Autonomous Wheelchair Attachment - YHack 1st Place Hardware — Self-Driving Wheelchair Add-On
timeline: 2026
tech stack: Python, ROS, LiDAR, Raspberry Pi, Computer Vision, 3D Printing
Overview
An autonomous navigation attachment that bolts onto any standard wheelchair, giving it self-driving capabilities without replacing the chair itself. Built in 24 hours at YHack and awarded 1st place in the hardware track. The system uses LiDAR and computer vision to map its surroundings, plan obstacle-free paths, and drive the wheelchair to a user-selected destination.
How It Works
A Raspberry Pi serves as the main compute unit, fusing data from a 2D LiDAR scanner and a camera running a lightweight object-detection model. The navigation stack handles SLAM-based mapping, path planning, and motor control through a custom drive module that interfaces with the wheelchair's wheels. The entire attachment is designed to be removable — it clamps onto the frame and connects to the wheels through a friction-drive mechanism, so the wheelchair can still be used manually at any time.
Results
The prototype successfully navigated an indoor course at YHack, avoiding static and dynamic obstacles in real time. Judges awarded it 1st place in the hardware category for the combination of practical impact, technical execution, and the fact that it augments existing wheelchairs rather than replacing them.