MotionControlled Kart
What it does
The project builds motion controls without the use of sensors. The main use case is for handicaped patients on wheel chairs who can't control them with their hands. Recent technology has seen similar machines controlled using breath and other methods. We believe head tilting is the least intrusive method of such control. Aside from wheel chairs, we demonstrate that the same technology can be used to control small robots and drones for fun and work.
What we learned
We learned a lot about computer vision, detection by tracking, the Dragonboard 410c, and robotics.
Challenges we faced
There was a lot of lag in detection which we had to work to fix. There were issues with the memory in the dragonboard. Specifically there wasn't enough space to install all the repos we needed.
Accomplishments we are proud of
We are very proud of the low latency we achieved with a low powered computer.
Built With
- c
- c++
- jupyter-notebook
- processing
- python
- shell
Log in or sign up for Devpost to join the conversation.