Running AI robotics experiments at home with LeRobot and SO-ARM100

I have summarized my experience with the SO-ARM100 robot from the general overview to the training process and the results I got.

Links:
- Lerobot repo: https://github.com/huggingface/lerobot
- SO-arm100 repo: https://github.com/TheRobotStudio/SO-ARM100
- DOT-policy repo: https://github.com/IliaLarchenko/dot_policy
- My Hugging Face page: https://huggingface.co/IliaLarchenko
- My fork of the LeRobot: https://github.com/IliaLarchenko/lerobot (has branches for PS4 controller and DOT-policy)
- Follow me on X for more updates: https://x.com/IliaLarchenko

00:00 - Intro
00:30 - Robot Overview & Assembly
02:15 - LeRobot Library
03:39 - How the Robot Works
04:35 - Teleoperation
08:07 - PS4 Controller Teleoperation
11:54 - Robot Testing
17:25 - Custom Robot Configuration
20:18 - Dataset Collection
24:02 - Dataset Tips & Environment Setup
28:06 - Dataset Visualization & Simulated Environments
29:49 - Training Policies
30:39 - My DOT-Policy Explained
33:01 - Training
34:15 - Running on the Real Robot
36:00 - Common Failure Cases
38:12 - Recap

#ai #robotics #opensource #deepLearning #3dprinting #lerobot #huggingface #robotarm #roboticsprojects #machinelearning