Project

# Title Team Members TA Documents Sponsor
21 Vision-driven Automatic Posture Correction Device
 Weichong Chen
Xiaoyu Xu
Yilun Chen
 design_document1.pdf
final_paper1.pdf
final_paper2.pdf
presentation1.pptx
proposal1.pdf
 Wee-Liat Ong
#Problem
The digital age has led to increased reliance on portable electronic devices, causing a significant rise in poor sitting postures. Traditional brackets lack dynamic adjustment, forcing users to adapt to fixed screens, which hinders healthy habits. Existing market solutions often fail to optimize the sight-screen relationship or rely on imprecise manual adjustments. This results in health issues such as cervical spine strain, muscle soreness, and carpal tunnel syndrome.
#Solution Overview
The project develops an Automatic Sight Correction Device Bracket. Using visual detection and attitude sensing, the bracket dynamically adjusts its height and tilt angle to maintain the user’s sight in a horizontal state. It is portable, universally compatible with mainstream devices, and powered via USB for mobile use.
#Solution Components
##Subsystem 1 (Hardware)
Core Microcontroller: A high-performance MCU processes data from the camera and gyroscope to perform closed-loop regulation of actuators.
Actuators: Includes a micro electric linear actuator (load capacity ≥2kg) with a linear encoder for precise height adjustment, and a worm gear motor for tilt angle control.
Sensing Modules: A high-definition camera captures facial landmarks (pupil, jawline) with autofocus and low-light compensation. A gyroscope provides real-time attitude data.
Structure & Power: Built from Higher-strength 3D printing materials, the frame supports 7-12.9 inch tablets, smartphones and e-readers. It uses a 5V/2A USB-C power scheme.
Interaction: Includes a one-click start button, emergency stop, and a DIP switch for manual/automatic mode switching.
##Subsystem 2 (Software)
Data Processing: Uses the Kalman Filter Algorithm to fuse sensor data and the Mediapipe framework to detect 68 facial landmarks.
Control Logic: A PID Control Algorithm calculates deviations between actual sight and the horizontal standard, driving actuators to correct the bracket without overshoot.
Safety: Automatically triggers alarms and stops adjustment if feedback is lost or deviations persist.
#Criteria of Success
Efficiency: Completes initial correction within 10 seconds; responds to posture changes exceeding 3°.
Performance: Supports up to 2kg loads; achieves ≥95% recognition accuracy under various lighting.
Safety & Usability: Features torque protection and emergency stop. Setup involves only three steps: place device, fix bracket, and one-click start.

Remote Driving System

Bo Pang, Jiahao Wei, Kangyu Zhu

Featured Project

#### TEAM MEMBERS

Jiahao Wei (jiahaow4)

Bo Pang (bopang5)

Kangyu Zhu (Kangyuz2)

## REMOTE DRIVING SYSTEM

#### PROBLEM:

In daily life, people might not be able to drive due to factors like fatigue and alcohol. In this case, remote chauffeur can act as the driver to make the driving safe and reduce the incidence of traffic accidents. Remote chauffeuring can improve the convenience of driving. In the case of urban traffic congestion and parking difficulties, remote chauffeurs allow drivers to park their vehicles in parking lots away from the city center and then deliver them to their destination via remote control.

#### SOLUTION OVERVIEW:

The remote driving system is designed to provide real-time feedback of the car's external environment and internal movement information to the remote chauffeurs. Through the use of advanced technologies, the remote chauffeurs can remotely operate the car's movement using various devices. This system is capable of monitoring the car's speed, distance from obstacles, and battery life, and transmitting this information to the remote chauffeurs in a clear and easy-to-understand format.

#### SOLUTION COMPONENTS:

##### Modules on TurtleBot3 :

- The mechanical control system: to achieve the basic motion functions of the TurtleBot3 car.

- The distance sensing system used for monitoring the surrounding environment: Using LiDAR to detect the distance of the car in different directions.

- The system used for monitoring the vehicle's status: real-time monitoring the car's battery power, speed, etc., and uploading the data to the PC server in real-time.

##### Server Modules:

- The transmission system used to remotely control the car: implemented using Arduino IDE.

- The system used to build an AR-based information interaction system: implemented using Unity.

- The system used to output specific car motion commands: implemented using ROS to control the car.

##### HRI modules:

- The gesture recognition system used to recognize gestures given by people and feed back to the central PC server.

- The device used for interaction between the car and people: transmitting real-time surrounding information of the car to the Hololens 2 glasses in video form.

#### CRITERION FOR SUCCESS:

- Functionality: The remote driving system needs to be able to facilitate interaction between the user and the vehicle, enabling the user to remotely control the vehicle's steering, acceleration, and deceleration functions.

- User experience: The user can obtain real-time information about the surrounding environment while driving the vehicle through the glasses, and control the vehicle's movement through gestures.

- Environmental parameter detection: The vehicle can obtain distance information about the environment and its own real-time information.

- Durability and stability: The server needs to maintain a stable connection between the vehicle and the user.

#### DISTRIBUTION OF WORK:

- ECE STUDENT PANG BO:

Implementing the ROS interaction with the PC, using the ROS platform to control the car's speed and direction.

- ECE STUDENT WEI JIAHAO:

Building the car, implementing environmental monitoring and video transmission, ensuring stable transmission of environmental information to the user.

Implementing speed measurement, obstacle distance detection, and battery level monitoring for the car.

- EE STUDENT ZHU KANGYU:

Designing the AR interaction, issuing AR information prompts when the car is overspeeding or approaching obstacles.

Implementing hand gesture recognition for interaction between hololens2 and PC.