# Title Team Members TA Documents Sponsor
4 Actions to Mosquitoes
Lumeng Xu
Peiqi Cai
Xiangmei Chen
Yang Dai
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.

Keebot, a humanoid robot performing 3D pose imitation

Zhi Cen, Hao Hu, Xinyi Lai, Kerui Zhu

Featured Project

# Problem Description

Life is movement, but exercising alone is boring. When people are alone, it is hard to motivate themselves to exercise and it is easy to give up. Faced with the unprecedented COVID-19 pandemics, even more people have to do sports alone at home. Inspired by "Keep", a popular fitness app with many video demonstrations, we want to build a humanoid robot "Keebot" which can imitate the movements of the user in real time. Compared to a virtual coach in the video, our Keebot can provide physical company by doing the same exercises as the user, thus making exercising alone at home more interesting.

# Solution Overview

Our solution to the create such a movement imitating robot is to combine both computer vision and robotic design. The user's movement is captured by a fixed and stabilized depth camera. The 3D joint position will be calculated from the camera image with the help of some neural networks and depth information from the camera. The 3D joint position data will be translated into the motor angular rotation information and sent to the robot using Bluetooth. The robot realizes the imitation by controlling the servo motors as commanded. Since the 3D position data and mechanical control are not ideal, we leave out the consideration of keeping robot's balance and the robot's trunk will be fixed to a holder.

# Solution Components

## 3-D Pose Info Translator: from depth camera to 3-D pose info

+ RealSense Depth Camera which can get RGB and depth frames

+ A series of pre-processors such as denoising, normalizing and segmentation to reduce the impact of noise and environment

+ Pre-trained 2-D Human Pose Estimation model to convert the RGB frames to 2-D pose info

+ Combine the 2-D pose info with the depth frames to get the 3-D pose info

## Control system: from model to motors

+ An STM32-based PCB with a Bluetooth module and servo motor drivers

+ A mapping from the 3-D poses and movements to the joint parameters, based on Inverse Kinematics

+ A close-loop control system with PID or State Space Method

+ Generate control signals for the servo motors in each joints

## Mechanical structure: the body of the humanoid robot

+ CAD drawings of the robot’s physical structure, with 14 joints (14 DOF).

+ Simulations with the Robotics System Toolbox in MATLAB to test the stability and feasibility of the movements

+ Assembling the robot with 3D print parts, fasteners and motors

# Criterion of Success

+ 3-D pose info and movements are extracted from the video by RealSense Depth Camera

+ The virtual robot can imitate human's movements in MATLAB simulation

+ The physical robot can imitate human's movements with its limbs while its trunk being fixed