bdx_r_mjlab.mp4
This repository showcase the implementation of the BDX-R robot into MjLab.
Warning
As MjLab is still in early development, this repository may be impacted by breaking changes. If an issue were to arise when running one of the scripts, feel free to open an issue or contribute to the project. Thanks you for your understanding!
MjLab is a project to have the Isaac Lab API using MjWarp as the backend. If you’re wondering about the motivation behind it or how it differs from Newton, you can learn more about it here.
Clone the repository.
git clone https://github.com/BDX-R/BDX-R-MjLab.git && cd BDX-R-MjLabGet the robot description.
curl -L -o bdx_r_description.tar.gz https://github.com/KaydenKnapik/BDX-R-Description/archive/refs/heads/main.tar.gz
tar -xzf bdx_r_description.tar.gz -C src/bdx_r_mjlab/robots/bdx_r/
rm bdx_r_description.tar.gzList available environments.
uv run bdx_r_list_envsUse the dummy agents.
uv run bdx_r_play Mjlab-Velocity-Flat-BDX-R --agent zero # send zero actions to the robot
uv run bdx_r_play Mjlab-Velocity-Flat-BDX-R --agent random # send random actions to the robotTrain the policy.
uv run bdx_r_train Mjlab-Velocity-Flat-BDX-R --env.scene.num-envs 4096Evaluate the policy.
uv run bdx_r_play Mjlab-Velocity-Flat-BDX-R-Play --wandb-run-path your-org/mjlab/run-id- Use IMU for observations
- Use simplified meshes for collisions
- Deploy the policy on real robot
- Use rough terrains
- Add a head to the robot
Check here for the general roadmap of the project!
We look forward for contributions. Before submitting a PR, please run the following command for format:
make formatWe're grateful to the people behind MjLab, MuJoCo Warp and Isaac Lab.