Project

# Title Team Members TA Documents Sponsor
7 Drone Delivery System for Takeaway Business
 Ximo Wang
Yanbing Yang
Yang Chen
Yuzheng Zhu
 design_document2.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.

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