search

silvery107 / rl-mpc-locomotion

Deep RL for MPC control of Quadruped Robot Locomotion
https://docs.google.com/presentation/d/18bznpYrkCPnhCisySPDz18hvL3Ytere7JiJEbdLvpgU/edit?usp=sharing
MIT License
347 stars 41 forks source link

Can you share your "simulation to reality " code base? #16

Closed heartInsert closed 2 months ago

heartInsert commented 2 months ago

Hi, I have successfully trained a PPO model in isaacgym and deploy to ros and gazebo . My model walks well in gazebo , but I don't know how to deploy to a real A1 robot . I read the unitree's official demo , their demo is c++ , I don't know how to deploy in c++ , do you have python to control the robot by 12 joints like in gazebo ?

silvery107 commented 2 months ago

Hi,

Unitree has new sdk available in Python, but I think it's not for A1, so if you have your controller/policy ready in Python, you can bridge their C++ SDK to Python via pybind. An example code can be found here.

If you are particularly interested in deploying my codebase, you can check https://github.com/silvery107/rl-mpc-locomotion/issues/9 and https://github.com/silvery107/rl-mpc-locomotion/issues/1 discussions for further reference.

Thanks