Skip to main content

Simulation

Wiki-GRx-Gym tests the performance of RL policies trained using NVIDIA Isaac Gym on the GR1 robot model in Mujoco. You can also use Mujoco to view your robot.

User Guide​

Create conda environment​

conda create -n wiki-grx-mujoco python==3.8

Activate environment​

conda activate wiki-grx-mujoco

Install Mujoco and Mujoco-viewer​

pip install mujoco mujoco-python-viewer

  1. Install dependencies:

    cd wiki-grx-mujoco
    pip install -e .

  2. Load model in Mujoco:

    Enter Mujoco's bin directory:

    ./mujoco-3.1.5/bin/

    Run:

    ./simulate

    and drag the .xml file you want to view into the robots folder

Load trained policy:​

  1. Enter file location:

    ./run/scripts

  2. Run code:

    ./mjsim.py <robot_name> --load_model <path_to_model>

    Example Load standing policy to make GR1T1 robot stand:

    ./mjsim.py gr1t1 --load_model /home/username/.../policy/stand_model_jit.pt

    Load walking policy to make GR1T2 robot walk:

    ./mjsim.py gr1t2 --load_model /home/username/.../policy/walk_model_jit.pt

    You can modify model parameters in gr1tx_lower_limb.xml and robot_config

  3. Use keyboard to control robot:

    After the simulation starts, press ** . ** to make the robot stand, press / to make the robot walk!