelligent Automated Pour-over Coffee Machine leveraging imitation learning algorithms**. This machine will mimic the techniques of professional baristas, ensuring consistency and high-quality in every cup. The project will involve designing a mechanical structure integrated with sensors and developing sophisticated software algorithms. # Solution Components ## Component 1: Mechanical Design - **Purpose:** To create a machine that can physically replicates the movements and precision of a barista. - **Features:** An adjustable nozzle for water flow control, a mechanical arm for simulating hand movements, and a stable structure to house the coffee dripper. - **Challenges:** Ensuring precise movement and durability of moving parts, and integrating the mechanical system with electronic controls for seamless operation. - **Expectation:** A workable, fixed coffee machine first, then upgrade it. ## Component 2: Sensors and Data Collection - **Purpose:** To gather precise data on barista techniques for the learning algorithm. - **Features:** High-precision sensors capturing data on water flow, angle, speed, and trajectory during the pour-over process. - **Challenges:** Accurately capturing the nuanced movements of a professional barista and ensuring sensor durability under varying conditions. ## Component 3: Imitation Learning Algorithm - **Purpose:** To analyze and learn from the collected data, enabling the machine to replicate these actions. - **Features:** Advanced algorithms processing visual and sensory data to mimic barista techniques, this requires to duplicate the state-of-the-art research result from Robotics field. - **Challenges:** Developing an algorithm capable of adapting to different styles and ensuring it can be updated as it learns from new data. ## Optional Components: - **Multimodal Origin Information Pre-Processing:** To adjust settings based on different coffee beans and grind sizes. - **User Interface Design:** An intuitive interface for user customization and selection of coffee preferences. - **ChatGPT Enhanced Custom Coffee Setting**: To make the machine more intelligent and like a human barista, SOTA artificial intelligence like LLMs should be involved to make it more a sort of an agent than a regular machine. # Criterion for Success - **Mechanical Precision:** The machine must accurately control water flow and replicate barista movements. - **Algorithm Effectiveness:** The machine should consistently brew coffee that matches or surpasses the quality of a professional barista. - **User Experience:** The interface should be user-friendly, allowing customization without overwhelming the user. - **Reliability and Durability:** The machine should operate consistently over time with minimal maintenance. - **Taste Test Approval:** The coffee produced must be favorably reviewed in taste tests against traditional pour-over coffee. |
||||||
| 16 | Intelligent fire protection ecosystem |
Honglei Zhu Jiawei Zhu Xiaohua Ding Yiyang Liu |
design_document1.pdf design_document2.pdf final_paper1.pdf final_paper2.pdf proposal1.pdf proposal2.pdf proposal3.pdf video1.mp4 |
Yu Lin | ||
| #TEAM MEMBERS: - Honglei Zhu - Jiawei Zhu (jiawei6) - Xiaohua Ding (xiaohua5) - Yiyang Liu (yiyang24) # PROBLEM Traditional fire protection systems often rely on outdated equipment and simplistic detection methods, leading to inefficiencies and potential safety hazards. Current smoke sensors, sound alarms, and manual alarm buttons lack the sophistication needed to accurately detect and respond to fire incidents promptly. Additionally, conventional systems may suffer from high rates of false alarms, causing unnecessary disruptions and desensitizing occupants to genuine threats. Moreover, the limited capabilities of traditional systems hinder their ability to adapt to evolving fire risks and environments. With the increasing complexity of modern buildings and the prevalence of diverse fire hazards, there is a growing need for intelligent fire protection solutions that can analyze fire information comprehensively, distinguish genuine threats from false alarms, and transmit critical fire signals remotely to safeguard lives and property effectively. # SOLUTION OVERVIEW Enhance the efficiency of conventional fire alarm apparatus while modernizing standard smoke sensors, auditory and visual alert systems, and manual alarm activation mechanisms. This advanced system is equipped with the capability to meticulously analyze data derived from fire sensors, enabling precise determination of fire occurrences. Additionally, it facilitates remote transmission of fire alerts, thereby ensuring swift responses to potential hazards, ultimately safeguarding both lives and property. # SOLUTION COMPONENTS ## BLUETOOTH CONTROL SYSTEM: - Apply a user-friendly mobile application interface for remote control and monitoring of the fire protection system via Bluetooth connectivity. - Implement secure Bluetooth communication protocols to ensure data integrity ## CIRCUIT SYSTEM: - Design and prototype circuit boards to integrate various sensors, alarms, and communication modules into a cohesive system. - Conduct rigorous testing and optimization of circuit designs to ensure reliability and efficiency in operation under different environmental conditions. ## SENSOR SYSTEM: - Research and select advanced smoke sensors with improved detection capabilities. - Integrate additional sensors for detecting environmental factors like temperature, humidity, and gas levels to enhance fire detection accuracy. ## PHYSICAL APPEARANCE SYSTEM: - Design aesthetically pleasing enclosures and housings for the fire protection system components, considering factors such as durability, ease of installation, and maintenance. - Incorporate visual indicators and status lights into the design to provide intuitive feedback to users about the system's operational status. ## DATA ANALYSIS SYSTEM: - Develop algorithms for real-time analysis of sensor data to accurately detect and classify fire incidents while minimizing false alarms. - Implement data logging and storage mechanisms to maintain a record of fire events and system performance for later analysis and optimization. ## USER INTERFACE SYSTEM: - Design intuitive interfaces for both physical control panels and mobile applications to facilitate user interaction with the fire protection system. - Conduct usability testing and gather feedback to refine the user interface design for enhanced user experience and accessibility. # CRITERION FOR SUCCESS ## RELIABILITY AND ACCURACY: The system should demonstrate consistent and accurate fire detection capabilities, minimizing false alarms while promptly identifying genuine fire incidents. ## REMOTE ACCESSIBILITY Users should be able to access and control the fire protection system remotely via Bluetooth connectivity or mobile application, ensuring timely response and management of fire-related emergencies. ## ENERGY EFFICIENCY Energy consumption should be optimized to maximize battery life and minimize environmental impact, ensuring continuous operation even during power outages. ## COMPLIANCE AND SAFETY The system should meet or exceed industry standards and regulatory requirements for fire protection, ensuring the safety of occupants and compliance with legal obligations. ## RELIABLE COMMUNICATION The communication system should demonstrate high reliability and resilience, ensuring seamless transmission of fire alerts and system status updates to designated recipients in real-time. # DELIVERABLES - Fire alarm signal remote reminder, alarm signal transmission to cell phone applet and cell phone SMS reminder - Linkage control between devices, detecting the fire signal can be linked to trigger the sound and light alarms. - A variety of fire information collection, carbon monoxide, smoke concentration, temperature sensor specific values, human infrared signal detection, comprehensive analysis of big data to reduce the probability of false alarm trigger - Development of fire information feedback platform, a fire alarm signal can be analyzed according to the data of a variety of detectors, to build fire models - Design a fire control host, able to unify control # DISTRIBUTION OF WORK - ME Student Xiaohua Ding and Honglei Zhu perform product design and design shelves for final display. - EE Student Jiawei Zhu and Yiyang Liu is responsible for writing Bluetooth transmission programs and designing the virtual circuits associated with them. - All team members are involved in PCB soldering, circuit debugging and assembly. |
||||||
| 17 | Arduino-Powered Network Flow Visualization Toolbox |
Bolin Zhang Jiahao Fang Yiyang Huang Ziyuan Chen |
design_document2.pdf design_document3.pdf final_paper1.pdf final_paper2.pdf final_paper3.pdf proposal1.pdf proposal2.pdf video |
Pavel Loskot | ||
| ## PROJECT DESCRIPTION Many real-world systems involve flows over networks. Our team aims to build a **modular, reconfigurable hardware emulator** to visualize network flows under capacity constraints on links. Each node can be configured to act as a sink, a source, or a "transfer station" that holds zero flux. This toolset will facilitate the understanding of flow optimization algorithms in a classroom setting. ## SOLUTION OVERVIEW We use a scalable design where components are easily replaceable to account for network expansion. The emulator should have a central Arduino controller that talks to each node and link to display the capacities and actual flow amounts. *Tentative: It may be desirable to have a software GUI to display the network alongside the physical model due to space (# LEDs) and protocol (# pins) constraints in each node/link.* ## SOLUTION COMPONENTS ### Subsystem 1: Physical Network Model - We should build a fully functional physical model where pipes represent network links and the LEDs within show the maximal capacity and real-time flow of "data packets." - Each node should be configurable as sink, source, or neither ("transfer station") with a user-friendly interface such as buttons or switches. ### Subsystem 2: Software Flow Computer - We should build an intuitive software interface that allows the user to easily configure nodes (3 modes) and links (capacity) while controlling the LED flow display. - We should implement a robust and *lightweight* optimization algorithm that efficiently computes network flows on an embedded Arduino board while considering all constraints (node configurations, link capacities). - Alongside the design process, we should write comprehensive documentation detailing the manuals for software setup, operation, troubleshooting, and our development process. ## CRITERION OF SUCCESS - The physical model should be modular, i.e., each node has a certain number of "slots" reserved for installing new links (pipes). - The Arduino software should communicate with all nodes and pipes and update the flows in real-time in response to changes in setup. At the current stage, we aim to serve 4~6 fully connected nodes. - The algorithm should handle (and report) edge cases such as a network with zero or multiple feasible flows. ## DISTRIBUTION OF WORK - Ziyuan Chen (ECE) - software developer: maintain the code for flow optimization and Arduino-hardware communication protocol - Bolin, Jiahao (EE) - hardware developer: handle the physical layout of peripherals (pipes and LEDs), design user interface - Yiyang Huang (ME) - integration and testing specialist: design the protocol for node configuration and conduct stress tests in edge cases |
||||||
| 18 | Wireless Fast Charging Autonomous Car |
Yiquan Jin Yizhi Li Ziyue Guo Zongyang Zhu |
design_document1.pdf final_paper1.pdf final_paper3.pdf proposal1.pdf |
Chushan Li | ||
| # Problem An autonomous car with wireless fast charging capability (Pin≥100W) is proposed. The car can automatically detect the place of wireless charging station and drive to the station with fast speed. # Solution Overview - An autonomous car with energy storage and fast speed - The wireless charging power Pin ≥ 100W - Car can automatically align to the charging coils - Car can detect the place of wireless charging station. - Obstacles can be avoided during the driving - Car can fully utilize its mechanical structure and shock absorption system to work on various road condition # Solution Components ## Hardware Components: - Autonomous Driving Car Prototype: Developed a prototype of an autonomous driving car capable of autonomous navigation and driving functions, including sensors, control units, actuators, and designed the car's exterior and shock absorption structure. - Wireless Charging System: Designed and implemented a wireless charging system capable of delivering over 100W of power, including hardware devices for the charger and car receiver end. - Positioning and Navigation Equipment: Integrated high-precision positioning and navigation equipment to enable the car to navigate and plan routes in complex environments. ## Software Components: - Autonomous Driving Software: Developed a comprehensive autonomous driving software system, including environment perception, path planning, control algorithms, etc., capable of achieving safe and stable autonomous driving functions. - Charging Alignment Algorithm: Implemented precise charging alignment algorithms, capable of accurately identifying the position of charging stations and automatically aligning the car with the charging coils, ensuring charging efficiency and safety. - Obstacle Detection and Avoidance Algorithms: Developed efficient obstacle detection and avoidance algorithms, capable of timely identifying obstacles on the road and taking appropriate measures to avoid collisions. - Charging Station Position Detection Software: Implemented charging station position detection software, capable of accurately identifying the position of charging stations and planning the optimal route to reach the charging station. # Criterion for Success Our ultimate goal is to develop an autonomous vehicle with energy storage and high-speed capabilities, equipped with wireless fast charging (Pin ≥ 100W). It should automatically align with charging coils, detect the location of wireless charging stations, navigate around obstacles during driving, and fully utilize its mechanical structure and shock absorption system to adapt to various road conditions. |
||||||
| 19 | Smart Power Routing with MPPT-Based Wind Turbine |
Rong Li Tiantian Zhong Zhekai Zheng |
design_document3.pdf final_paper3.pdf proposal2.pdf |
Lin Qiu | ||
| ## Problem Statement Traditional wind energy systems often face challenges related to suboptimal power extraction, limited adaptability, and inadequate integration with smart grids. Conventional wind power systems usually requires a giant turbine which produces power for the grid. Yet a new trend arises in recent years where a small wind power system is installed on a fisher or on the roof of a villa. Such scenario requires a stable power converter and router to ensure stable power supply, which not only allows the user to use cheap and clean wind energy, but is also able to switch to battery or mains when wind force is too light to drive the turbine or when the turbine is in fault. ## Solution Overview and Components The proposed solution involves the development and implementation of the system integrated with a MPPT-based wind turbine. This comprehensive solution aims to address the inefficiencies and limitations of traditional wind energy systems by incorporating advanced technologies for optimal power extraction, intelligent management, and seamless integration with smart grids. Some key components of the solution are as follows: 1. **Wind turbines.** The project plans to use a three-phase asynchronous motor to build a down-scaled wind turbine. The turbine should produce no more than 30 V AC output under normal weather condition with wind speed less than 8 m/s (force 4). (Similar turbine with suitable size (diameter = 1.1 m) for the project appears on Taobao, which has rated output voltage 12 V, maximum power ranges from several hundred watts to kilowatts, and can work safely within wind speed 35 m/s (wind force 6). Link to the turbine) 2. **MMC-Based AC-DC converter.** This unit is expected to provide stable DC output for users. Its controller consists of MCUs and voltage sensors. The converter should be designed using MMC technology and should be able to implement Maximum Power Point Tracking (MPPT). 3. **User interface.** This unit displays real-time current, voltage and power of the system. 4. **Simulated mains.** This is a low-voltage (<30 V) power supply that simulates the mains. It is apparently down-scaled for safety considerations. 5. **Routing system.** This unit should be able to decide which power should be connected to the load, the turbine or the simulated mains. 6. **Safety.** An emergency stop button should be connected to the circuit in order to cut off all power sources and stop the turbine whenever an emergency happens. Control units should be able to cut the power when the system is overload or in fault status. The solution should fit in relevant national or industrial standards. ## Criterion for Success The design will be tested using various common loads that is used at home. The following criterion should be satisfied to indicate a successful design: 1. **Safety is the first priority**. All safety measures should be working properly. 2. The controller should be able to keep the converter working at the maximum power point. 3. The MMC converter should be able to provide stable output with current and voltage ripple less than $\pm10\%$. 4. The controller should switch between power supplies within a short period of time (specific time limit needs to be determined after further research on relevant national standards and other technical documents). ## Distribution of Work The project can be divided into three modules – the power system, the control system, and the mechanical system. - The power system deals with everything related to power transmission, include the design of generators and converters. - The control system provides control signals to the converter, properly routes power to the load, and provide safety measures. - The mechanical design should put every hardware components organized to form a ready-to-use product, and print necessary instructions and warnings at proper places. The following is the detailed task division: - Power system and circuit design: Rong Li & Zhekai Zheng - Control system and circuit design: Tiantian Zhong & Rong Li - Mechanical design and manufacturing: Zhekai Zheng - Purchasing, finance, and other miscellaneous affairs: Tiantian Zhong |
||||||
| 20 | Touch Controlled Programmable DC Power Supply Circuit |
Chaoli Xia Sichen Wang Weisong Shi Yiyi Wang |
design_document1.pdf final_paper2.pdf final_paper3.pdf proposal2.pdf |
Aili Wang | ||
| # MEMBERS: - **Weisong Shi** weisong4 - **Chaoli Xia** chaolix2 - **Yiyi Wang** yiyi4 - **Sichen Wang** sichenw2 # TITLE: **Touch Controlled Programmable DC Power Supply Circuit** # PROBLEM: Numerous electronic devices are powered by varying DC voltage levels. For instance, cell phones, watches, and Kindles all require a 5V voltage adapter, whereas a laptop adapter supplies the motherboard with 12V. There are a variety of models, standards, and power supply methods for electronic devices, which can make powering them both inconvenient and problematic. Accommodating these diverse standards can be challenging. So in this project, we aim to build an intuitive, touch-controlled and programmable DC power supply to avoid the limitations. # SOLUTION OVERVIEW: The aim of this project is to develop printed circuit board (PCB) level touch-controlled programmable DC power supply circuits that can accommodate these diverse DC voltage levels. Its configuration adjustments are initiated by touch, fusing technology. The design integrates an AC-DC converter, variable regulated power supply, touch control circuit, and short circuit protection, creating a flexible and safe power supply solution. # SOLUTION COMPONENTS: - **AC-DC Converter:** This component efficiently converts AC to DC to power the circuit. It includes a step-down transformer, a bridge rectifier, a low-pass filter circuit, an LED indicator, switch and fuse to ensure efficient and reliable power conversion. - **Variable Regulated Power Supply Circuit:** This component provides a stable and adjustable DC output to fulfill diverse voltage requirements. It includes Variable voltage regulator from TI or ADI, and variable voltage control circuits for outputting different voltage levels. - **Touch Control Circuit:** This component allows touch-sensitive controls for user interaction.It includes touch sensors (touch plate), digital IC and other circuits to produce control signal for the variable voltage control circuits. - **Short Circuit Protection Circuit:** This component ensures the safety of the circuit and the connected devices by detecting and preventing short circuits. It includes current sensors and overcurrent protection components. # CRITERION FOR SUCCESS: - **Diverse Voltage Accommodation:** The power supply circuit should be able to efficiently supply a wide range of DC voltage levels to meet diverse application requirements. - **Touch Controlled:** The touch-controlled system should be intuitive and responsive. - **Short Circuit Protection:** The circuit should effectively detect and respond to short circuits. - **Stablity and Reliability:** * The variable regulated power supply should deliver stable and accurately regulated DC output under varying load conditions. * The PCB design should be reliable and efficient. # DISTRIBUTION OF WORK: - **Weisong Shi & Chaoli Xia (ECE):** * Design and implement the touch control circuit. * Develop the algorithm for short circuit detection and protection. - **Yiyi Wang & Sichen Wang (EE):** * Design the AC-DC converter circuit, considering efficiency and safety. * Design the variable regulated power supply circuit, considering the stability and the voltage range. - All the team members will contribute to the documentation, including circuit diagrams, PCB layouts, and code documentation. We will also collaborate on testing the integrated system to ensure the functionality. |
||||||
| 21 | Campus Tour Guide by AI-Powered Autonomous System |
Bob Jin Hao Ren Weiang Wang Yuntong Gu |
design_document1.pdf design_document2.pdf design_document3.pdf final_paper2.pdf final_paper3.pdf proposal1.pdf |
Simon Hu | ||
| This [link](https://accurate-ringer-067.notion.site/Campus-Tour-Guide-by-AI-Powered-Autonomous-System-f4d17e16378740e2948f5bef4afd7315?pvs=4) contains the html version of our project description. # Team Members * Hao Ren 3200110807 haor2 * Xuanbo Jin 3200110464 xuanboj2 * Weiang Wang 3200111302 weiangw2 * Yuntong Gu 3200110187 yuntong7 > 💡 Note: this doc provides an overview of the project “Campus Tour Guide by AI-Powered Autonomous System”. We start by re-iterating the problem. We then present our proposal and solution. We also draft an initial plan to help build `v0`solution. # 👀 Problem Anyone entering a place for the first time, like an university, can be quite challenging. Knowing where you are, how to get to your destination, how to optimize your routes, knowing factors that will influence your routes can be complicated. Having a real-time interactive system that guides people through this process is needed. It has been possible yet not able to scale because it’s not open-sourced, and its hardware isn’t standardized, and is expensive. The interaction isn’t versatile enough to adapt well under the ever-changing applications. A cheap and versatile solution is needed. ------ # 💭 Proposal ## Solution Overview Our solution utilizes autonomous UAV to guide our clients, sensing them and the environment, such as obstacles and drone’s location with a sensor module, controlled by a control unit which orchestrate a series of tasks. Our solution is cheap, open-sourced, and versatile to meet the need of a generalized and sustainable long-term solution for our campus and many other applications. ## Solution Components Our solution contains the following parts: a sensor subsystem, a control subsystem, a mobility subsystem, an inter-connect module. ### Sensor Subsystem - Identify obstacles - Identify the person to lead, exclude the other people - GPS location ### Control Subsystem - Deploy routes ### Mobility Subsystem - A drone ### Inter-connect Module - Inter-communication of control unit, peripheral sensors, and the drone - Supply power to the sensor module and control unit. ## Criteria for Success ### Milestone 1 - drone can be controlled and moved independently - GPS can sense the location - Sensors can be powered ### Milestone 2 - Drone can be controlled by control subsystem - control subsystem can receive signal from GPS module and sensors - Routes can be output (not necessarily by moving the drones) ### Milestone 3 - Without obstacle, the system can follow the human - Without obstacle, the system can fly from A to B and slow down / stop when human is too far away - System can identify obstacle and plan a route to avoid them ### Milestone 4 - With obstacle, the system can fly from A to B and slow down / stop when human is too far away - The starting point and ending destination pairs can be selected, e.x. 5 pairs of (A,B) is available. ### Milestone 5 [optional] - An easy web app which sends signal to the system - System can receive our instruction (vocal) and design a destination and lead the clients - Support interactive chatting mode to help understand the surroundings ## Alternatives *SKYCALL* currently provides a similar version of guiding tour for MIT. But that project isn’t open-sourced and the hardware are not cheap enough, or easy-to-maintain. Our solution is different in that we provide - Cheap solution - Open sourced solution (software + hardware), each component will be documented - Unnecessary functionality will give its way to generality - Versatile enough to support our campus (which is drastically different to MIT) ------ # 🛫 Division of Work - Xuanbo Jin: Xuanbo excels at software works. He should do the algorithm part of the design and also takes part in the firmware integration. - Yuntong Gu: Yutong’s strong background at electrical engineering makes him a great candidate to test the validity of different hardware and connect them to the object. He should also helps the communication between each components. - Weiang Wang: Enabled by weiang’s strong background in electrical engineering, he should actively helps the communication and interfaces between components. - Hao Ren: Hao can do assorted works. Hao should actively do the software and firmware part of the work. Hao should explore the validity of possible direction and iterate the version of the projects properly. Hao should organize the roadmap and update it frequently, examining the priority of each part by experimentation and analysis. |
||||||
| 22 | Fingerprint Recognition Door Lock |
Chengrui Wu Hanggang Zhu Haoran Yuan Lizhuang Zheng |
design_document1.pdf final_paper1.pdf final_paper2.pdf final_paper3.pdf proposal1.pdf |
Meng Zhang | ||
| # Team Members Chengrui Wu (cw70) Hanggang Zhu (hz66) Haoran Yuan (haorany7) Lizhuang Zheng (lzheng17) # Project Title Fingerprint Recognition Door Lock # Problem In our Residential College dormitories, each room door requires a student IC card to unlock. However, sometimes students may forget to bring their own card with them when they are out. The current solution is to apply for a temporary card, so a fingerprint recognition door lock can be a better solution. Currently, most fingerprint recognition door locks are integrated units. To install a new one, users must remove the entire old lock, typically requiring professional assistance. But updating all the locks in the Residential College is a huge project, and may affect students’ daily life. Thus, we propose a more user-friendly solution that allows users to integrate advanced fingerprint recognition technology with their current locks, without the needs of extensive installation processes, so that students can install the device by themselves. # Solution Overview We aim to create a smart, compact device that can be added to existing locks, enabling fingerprint-based unlocking. So that students can install the device easily by themselves. This device will feature a fingerprint recognition module, a control unit, mechanisms for lock interaction, a mobile app for management and GPS integration, and a wireless communication module. Besides, a security module and a power supply module are needed to support other subsystems. # Solution Components ## Capacitive Fingerprint Sensor Module This module will feature a state-of-the-art capacitive fingerprint sensor, known for its high sensitivity and accuracy in capturing detailed fingerprint images. It is designed to efficiently transmit high-resolution fingerprint image data to the Fingerprint Recognition Subsystem. The sensor's advanced technology allows it to quickly and accurately read a fingerprint, even under varying environmental conditions. Its compact size and low power consumption make it an ideal choice for integration into the smart door lock system. The sensor will be interfaced with the STM32 development board, ensuring seamless communication and data transfer between the sensor and the Fingerprint Recognition Subsystem. ## Fingerprint Recognition Subsystem This will be a high-precision module with algorithms capable of accurately identifying the user's unique fingerprint patterns. It will also be able to store multiple fingerprints the user registered, for shared use among the user and other authorized individuals. The code implementation will be written into STM32 develop board to output True/False signal to the downstream controller subsystem. ## Controller Subsystem This will be a microcontroller that manages the operations of the device, including processing fingerprint data, controlling lock mechanisms, and coordinating with the mobile app and a wireless communication module designed to retrieve messages from the app. We may choose a STM32 develop board with Wi-Fi module as the platform. ## Software UI A mobile app for fingerprint recording and remote lock control. It will allow users to manage their fingerprints, remotely control the lock, and adjust settings such as auto-lock and unlock. It will also provide notifications about lock status and usage. ## Wireless Communication Module An ESP8266 microchip for Wi-Fi connectivity with secure protocols, and a GPS module for location tracking. The microchip will provide the device with Wi-Fi connectivity to communicate with the mobile app, receive updates, and enable remote access and control. The module will also use secure protocols to ensure data privacy and security. Based on the GPS location of the users’ mobile phone, it will allow the lock to unlock automatically when the user's phone is nearby, and lock automatically when it is too far away, ## Security Module The security module ensures secure wireless communications and app usage, prevents unauthorized access, and verifies user identity. It uses advanced encryption for data transmission and includes mechanisms for detecting and reporting security breaches. ## Mechanical Engine An actuator to engage/disengage the existing lock mechanism. These will be designed to be compatible with the dorm lock design and will physically engage and disengage the lock mechanism in response to input from the control unit. ## Power Supply Subsystem This system will include a battery and other components used to power up all the subsystems above, it should be able to last for a significant period. # Criterion for Success - Efficient and accurate fingerprint-based unlocking. - Remote access and control of the lock's status through the app, ensuring exclusive user access. - Ease of installation and removal from the existing lock, with robust security. - Lock the door from inside, when the person is left # Distribution of Work - Chengrui Wu: Microcontroller and Software App - Hanggang Zhu: Software App, Fingerprint Recognition and Security Module - Haoran Yuan: Wireless Communication and Fingerprint Recognition, Chip and sensor selection. - Lizhuang Zheng: Mechanical Engine, Microcontroller and Power Supply Subsystem |
||||||
| 23 | Clickers For ZJUI Undergraduate Mk Ⅱ |
Benlu Wang Luozhen Wang Suhao Wang Zhenyu Zhang |
design_document1.pdf final_paper1.pdf final_paper2.pdf final_paper3.pdf proposal1.pdf proposal2.pdf |
Fangwei Shao | ||
| # TEAM MEMBERS Zhenyu Zhang (zhenyuz5) Benlu Wang (benluw2) Luozhen Wang (luozhen2) Suhao Wang (suhao2) # PROBLEM I-clicker is an educational tool employed by ZJUI to fulfill the digital demands of the classroom, serving as a class check-in and answer device. However, the existing transmitters and receivers face limitations in terms of their capacity to handle substantial loads, high signal delay, and signal loss. These constraints hinder the device's ability to effectively meet the requirements of a large number of users. Additionally, the current I-clicker system fails to cater to the preferences of students who prefer to utilize mobile applications for participation. # SOLUTION OVERVIEW This project aims to design and develop a comprehensive classroom response system that supports multiple frontends, including web browsers, mobile applications (iOS and Android platforms), WeChat Mini Programs, and physical Clickers. Additionally, a user-friendly web-based interface will be created to provide teachers with intuitive management functionalities. The system incorporates a high-concurrency unified backend equipped with distributed and in-memory databases, offering caching capabilities to efficiently handle large volumes of student submissions, as well as perform evaluation and statistical analysis. The project also entails the shell design and implementation of a distributed and energy-efficient transmission system for the physical Clickers and their receivers to address the limitation of signal loss. # SOLUTION COMPONENTS This project encompasses four essential components: frontend development, backend optimization, hardware improvement, and enclosure design. ## Frontend Development: For instance, we can develop a user-friendly web-based interface using popular frontend technologies such as HTML, CSS, and JavaScript. This interface can be accessible through standard web browsers on various devices, offering teachers the flexibility to manage the voting result. Additionally, as part of the meticulous frontend development process, the project aims to provide students with diverse options to interact with the voting system. As we possess a physical clicker as part of our system, our commitment lies in ensuring compatibility and functionality between the mobile app and the physical clicker, allowing both to transmit signals that can be effectively processed by the receiver. Furthermore, if time permits, the project can also develop WeChat Mini Programs. These lightweight applications within the WeChat ecosystem provide a seamless and familiar voting experience for students who prefer to use the WeChat platform. ## Backend Development: By constructing a high-concurrency unified backend, fortified with distributed and in-memory databases, the system will be empowered with caching capabilities capable of effectively managing the influx of student submissions. In this scenario, the system can employ a distributed database system, such as Apache Cassandra or Amazon DynamoDB, to handle the storage and retrieval of student submissions. By distributing the data across multiple nodes, the system can benefit from increased scalability and fault tolerance. To further enhance performance, an in-memory database, such as Redis or Apache Ignite, can be utilized as a caching layer. This allows frequently accessed data, such as student responses and evaluation results, to be stored in memory for faster retrieval, reducing the need to repeatedly access the distributed database. ## Hardware Improvement: Recognizing the significance of enhancing reception capabilities, the project dedicates attention to the development of a distributed and energy-efficient transmission system for the physical Clickers and their corresponding receivers. The voting system incorporates a System-on-Chip (SoC) solution to handle both the transmitter and receiver functionalities. The SoC, such as ESP32 or STM32, integrates microcontroller capabilities and offers built-in wireless connectivity options like Wi-Fi or Bluetooth. The SoC transmitter facilitates the transmission of votes from the voting devices to the central system using its dedicated peripherals for user input. The SoC receiver receives the transmitted votes, establishes a reliable connection with the voting devices through Wi-Fi or Bluetooth, decodes the received data, and manages the voting information effectively. This integrated approach utilizing SoC technology ensures seamless bidirectional communication, efficient data transmission, and reliable vote collection within the voting system. ## Enclosure Design: In addition to the technical facets, the project encompasses the meticulous design of an enclosure, using 3D printing technology, specifically tailored for the physical Clickers. This component embraces the principles of aesthetics, functionality, durability, ergonomics, and user-friendliness. By prioritizing these design considerations, the enclosure aims to enhance the overall user experience, ensuring that the physical Clickers are comfortable to handle and operate. # CRITERION FOR SUCCESS Concurrency Handling: Build a high-concurrency backend system for efficient processing of large volumes of student submissions concurrently. Affordability: Develop cost-effective i-clickers to promote widespread adoption and accessibility for students. Support for Multiple Frontends: The system should be designed to support multiple frontends, including mobile applications, web browsers, and dedicated software, ensuring compatibility, seamless interaction, and consistent user experience across various platforms. Signal Stability: Ensure reliable signal reception in challenging environments and minimize signal loss within classrooms. Distributed and Energy-Efficient Transmission: Implement a distributed transmission system with low-power consumption to optimize device performance and energy efficiency. Aesthetic Design: Create visually appealing i-clicker shell designs that are widely accepted and facilitate customization through 3D printing. # DISTRIBUTION OF WORK Benlu Wang: Responsible for designing and developing web-based interfaces, mobile applications, and WeChat Mini Programs to provide a range of frontend options for students to interact with the voting system. Zhenyu Zhang: Tasked with optimizing the backend infrastructure, including the development of a high-concurrency unified backend, distributed and in-memory databases, and efficient data management for seamless operations. Luozhen Wang: Responsible for designing and creating customized enclosures for the physical Clickers using 3D printing technology, ensuring an aesthetically pleasing, functional, and user-friendly design. Suhao Wang: In charge of improving the hardware components of the voting system, particularly focusing on the development of a distributed and energy-efficient transmission system using System-on-Chip (SoC) technology. |
||||||
| 24 | Autonomous Transport Car |
Size Feng Xinyue Lu Zhixin Chen Zhuozheng He |
design_document1.pdf final_paper1.pdf final_paper2.pdf final_paper3.pdf proposal1.pdf |
Chushan Li | ||
| ## Team Members - Zhixin Chen(zhixinc3) - Zhuozheng He(zh37) - Size Feng(sizef2) - Xinyue Lu(xinyue15) ## Problem We have found that most warehouses still use manual management for inbound and outbound operations. This mode requires a high level of manual labor. Therefore, we decided to design a small autonomous vehicle for small warehouses that can automatically pick up pieces. The car will find the designated goods as needed, move them away, and place them in the designated area. This design can simultaneously avoid picking up goods by mistake and reduce the pressure and cost of warehouse management. ## Solution Overview Our car will be tested and displayed in a simplified shelf environment designed by ourselves. The shelf environment will consist of several arranged shelves, guide lines on the ground, and several demonstration goods with RFID chips. The car will find the corresponding goods based on the information provided in the app, and use the mechanical structure to grab them and place them on the designated platform. If time permits, we will optimize for car movement speed, gripping speed, and the app platform human-computer interaction. ## Solution Components ### Mechanical Subsystem - Car subsystem: The car will plan the optimal route based on the location of the goods and travel faster along the predetermined trajectory on the ground. - Grab subsystem: After the car comes to a stop, the robotic arm can move to the designated position and grab the goods without touching other objects. Always hold onto the goods until they are transported to the designated pickup platform. - Identify subsystem: Using RFID technology to identify the specific location of goods on the shelves. We will place RFID chips on the goods in advance. - Interactive subsystem: Use the mobile app to give instructions to the car to retrieve the goods. The mobile app will receive feedback that the goods have been placed on the pickup platform or do not exist. ### Power Subsystem The driving PCB board of the car, the driving circuit of the robotic arm, and the circuit recognized by the RFID chip are independently powered. ### Criterion for Success - The car can travel along the trajectory at a fast speed to a designated position. - It can correctly identify the goods that need to be grabbed - The mechanical structure on the car can grab the goods on the shelves and transport them - A simple app for issuing instructions and receiving feedback |
||||||
| 25 | Airport Baggage Robot |
Jiajun Hu Xuchen Ding Yixuan Li Yuhao Wang |
design_document1.pdf design_document2.pdf design_document3.pdf final_paper1.pdf final_paper2.pdf proposal1.pdf proposal2.pdf |
Liangjing Yang | ||
| # Team Members - Jiajun Hu jiajunh5 654970401 - Yixuan Li yixuan19 - Yuhao Wang yuhaow7 - Xucheng Ding xuchend2 # Title Airport Baggage Robot # Problem Carrrying bags in airport is somehow inconvenient, because airport is to large and you need to carry the bag for a long time. We want to free our hands. # Solution Overview We plan to build a wheel-legged robot to carry the bags for customers. You can place the bag on this robot and it will automaticlly follow you via computer vision to the boarding gate. The leg control algorithm allows this robot to cross barriers like steps and steep ramps. # Solution Components ## Subsystem 1 The gyroscope system used to balance the leg wheel robot ## Subsystem 2 5-links solver algorithm to control the position of robot legs to balance the robot. ## Subsystem 3 The visual algorithm is used to identify the following users and the path planning algorithm is used to plan the route and achieve the goal of avoiding obstacles. Since we are solving with the visual solution, so we will simply use a high resolution camera for recognition instead of 12 Vehicle radars. And the other components are mainly software-level. # Criterion for Success 1. The robot is able to balance itself 2. The robot can adapt to different weights by adjusting its posture 3. At least can identify the person and follow the person. What is more, if the tracking path has obstacles, it can avoid them. # Distribution of Work - Jiajun Hu: CAD model - Yixuan Li: Construction of robot - Yuhao Wang: Control algorithms - Xuchen Ding: PCB |
||||||
| 26 | Teaching Heat to Student |
Kaihua Hu Tianyu Feng Yongxin Xie Ziang Liu |
design_document1.pdf final_paper1.pdf final_paper2.pdf proposal1.pdf video1.mp4 |
Wee-Liat Ong | ||
| # Team Member - Kaihua Hu, kaihua2 - Tianyu Feng, tianyuf2 - Yongxin Xie, yjie3 - Ziang Liu, ziangl4 # Title Teaching Heat to Student # Problem The need for an effective and engaging educational tool to introduce elementary and middle school students to fundamental concepts of heat transfer and thermal energy conversion. # Solution Overview We propose the design and manufacture of an integrated thermal experiment platform that provides a safe and hands-on environment for students. The platform will include visual demonstrations of heat conduction and convection, a coating for thermal radiation visualization, and an introduction to thermoelectricity. # Solution Components ## Subsystem 1 Use a metal rod with one end heated and temperature sensors to detect every temperature on certain position, then visualize it on a computer. And we can use another hollow metal rod with fluid in it, detect and visualize the temperature in same way and show the influence of convection. ## Subsystem 2 Demonstrate the principle of electric heating material which could generate current when people put their hands on it and light up LEDs displaying 'ZJUI'. ## Subsystem 3 Design a coating material which could reflect certain wavelength of a light source and allow the electronicmagnetic wave from human to pass through. Demonstrating a scenario that people could feel cool with this material when received heat source radiation. # Criterion for Success - Engaging and safe educational experience. - Clear understanding of heat transfer concepts by students. - Successful demonstration of thermal radiation and thermoelectricity. # Distribution of Work - Kaihua Hu: Design and Manufacturing - Tianyu Feng: Design and Manufacturing - Yongxin Xie: Control and Electrical circuit - Ziang Liu: Control and Electrical circuit |
||||||
| 27 | Supernumerary Robotic Limbs |
Haotian Jiang Xuekun Zhang Yichi Zhang Yushi Chen |
design_document1.pdf design_document2.pdf final_paper1.pdf final_paper2.pdf proposal2.pdf proposal1.pdf |
Liangjing Yang | ||
| # TEAM MEMBERS Haotian Jiang (hj24) Yushi Chen Yichi Zhang Xuekun Zhang(xuekunz2) # PROBLEM Supernumerary Robotic Limbs (SRLs) have emerged as a fascinating advancement in the field of robotics, offering the potential to augment human capabilities by providing additional robotic limbs. However, a significant current problem plaguing the implementation of SRLs revolves around integration challenges. The seamless coordination between these robotic limbs and the user's natural limbs remains a complex issue. Achieving intuitive and synchronized control over the supernumerary limbs, ensuring they move in harmony with the user's intended actions, poses a considerable technological hurdle. Additionally, the current state of SRLs faces limitations in adaptability to various tasks and environments, hindering their practicality. # SOLUTION OVERVIEW 1. Seamless Coordination and Control: One of the main challenges is achieving intuitive and synchronized control between SRLs and the user's natural limbs. This requires advanced sensor technologies and algorithms capable of interpreting human intent and translating it into precise robotic movement. Solution Ideas: Advanced Sensory Feedback: Implementing a sophisticated sensory feedback system that can accurately detect and interpret the user's movements and intentions. This could involve a combination of technologies like electromyography (EMG) to read muscle signals, motion sensors, and perhaps even neural interfaces. Machine Learning Algorithms: Developing algorithms capable of learning and adapting to the user's movement patterns. Machine learning can help in predicting and synchronizing the movements of the robotic limbs with the user's natural limbs. Haptic Feedback: Integrating haptic feedback into the SRL system can provide the user with tactile information about the limb's position and the forces it encounters, enhancing control. 2. Adaptability to Various Tasks and Environments: SRLs need to be versatile enough to perform a wide range of tasks in different environments, which is a challenging aspect of their design and functionality. Solution Ideas: Modular Design: Creating a modular SRL system where different types of limbs or tools can be attached and detached as needed could provide the versatility required for different tasks. Environment Sensing and Adaptation: Incorporating sensors that allow the SRL to understand and adapt to different environments. This could involve visual recognition systems, lidar for spatial awareness, or other environmental sensors. User-Defined Customization: Allowing users to customize the settings and behavior of the SRLs for specific tasks could enhance their practicality in various scenarios. 3. User Training and Interface Design: Another critical aspect is how users interact with and control the SRLs. The learning curve and ease of use are important for wide adoption. Solution Ideas: Intuitive User Interfaces: Designing user interfaces that are intuitive and easy to learn can significantly enhance the user experience. This could involve gesture-based controls, voice commands, or even direct brain-computer interfaces for more advanced implementations. Simulation and Training Programs: Providing simulation-based training tools can help users learn to control the SRLs effectively, ensuring they can be used efficiently in real-world tasks. 4. Safety and Compliance: Ensuring the safety of both the user and those around them is paramount, especially in environments where human-robot interaction is frequent. Solution Ideas: Real-time Safety Protocols: Implementing real-time monitoring and safety protocols that can prevent accidents or injuries. This includes collision avoidance systems and emergency stop mechanisms. Compliance with Regulations: Adhering to existing robotic and workplace safety regulations, and contributing to the development of new standards specifically for SRLs. # CRITERION FOR SUCCESS For our Supernumerary Robotic Limbs (SRLs) project, success is contingent upon meeting specific high-level criteria. Stability is a paramount goal, demanding that signals are received seamlessly, without any loss, especially within the confines of a room, even when there is a gap of two chairs. Affordability is a key criterion, emphasizing the importance of keeping costs low to enable widespread adoption and accessibility. Efficiency is critical; the process from user input to signal collection and transmission should operate with minimal delay. Aesthetic considerations are not overlooked; the design should be widely accepted and easily producible through technologies like 3D printing. Feedback mechanisms are crucial for user satisfaction; users should receive prompt and meaningful feedback from the system, enhancing their experience and trust. Additionally, the system's concurrency is vital; it must adeptly handle signals from multiple limbs in real-time, ensuring seamless integration and coordination. These high-level goals collectively define the success of our Supernumerary Robotic Limbs project. # DISTRIBUTION OF WORK Yichi Zhang: Part of the code work and electronic control system design and equipment selection Yushi Chen: Part of the code work and electronic control system design and equipment selection Xuekun Zhang: Progress major code work and overall design work Haotian Jiang: 3D print structure design and physical setup for the hardware part. |
||||||
| 28 | A climbing robot for building 3d printed concrete wall |
Benhao Lu Jianye Chen Shenghua Ye Zhenghao Zhang |
design_document1.pdf final_paper1.pdf final_paper2.pdf proposal1.pdf |
Binbin Li | ||
| ## Members: - Jianye Chen (jianyec2) - Zhenghao Zhang (zz84) - Shenghua Ye (sye14) - Benhao Lu (benhaol2) ## Project title A climbing robot for building 3d printed concrete wall ## PROBLEM: Current 3D printing construction, while effective in reducing construction waste and improving efficiency, faces challenges in adapting to complex architectural forms and constructing tall buildings. The existing equipment is limited in spatial adaptability, especially when dealing with the irregularities and textures of 3D printed concrete structures. The need for a versatile climbing and printing system for high-rise and complex architectural construction is a pressing issue in the construction industry. ## SOLUTION OVERVIEW: This project proposes an innovative climbing and self-supporting 3D printing system for construction. The system comprises a versatile mobile unit, including a climbing device for adapting to complex facades and a movable support system for irregular plans. The climbing device ensures stable ascent through power-driven surface adaptation and load-bearing anchors. The support system includes telescopic rails, pulleys, lifting columns, and a robotic arm for diverse construction needs. The construction system integrates material feeding, real-time printing feedback, and precise steel bar placement. The control system, based on GPS, facilitates targeted positioning, enabling intelligent construction of complex spatial structures. Overall, this solution aims to enhance 3D printing adaptability, revolutionizing construction methods for diverse architectural forms. ## SOLUTION COMPONENTS: The proposed solution consists of the following components: ## MOBILE SYSTEM: Climbing and lifting device with power drive, surface climbing, and load-bearing anchor lock modules. Construction support device with telescopic rails, universal pulleys, rigid lifting columns, and a multifunctional construction robotic arm. ## CONSTRUCTION SYSTEM: Material feeding device for adjusting material flow. Printing device for real-time feedback on additive construction accuracy. Reinforcement device for positioning and laying steel bars. ## CONTROL SYSTEM: GPS-based control system for precise positioning and printing control. In summary, this project aims to revolutionize 3D printing construction by providing a climbing and self-supporting printing system capable of adapting to complex architectural forms and surface textures, offering a new paradigm for industrialized building construction. ## CRITERION OF SUCCESS 1. INITIALIZATION AND PRINTING COMMAND: Receive input for architectural details and parameters. Perform self-checks and initiate the printing command. 2. PRINTING CONSTRUCTION EXECUTION: Execute printing at 0-1m height with moving and printing devices. Wait for concrete to reach the desired strength. 3. SELF-CLIMBING AND CONNECTION TO SMART FEEDING SYSTEM: Move to the self-climbing start. Lift to the designated position. 4. HORIZONTAL MOVEMENT AND PRINTING ADJUSTMENT: Detect and compensate for X-Y-Z oscillations. Use TOF camera for accuracy and adjust concrete flow. 5. TASK COMPLETION AND SELF-CLIMBING: After printing, perform downward pressure. Retract the horizontal movement device. ## DISTRIBUTION OF WORK 1. JIANYE CHEN: MECHANICAL DESIGN AND MANUFACTURE a) Jianye specializes in mechanical design and manufacturing aspects of the project. b) His expertise includes creating detailed mechanical plans, prototyping, and ensuring the physical components are well-crafted. 2. ZHENGHAO ZHANG: MECHANICAL DESIGN AND MANUFACTURE a) Zhenghao complements Jianye's skills in mechanical design and manufacture. b) Together with Jianye, they form a strong team handling the physical aspects of the project, ensuring its mechanical components are robust and functional. 3. SHENGHUA YE: PCB AND DIGITAL HARDWARE a) Shenghua focuses on the PCB and digital hardware aspects of the project. b) His expertise includes designing and implementing the electronic components, ensuring seamless integration with the mechanical elements. 4. BENHAO LU: SOFTWARE a) Benhao specializes in the software part related to printing. b) His role involves developing the necessary software for the printing process, optimizing functionality, and ensuring a user-friendly interface. |
||||||
| 29 | Advanced Modeling and Display of ZJU International Campus Power System |
Erkai Yu Jiahe Li Tiantong Qiao Yilang Feng |
design_document1.pdf final_paper1.pdf final_paper2.pdf proposal1.pdf |
Ruisheng Diao | ||
| # Team Member (NetId) - Tiantong Qiao(tqiao4) - Erkai Yu (erkaiyu2) - Jiahe Li (jiaheli2) - Yilang Feng(yilangf2) # Problem The electricity consumption of Haining International Campus of Zhejiang University is high and the visualization is not very intuitive, we intend to build a highly visual electricity consumption model. In addition, features such as AI prediction and intelligent control may be added to optimize the power consumption of the Haining campus. # Solution Our project plan is to build a physical model of the power system in the Haining International Campus of Zhejiang University and to perform power flow calculations using electricity consumption data from the Engineering Department. The brightness/different colors of LED strips are used to represent the current, voltage, power and other information. Based on this, anomaly detection can be implemented for various types of behaviors within the grid, such as abnormal user behaviors and grid infrastructure failures. Given the historical data of power consumption, we can build a vivid demonstration of the power flow inside the campus across the year. Based on that, we can also make predictions of how the power usage will change in the future. If given the live data of power consumption, we will be able to integrate them into our system, both for live demonstration and power monitoring. We also plan to use event-driven algorithms to autonomously detect abnormal conditions or disturbances. Other advanced applications, such as AI intelligent control, grid loss calculation, and installation and connection of distributed wind/photovoltaics power sources can also be developed. # Solution Components (and Distribution of Work) 1. Physical model of the campus -- Solid modeling of international campus districts using 3D printing technology or other modeling methods(Yilang Feng) 2. Power Flow Calculations -- Use software such as OpenDSS or Matpower to calculate the power flow of the electricity consumption of the campus(Tiantong Qiao), and control the LED light bar to display horizontally.(Erkai Yu) 3. Advanced Applications: -- Power usage anomaly detection, AI intelligent control, event-driven short circuit analysis, grid loss calculation, distributed photovoltaic generation, etc(Jiahe Li). # Criterion for Success The success of our project hinges on achieving key performance criteria, including the precision and accuracy of our power flow modeling. Utilizing software like OpenDSS or Matpower, we aim to attain a high level of accuracy in depicting the power flow within the campus, ensuring close alignment with historical and real-time power consumption data. In parallel, the construction of a physically accurate model of the international campus, employing 3D printing technology or other methods, is crucial for creating an immersive and realistic demonstration. Additionally, the implementation of LED strips with varying colors and brightness levels, responsive to calculated power flow and real-time data, is essential for effective representation. Furthermore, the success criteria encompass the accurate prediction of future power usage based on historical data, validation against real-time data, seamless integration of live power consumption data, and the autonomous detection of abnormal conditions through event-driven algorithms. The project's success is further evaluated through the successful implementation and practical assessment of advanced applications such as AI intelligent control, grid loss calculation, and the integration of distributed wind/photovoltaic power sources to enhance the overall capabilities of the campus power system. |
||||||
| 30 | Search and Identify |
Ruidi Zhou Shitian Yang Yilai Liang Yitao Cai |
design_document2.pdf design_document3.pdf final_paper2.pdf final_paper3.pdf final_paper4.pdf proposal1.pdf proposal2.pdf video1.mp4 |
Howard Yang | ||
| # Team members: Yang, Shitian sy39 Cai, Yitao yitaoc3 Zhou, Ruidi ruidi2 Liang, Yilai yilail2 # Title: Search and Identify # Problem: There is a noticeable gap in the availability of assistive applications tailored for homes, businesses, and individuals with mobility challenges. These groups lack efficient tools to swiftly locate everyday items, creating a significant inconvenience. This absence of specialized support not only hampers the day-to-day functionality within households and corporate environments but also poses a considerable barrier to independence for those with physical disabilities. Addressing this need with innovative solutions could dramatically improve the quality of life and operational efficiency by ensuring that vital items can be found quickly and easily, without unnecessary delay or reliance on others. # Solution overview: In solving the problem of accurately identifying specific items based on a user's immediate request, we are developing an innovative service-oriented robot capable of interactive processing. Our robot is equipped with a rotatable wireless camera mounted on a 360° steering engine which is controlled by a STM32F103c8t6 microcontroller under the drivetrain and power system, allowing it to visually scan its surroundings on receiving the user’s voice inquiry. When the software observes objects like cups, pencil cases, flowers, toys, and helmets, it processes the images to create an attention map. This map guides the robot to focus on and identify the specific object in question. Software component gives the object recognition feedbacks, the sensing system in the hardware component will output the 0/1 signal through signal control module and send it to the 360° steering engine. Such objects are easily achieved and can provide a suitable testing environment. # Solution Component: ## Software Component: 1. Speech recognition: Transform audio instructions given by users into text tasks. Prompt key item recognition: Simplify the text task prompt into a keyword or phrase. 2. Vision model: The vision model should take in the text prompt, and search for the object that matches the description best. 3. Algorithm: Our software parts will use a project on github called AbsVit as baseline, and we will remove the noise from the heatmap, and try to modify it to get the detail target object. The AbsVit is a algorithm and model for language-vision attention model. ## Hardware Component: 1. A drivetrain and power system: including a 360° steering engine, a wireless camera, a STM32F103c8t6 microcontroller, a 12V power source and a voltage converter. This system can rotate the camera to capture the pictures of its surroundings. 2. Control system: PC inputs the program into STM32F103c8t6 microcontroller, it will control the angles we want the camera to rotate each time and can control the time intervals between each rotation. 3. Storing system: including SD card which can store the pictures that the camera captures before, after software component finds that the object is found in the last picture, we can compare the pictures before and the picture which includes the object to verify the result. 4. Sensing system: including a signal control module. It can process the software component output into high-level or low-level signals and input 0/1 signals into drivetrain and power system to help it judge if it should operate or stop. # Criterion for Success 1. Capable of identifying and navigating in indoor spaces, which have varying lighting situations including bright natural sunlight to dim artificial lights, and obstacles such as furniture and shelves. 2. The voice response system should also be easy to use, so it must respond timely and interact in natural language with the user (Users don’t need to learn the extra commands). The voice response system should also be easy to use, so it must respond timely and interact in natural language with the user. 3. When search request received from PC, our microcontroller of STM32F103c8t6 should send the correct impulse signal to control the 360° steering engine to automatically stop when the desired object is detected by the camera attached to it. The difference of the direction of the camera to the actual direction of the desired object should be within 3°. 4. Steering engine can rotate uniformly, smoothly, and continuously when no commands are given in a balanced and room temperature environment. # Distribution of work Yang, Shitian and Cai, Yitao: Voice Recognition and Software Development: Responsible for developing and testing the voice recognition system. Yang, Shitian and Zhou, Ruidi: Vision Module and Software Development: Focus on developing and testing the vision module for object identification. Zhou, Ruidi and Liang, Yilai: Hardware and Microcontroller Development: Responsible for developing and testing the hardware components, including the steering engine and microcontroller. Cai, Yitao and Liang, Yilai: Integration and Testing: Oversee the integration of software and hardware components and conduct comprehensive testing of the entire system. |
||||||
| 31 | Movable Robotic Arm Platform |
Chenxi Wang Shihua Zeng Zhizhan Li Zhuohao Xu |
appendix1.docx design_document5.pdf design_document6.pdf design_document1.pdf design_document2.pdf design_document3.docx final_paper1.pdf final_paper2.pdf photo1.png proposal1.pdf proposal3.pdf proposal2.pdf |
Jiahuan Cui | ||
| # Problem There will be dangerous waste that generate daily in laboratory or factory. Moving the waste manually can be risky because operator will contact these materials which may be toxic, explosive, radiative, etc. Hence, disposal unit need a better way to remotely take, and transport boxed waste within narrow circumstances like aisle. Meanwhile, they can also remotely place the waste into the disposal device in a specific orientation. # Solution Overview Our solution for remote taking, moving, and placing hazardous waste is to build a movable robotic arm platform with somatosensory controller. - The platform with four non-offset caster wheels can move omnidirectionally without changing chassis orientation, making robot be able to move in narrow space smoothly without making much turn. - There will be a 6-freedom robotic arm with a suction cup end actuator on platform. The arm can easily get and place the object at any orientation we want. - The platform has a camera to give real-time video feedback. Operator can refer to the feedback and adjust robotic arm’s movement by moving its hand with somatosensory controller. # Solution Components ## Omidirectional Chassis - 4 non offset caster wheels with motor controlling steering - A camera to give video feed back ## Robotic Arm - A SCARA type structure providing 3 axes translation freedom - A RRR structure at the end providing 3 axes rotation freedom - A suction cup end actuator to suck and drop object ## Controller - A Jetson Orin Nano miniPC to run the code within ROS - A specially designed controller with 3 IMU to detect the position change of user’s hand, then mapping the movement to robotic arm. # Criterion for Success - The platform can operate smooth omnidirectional translation and rotation. - The robotic arm can fetch a 200*200*200mm, 600g-700g EVA cubic (we assume it as dangerous material in laboratory) from a 218*218mm square section tunnel precisely. - The robotic arm can transport the cubic and then placing it into a 240*240*240 mm box whose orientation will varying in 6 axes. - The operator can easily control the robotic arm remotely with its hand moving and placing the cubic within 40s. |
||||||
| 32 | A Wearable Device That Can Detect Mood |
Junjie Ren Kejun Wu Peidong Yang Xinzhuo Li |
design_document1.pdf design_document2.pdf final_paper1.pdf final_paper2.pdf proposal2.pdf proposal1.pdf |
Said Mikki | ||
| # A Wearable Device That Can Detect Mood **Team Members:** - Junjie Ren [junjier2] - Peidong Yang [peidong5] - Xinzhuo Li [xinzhuo4] - Kejun Wu [kejunwu2] ## Problem Our project targets the pervasive impact of workplace stress, anxiety, and depression, recognizing these as critical challenges compromising individual well-being and overall productivity. Motivated by the need for proactive solutions, we aim to provide a wearable device equipped with advanced sensors and a unique mood recognition framework. By integrating psychological knowledge and wearable technology, our solution objectively monitors and manages mood-related challenges, offering timely feedback. The goal is to contribute to a healthier work environment, and our project represents a significant step at the intersection of technology and mental health in modern workplaces. ## Solution Overview ### Objective The project aims to recognize and monitor the mood of employees in a workplace environment, leveraging wearable sensors and smartphone technology. ### Problem-Solving Approach 1. **Mood Recognition**: Using wearable sensors to collect physiological data that correlates with various mood states. 2. **Data Analysis**: Applying machine learning algorithms to interpret the physiological data and predict mood states. 3. **Feedback Mechanism**: Providing individual feedback to users and aggregated data to employers for well-being initiatives. ## Solution Components 1. **Wearable Sensor Subsystem**: - **Components**: Practical sensors, like Toshiba Silmee™ Bar Type or W20/W21 wristbands. - **Function**: Collects physiological data such as heart rate, skin temperature, and activity levels. - **Role in Solution**: Provides the raw data necessary for mood prediction. 2. **Data Processing and Analysis Subsystem**: - **Components**: Machine learning models (both personalized and generalized), feature extraction techniques. - **Function**: Analyzes sensor data, extracts meaningful features, and applies machine learning techniques to predict mood. - **Role in Solution**: Core of the mood recognition framework, turning data into actionable insights. 3. **Feedback and Reporting Subsystem**: - **Components**: User interface for feedback, anonymized data aggregation for employers. - **Function**: Provides mood predictions and wellness statistics to users and employers. - **Role in Solution**: Closes the loop by informing users about their mood trends and assisting employers in enhancing workplace wellbeing. ## Criterion for Success ### Hardware Achievements 1. Successful deployment of advanced sensors, which are capable of collecting various physiological data such as heart rate, pulse rate, and skin temperature. 2. Integration of sensors into a wearable format that can be comfortably used in the working environment. 3. Clear and vivid display on the screen, indicating the detected mood. ### Software Achievements 1. Creation of a sophisticated mood recognition framework capable of identifying eight different types of moods at five intensity levels, with regular time updates. 2. Application of machine learning techniques for both personalized and generalized mood prediction models based on physiological data. 3. Achievement of a high average classification accuracy in mood prediction, showcasing the efficacy of the software algorithms. ## Distribution of Work - Junjie Ren is responsible for System Design and Architecture. - Peidong Yang is responsible for Data Collection and Analysis. - Xinzhuo Li takes charge of Psychological Model Integration. - Kejun Wu is responsible for User Study Coordination. ### Electrical Complexity The project's electrical complexity encompasses integrating advanced sensors into the wearable device, demanding intricate signal processing algorithms, and robust coding for accurate mood interpretation. Ensuring seamless communication with the smartphone app adds complexity, along with implementing an efficient power management system for sustained monitoring. ### Mechanical Complexity The mechanical intricacy involves designing a comfortable and durable wearable, accommodating integrated sensors while considering user ergonomics. The challenge lies in achieving a balance between functionality and aesthetics, ensuring the device is robust enough for daily wear and capable of withstanding various environmental factors. This complexity is justified by the need for a reliable, user-friendly solution contributing to mental health monitoring in professional settings. |
||||||
| 33 | 3D model of a satellite footprint over the Earth |
Kuangji Chen Lunan Ke Wenhan Jiang Zhihua Gong |
design_document1.pdf final_paper1.pdf final_paper2.pdf other1.docx proposal1.pdf |
Pavel Loskot | ||
| Show a 3D model of a single satellite footprint over the Earth. The idea is to make the satellite stationary or move it along a 1D axis to vary its altitude, whereas the 3D Earth placed in a stand with internal wheels can rotate in a pre-calculated way. | ||||||
| 34 | Virtual Band |
Han Chen Lenny Liu Xuan Tang Zhanpeng Li |
design_document1.pdf final_paper1.pdf final_paper2.pdf proposal2.pdf proposal3.pdf proposal1.pdf |
Huan Hu | ||
| The goal of the Virtual Band project is to provide a new musical instrument interface that provides users with an exclusive and engaging experience. The system's integration of pressure sensors enables precise measurement of the pressing pressure applied by the user, thereby influencing the instrument's output sound level. A camera is also used to follow the hand's movement, which makes instrument key detection easier and improves the user's intuitive interface interaction. The electrical impulses are converted into high-quality instrument sound outputs by utilizing cutting-edge audio processing techniques, giving consumers a smooth and genuine musical performance experience. In order to create a dynamic and captivating musical interface, the Virtual Band project combines motion tracking, audio processing, and sensor technologies—a new approach to music technology. | ||||||
| 35 | Privacy-protected Elderly monitoring system: Wi-Fi and wearable sensors |
Jincheng Zhou Junyue Jiang Pu Lin Zizhao Cao |
final_paper1.pdf final_paper2.pdf final_paper3.pdf other1.pptx other2.pdf proposal2.pdf proposal1.pdf |
Huan Hu | ||
| # Problem Due to their busy work schedules, many families are faced with the inevitable situation of leaving the elderly alone at home. This makes it a challenge to respond to emergencies of elderly falls at home and to monitor the health of the elderly. There is a need for a way to remotely know the activities and health status of the elderly at home. # Solution Overview Our solution for above problem is that use Wi-Fi devices that could send Wi-Fi signals for motion detection while ensuring data privacy and make wearable devices with multiple sensors attached to assist Wi-Fi monitoring. We will build an integrated monitoring system combining Wi-Fi monitoring devices and wearable sensors used for emergency happening in old people’s home. # Solution Components ## Detection Subsystem - Wi-Fi devices sending Wi-Fi signal providing most data - Wearable devices with sensors providing data for assistence ## Processing and Output Subsystem - Algorithm that identify present situation - User Interface that send alarm to remote device. # Criterion for Success - Common Wi-Fi devices that can be used to obtain the desired Wi-Fi signal - Wearable devices that are convenient and less likely to leak private information - Algorithms that quickly and accurately determine the current situation - Simple and easy-to-use user interfaces and alerts. |
||||||
| 36 | intelligent robot arm |
Chenghan Li Haoran Yang Yiming Li Yipu Liao |
design_document1.pdf design_document2.pdf final_paper1.pdf final_paper2.pdf other2.pdf proposal4.pdf proposal3.pdf |
Wee-Liat Ong | ||
| # TEAM MEMBERS - Haoran Yang [haorany8] - Chenghan Li [cli104] - Yiming Li [yiming20] - Yipu Liao[yipul2] # TITLE Intelligent robot arm # PROBLEM For individuals with disabilities or limited mobility, it is hard for them to perform certain or multiple taskes. Or under some circumstances, the task is repetitive and boring for human. We want to design a intelligent robot arm that help disabilities and free people from repetitive work. # SOLUTION OVERVIEW Our graduation project aims to conceptualize an intelligent robotic arm, proficient in executing diverse tasks through voice and visual recognition. The overarching concept involves a user verbally identifying an object on a table to the robot. The robot, upon receiving the voice command, leverages its camera system to detect the specified object and subsequently manipulate it. In addition to these fundamental functionalities, the system is designed to interpret intricate voice instructions, such as rotating the object to specific degrees based on predefined references or following a set reference for movement. This innovative project harbors the potential to significantly benefit individuals with visual impairments in managing their daily tasks, as well as aiding those facing critical situations, such as during fires or earthquakes. # SOLUTION COMPONENTS # SUBSYSTEM 1 Four or five axis robotics arms # SUBSYSEM 2 An algorithm that can control the robotics arms to move and grab things # SUBSYSEM 3 A robotics vision system that contains a camera and an algorithm that can detect certain object and its relative position to the robotic arm # SUBSYSTEM 4 A voice recognition system that contains a microphone and an algorithm that can recognize what objects that a person is speaking of. # CRITERION FOR SUCCESS 1. The robotics arm is able to receive and process the relative position of an object that is sent by robotics vision system and grab the target using those information. 2. Robotics vision system is able to detect object and measure the relative position of it and feeds back to the robotics arm 3. Voice recognition system is able to recognize what objects that a person is speaking of and feed back to the robotics vision system. # DISTRIBUTION OF WORK - Haoran Yang: CAD model, construct robotics arm - Chenghan Li: design voice recognition system - Yiming Li: design robotics vision system - Yipu Liao: design robotics arm algorithm, construct robotics arm. |
||||||
| 37 | Visual chatting and Real-time acting Robot |
Haozhe Chi Jiatong Li Minghua Yang Zonghai Jing |
design_document1.pdf design_document2.pdf final_paper1.pdf final_paper2.pdf final_paper3.pdf proposal1.pdf proposal2.pdf proposal3.pdf video1.mp4 |
Gaoang Wang | ||
| Group member: Haozhe Chi, haozhe4 Minghua Yang, minghua3 Zonghai Jing, zonghai2 Jiatong Li, jl180 Problem: With the rise of large language models (LLMs), Large visual language models (LVLMs) have achieved great success in recent AI development. However, it's still a big challenge to configure an LVLM system for a robot and make all hardware work well around this system. We aim to design an LVLM-based robot that can react to multimodal inputs. Solution overview: We aim to deliver an LVLM system (software part), a robot arm for robot actions like grabbing objects (hardware part), a robot movement equipment for moving according to the environment (hardware part), a camera for real-time visual inputs (hardware part), a laser tracker for implicating the object (hardware part), and an audio equipment for audio inputs and outputs (hardware part). Solution components: LVLM system: We will deploy a BLIP-2 based AI model for visual language processing. We will incorporate the strengths of several recent visual-language models, including LlaVA, Videochat, and VideoLlaMA, and design a better real-time visual language processing system. This system should be able to realize real-time visual chatting with less object hallucination. Robot arm and wheels: We will use ROS environment to control robot movements. We will apply to use robot arms in ZJUI ECE470 labs and buy certain wheels for moving. We may use four-wheel design or track design. Camera: We will configure cameras for real-time image inputs. 3D reconstruction may be needed, depending on our LVLM system design. If multi-viewed inputs are needed, we will design a better camera configuration. Audio processing: We will use two audio processing systems: voice recognition and text-to-audio generation. They are responsible for audio inputs and outputs respectively. We will use certain audio broadcast components to make the robot talk. Criterion for success: The robot consists of functions including voice recognition, laser tracking, real-time visual chatting, a multimodal processing system, identifying a certain object, moving and grabbing it, and multi-view camera configuration. All the hardware parts should cooperate well in the final demo. This means that not only every single hardware should function well, but also perform more advanced functions. For instance, the robot should be able to move towards certain objects while chatting with humans. |
||||||
| 38 | VEHICULAR EDGE COMPUTING SYSTEM |
Mingjun Wei Shaohua Sun Ye Yang Yinjie Ruan |
design_document1.pdf final_paper2.pdf final_paper1.docx proposal1.pdf proposal2.pdf |
Meng Zhang | ||
| # TEAM MEMBERS - Shaohua Sun (shaohua6) - Ye Yang (yeyang3) - Mingjun Wei (mingjun9) - Yinjie Ruan (yinjier2) # VEHICULAR EDGE COMPUTING SYSTEM # PROBLEM: As more and more research has been conducted on mobile edge computing, we propose that a mobile edge computing server in application can be deployed on-board a vehicle. But when performing tasks, the server will heat up very quickly and traditionally, the air-conditioner is needed. We try to avoid the use of air-conditioner, but put the server exposed to the air. # SOLUTION OVERVIEW: The vehicular mobile edge computing server is designed with a general server installed on-board vehicle. To make full use of the server, it will be accessed to the Internet and realize functionalities according to the existing theory of edge computing. To solve the problem of heating when performing intensive computational tasks, we utilize the wind to cool it down while designing waterproof to protect the server from rain. # SOLUTION COMPONENTS: ## Modules on Waterproof and Shelter: - The waterproof: To protect the server from rain or snow. - The shelter: To carry the server with high stability. - The airpath on the shelter: To utilize the wind to cool down the server effectively, even in relatively low car speed. ## Server Modules: - The wireless communication access to the Internet. - The server can perform relatively complex tasks like deep learning effectively. # CRITERION FOR SUCCESS: - Functionality: The mobile edge computing server can do computation tasks in the complexity level of deep learning, and access to the Internet to send or receive data. The waterproof and shelter should be stable and firm to fasten the server and protect it from rain. Also it can dissipate heat effectively. - User experience: The user can get real-time access via the Internet and enjoy plentiful services like online video, etc. - Durability and stability: The server needs to maintain a stable access to the Internet, and it can be used in rainy environment. # DISTRIBUTION OF WORK: - ME STUDENT SHAOHUA SUN: Design how to set a waterproof. - ME STUDENT YE YANG: Design how the shelter can be breathable to cool down the server. - EE STUDENT MINGJUN WEI: Model a mobile edge computing server being able to take complex computing tasks. - EE STUDENT YINJIE RUAN: Make the edge computing server connected to the Internet. |
||||||
| 39 | Robotic T-shirt Launcher Mark III |
Jiakai Zheng Mingchen Li Shenao Wang Xiao Luo |
design_document1.pdf final_paper1.pdf final_paper2.pdf proposal1.pdf proposal2.pdf |
Timothy Lee | ||
| ## Team Members Li Mingchen (ml110), Zheng Jiakai (jiakaiz4), Wang Shenao (shenaow2), Luo Xiao (xiaoluo5) ## Project Title **Robotic T-shirt Launcher Mark III** ## Problem 1.The previous version of MARK II is excessively bulky for convenient portability and usage. It is imperative to reduce the dimensions and weight of the T-shirt launcher. 2.The shirt launcher is equipped with insufficient spare ammunition. It is necessary to ensure a minimum of three shots or enhance its firing rate. 3.To address system uncertainties, a comprehensive risk assessment should be conducted during the design phase to identify potential sources of uncertainty and their potential impacts. Mitigation strategies, such as redundant safety mechanisms, backup systems, and robust testing procedures, can be incorporated to minimize the effects of uncertainty on the system's performance and reliability. ## Solution Overview While preserving the achievements of ROBOTIC's T-SHIRT LAUNCHER MARK II, our team will address critical flaws. For example, the MARK II was too large and heavy for its function, and the MARK II fired too slowly. In addition, in terms of automation of the system, we will also try to achieve the unfinished goals of the MARK II and ensure safety by optimizing the launch trajectory. ## Solution Components Launcher system: The launcher system consists of an air chamber made up of gas cylinders, gas cylinders used to inflate the air chamber, an inlet valve, an exhaust valve, an exhaust trigger, and a barometer (for detecting the air pressure in the air chamber). These components are used to rapidly inflate and launch the T shirt through differential air pressure. Two Degree of Freedom Targeting Gimbal: This targeting gimbal consists of a stepper motor, reduction gear sets and aluminum frame structures. It consists of two degrees of freedom of motion, which enables precise control of the pitch and horizontal rotation angles in a stable manner while achieving light weight. The purpose is to adjust the position of the launcher in 3D space after receiving electrical signals from the control system so that the T-Shirt can be successfully launched to the desired place. Control System: The Control System plays a crucial role in efficiently managing the components of the system. It encompasses a gimbal controller, actuator controllers, electromagnetic valves, and a microcontroller like Arduino. They work together to ensure smooth and accurate operations, control the release of compressed air and keep the pressure in safe operating limits. Automation System: For the case of use on the gimbal, we want the launcher to be able to fire automatically. Therefore, the system should have a suitable function to automatically adjust the direction and force of the launch according to the situation. In addition, for safety reasons, the system will include a computer vision module to conduct spectator behaviour recognition to avoid potential accidents, such as stampedes. ## Criterion for Success Functionality of Launcher: The launcher should be able to fire T-shirts. The force of the launch can be changed by controlling the air pressure inside the launcher at the time of launch. The system should be able to simplify the operation by pre-loading the T-shirt in a certain amount. The operator can easily operate the transmitter with the trigger. Firing Rate: The launcher should have a relatively fast firing rate, which is determined by three key factors: the rate at which the gas chamber inflates to reach the desired pressure, the rate at which the controller controls the closing and opening of the valves, and the rate at which the T-Shirt bullet is loaded. The desired pressure of the chamber will determine the force of the shot, which can be controlled by adjusting the valve closing time, and the chamber will be equipped with a barometer to allow the operator to accurately control the force of the shot and make adjustments. Smaller Size and Weight: Reducing size and weight was one of the main objectives of this MARK III design, and for this reason we abandoned the rotary round change design of the MARK II and adopted a loaded round change design to reduce redundant size. Secondly, the weight of the gas chamber will be reduced. Two large gas cylinders are used in the MARK II, and in fact, the small volume of a single cylinder provides gas that is perfectly adequate for firing at least 40 rounds of ammunition. Then there is the reduction of overall size and weight, which is achieved by simplifying the frame design of the transport vehicle, and the overall size of the launcher. Safety: Since the launcher uses a pressure vessel, security considerations are very important to the system. The key parts of the launcher must have components to detect safety metrics, such as barometric values. In addition, for accidents that may occur during use, we should take into account and design safety mechanisms. ## Distribution of Work Li Mingchen: Automation System Zheng Jiakai: Launcher system Wang Shenao: Targeting Gimbal System Luo Xiao: Control System |
||||||
| 40 | Automatic Intelligent Fishing Pod |
Baiming Li Xinyi Song Yitong Gu Ziyi Shen |
design_document1.pdf design_document2.pdf design_document3.pdf final_paper1.pdf final_paper2.pdf proposal1.pdf proposal2.pdf proposal3.pdf |
Said Mikki | ||
| Our project, the SmartFish Pod, introduces a seamless fishing experience by integrating automation and AI technology. This device is an innovation in the recreational fishing industry, enhancing the traditional practice with modern technology. General Description: SmartFish Pod is a compact, intelligent fishing assistant that automates baiting, bite detection, and rod lifting. It employs cameras and sensors, coupled with machine vision, to not only detect activity but also identify fish species and analyze the environment. Uniqueness: The project's uniqueness lies in its autonomous operation, offering a hands-free fishing solution. Unlike inventions that create new methods, this innovation refines and elevates an existing practice. It's particularly distinctive due to its species identification capabilities, which none of the current fishing aids offer. Alternatives/Competitors: The current market offers basic electronic bite alarms and rod holders, which reduce but do not eliminate manual involvement. SmartFish Pod's full automation and environmental assessment features are novel, positioning it ahead of competitors in terms of technology integration and user experience. Technical Overview: The pod's mechanics are designed for ease of use, featuring an automatic baiting system and a responsive rod lifting mechanism. Its digital brain utilizes a robust AI algorithm trained on a multitude of data to recognize species and predict bites. This system is connected to a user-friendly interface that informs the angler of real-time conditions and statistics, making fishing accessible and educational for enthusiasts at all levels. |
||||||
| 41 | Continuous Roll-To-Roll LB Film Deposition Machine |
Boyang Fang Han Li Ruiqi Zhao Zhixian Zuo |
design_document1.pdf design_document2.pdf design_document3.pdf final_paper1.pdf final_paper2.pdf proposal1.pdf proposal2.pdf |
Kemal Celebi | ||
| # Team member - Boyang Fang 654045608 - Han Li 652796808 - Ruiqi Zhao 658317696 - Zhixian Zuo 669424542 # Title Continuous Roll-To-Roll LB Film Deposition Machine # Problem Statement The large-scale production of lb film has great economic potential, but there are technical problems. At present, the world has failed to achieve large-scale mass production of lb film, and the development cost is extremely expensive. # Solution Overview This project is aimed at solving the mass production problem of LB film using a continuous roll-to-roll production method which can make a great contribution to the industry application of LB film. # Solution Components The project consists of three parts: 1. The production system, including stainless steel tanks, is used for loading liquid solvents on which nanomaterials float. Above one side of the slot is a nanomaterial burette for adding nanomaterial to the slot, which is controlled by a computer system. 2. The collection system consists of a bracket and five stainless steel rolls, two of which are used to collect Ptes with nanomaterials attached to the surface and three of which are used to adjust the slope of the contact area. The reel is connected to the transmission and motor and is controlled by a computer system. 3. Electromechanical control system with all computer components built in, used to adjust the traditional speed, find the best production conditions, control the operation of the system. # Software Components: 1. The speed of stainless steel drum operation is adjusted by setting the code, and the speed is expected to be 0.55-20 mm per minute. Therefore, it is necessary to visualize the speed of stainless steel through the computer and observe the production results in time. 2. The height of the stainless steel drum is controlled by a computer to achieve different slopes of the film in order to find and stabilize the best Angle of tension diffusion to achieve maximum production efficiency. # Criterion for Success 1. Find the best moving speed of rolling speed, syringe pump speed and angle between interface and film surface. 2. Solve the problem of material will gp through the film from two sides. 3. Achieve the production of regularly LB film. |
||||||
| 42 | eVTOL Drone |
Chenyang Huang Hongfan Liu Xuan Chen Zhengpu Ye |
design_document1.pdf final_paper1.docx final_paper2.pdf other1.pdf other2.docx proposal1.pdf |
Jiahuan Cui | ||
| # Problem Today, both the primary and secondary industries need to carry out technology-led industrial upgrading, in such a process, how to efficiently detect the work flow is a major problem. For example, in the fields of agricultural inspection, power line and infrastructure inspection, environmental protection and wildlife monitoring, an effective, high-speed and wide-ranging inspection method will increase the productivity and accuracy of related industries. # Solution Overview The solution we give is to develop an eVTOL drone that can meet a certain load bearing, set up corresponding communication modules and cameras for it, and transmit real-time data back to the data cloud we build on the server, so as to achieve a large range and long distance accurate detection. # Solution Components ## Foam Board Body The foam plate body provides lower weight, thus reducing energy consumption and ensuring adequate performance in terms of movement and acceleration, while it has good insulation, which can effectively reduce heat transfer and noise diffusion. During the engineering phase, its characteristics made the air frame easy to process and had good impact protection characteristics. At the same time, foam board is also a more economical and environmentally friendly approach. ## Power System Internal micro controller for A/D conversion and initial signal processing ( Atmel atmega328 SIM Card Service ) Use SIM cards to provide identity authentication and data transmission in drone and cloud communications. SIM card technology allows drones to connect to a specific cellular network operator and use its network infrastructure to communicate remotely. In this way, the drone is not limited by distance, is able to perform long-distance missions, and can upload data to the cloud in real time. At the same time, it also ensures continuous connectivity between the drone and the cloud, and the drone can maintain a continuous network connection in the covered area. This allows for prolonged monitoring or data acquisition activities while enabling near real-time data analysis and decision support. ## Camera Cameras rely on built-in image sensors, such as CMOS or CCD, to convert light into electronic signals. These sensors divide the screen into pixel points, each point can record color and brightness information, analog cameras will capture the image into analog signal output; The digital camera further converts the analog signal to A digital signal through an A/D (analog-to-digital) converter. By reducing its size through encoding and compression algorithms (such as H.264, H.265) to reduce the bandwidth requirements during transmission, the compressed video data can be transmitted through the SIM's cellular network and stored in the cloud. # Criterion for Success Our aircraft must be able to lift more than 2kg and maintain smooth horizontal and vertical flight, while our cloud needs to be stable and receive video information from drones flying on the road |
||||||
| 43 | Digital Twin Bridge Monitoring System |
Hanchi Ge Kowshik Dey Rongjian Chen |
design_document1.pdf design_document2.pdf final_paper1.pdf final_paper2.pdf proposal2.pdf video1.mp4 |
Simon Hu | ||
| **Project Advisor:** Dr. Cristoforo Demartino **Team Members:** - Kowshik Arko Dey [arkod2] - Hanchi Ge [hanchig2] - Rongjian Chen [rc21] **Problem:** Bridges are one of the most vital infrastructures that serve as connectors both inside and outside of a country. They facilitate the movement of people, goods, and vehicles. Despite being marvels of engineering and architecture, accidents in bridges have become more frequent as time passes. The significant causes can be attributed to as being vehicle overloading and structural concerns of the bridge. These type of accidents are more prominent in third world countries, like Bangladesh, where most of the bridges have no monitoring system due to the cost involving these traditional monitoring systems. As a result, the drivers are left to their own assessments and judgements which may lead to accidents and structural damage to the bridges. The development of digital monitoring system can effectively save the money wasted on repetitive maintenance and repair of bridges due to overloading and structural damage. **Solution Overview:** The Digital Twin Bridge Monitoring System is designed to address the critical issue of bridge safety and maintenance. This innovative system involves the creation of a digital counterpart for a physical bridge, which is outfitted with advanced pressure sensors. These sensors are crucial for accurately gauging the weight of vehicles as they traverse the bridge, ensuring that the bridge's load capacity is not exceeded. Additionally, the system is equipped with a traffic light mechanism. This feature plays a vital role in warning drivers about potential overloading or existing structural issues, thereby enhancing safety measures. To demonstrate the practicality and functionality of this system, we plan to construct a scaled-down prototype model. This model will serve as a platform for installing our hardware components, which include various modules such as sensors and a micro-controller. The key to our system's effectiveness lies in the ability to transmit the sensor's processed data to the digital twin platform. This enables the real-time monitoring and detection of the bridge's condition, allowing for immediate responses to any detected problems. Through this advanced monitoring system, we aim to revolutionize how bridge safety is managed, ensuring the longevity and reliability of these critical infrastructures. **Solution Components:** *Pressure Sensor Subsystem Overview* The Sensor Subsystem is strategically designed for early detection of potential risks posed by overweight vehicles. Situated in every lane at the initial incline of the bridge, pressure sensors are meticulously installed. Their primary role is to identify vehicles exceeding the weight limit. Upon detection, the traffic light will show red. *Displacement Subsystem Overview* Displacement sensors are used to measure the displacement of a bridge structure, which is critical for us to assess the structural safety of a bridge. Displacement sensors will be strategically placed at key points in the bridge structure, such as supports, beams and joints, to ensure we can fully monitor the health of the bridge. *Processing Subsystem Details* The operation of the Processing Subsystem is pivotal for maintaining traffic flow and ensuring safety. Under standard operational circumstances, the traffic signal lights are set to green, allowing vehicles to pass. However, the system is on constant alert for overweight vehicles. The moment an overweight vehicle is identified, the traffic lights switch to flashing red, serving as a clear warning to drivers to halt and not to enter the bridge. Further, should there be any detected structural deformation within the bridge, the signal lights will steadfastly remain red. Moreover, to prevent any approach towards the potentially unsafe bridge, all traffic lights leading to it from the preceding intersection will be deactivated. The heart of this subsystem is an internal micro-controller responsible for Analog-to-Digital (A/D) conversion and the initial stages of signal processing. - **Signal Conditioning:** The raw signals from the sensors are often weak and noisy. Signal conditioning modules are used to amplify, filter, and convert these signals into a format suitable for digital processing. - **Analog-to-Digital Conversion (ADC):** The conditioned analog signals are converted into digital data through ADC. This conversion is essential for the subsequent data analysis and digital twin simulation. - **Data Processing Unit:** A micro-controller processes the digital data, performing preliminary calculations and data compression to reduce the amount of data to be transmitted. - **Data Transmission:** The processed data is transmitted to the Digital twin software. *Power Subsystem Functionality* It efficiently converts AC power, commonly available from standard outlet sources, into the DC voltages required by the various components of the system. This includes the sensors, micro-controller, and communications modules, thereby guaranteeing their uninterrupted operation and performance. **Criterion for Success:** Successful development and integration of the scaled physical model, software, and hardware components. The scale model can use pressure sensors to measure the weight of the passing model car, and when the weight of the car exceeds our preset standard, the signal light of the scale bridge will be red to warn the driver. At the same time, the signals obtained from the scale model, such as pressure signals and structural deformation signals of the bridge, need to be transmitted in real time to the digital twin monitoring system. Comprehensive documentation of the project's design, implementation, and testing process. --- |
||||||