英文 | 中文

tron1-rl-deploy-python

1. Running the Simulation

• Open a Bash terminal.

• Clone the MuJoCo simulator code:

  git clone --recurse https://github.com/limxdynamics/tron1-mujoco-sim.git

• Install the motion control development library (if not already installed):

  • For Linux x86_64 environment:

    pip install tron1-mujoco-sim/limxsdk-lowlevel/python3/amd64/limxsdk-*-py3-none-any.whl

  • For Linux aarch64 environment:

    pip install tron1-mujoco-sim/limxsdk-lowlevel/python3/aarch64/limxsdk-*-py3-none-any.whl

• Set the robot type:

  • List the available robot types using the Shell command:

    tree -L 1 tron1-mujoco-sim/robot-description/pointfoot

    Example output:

    tron1-mujoco-sim/robot-description/pointfoot
    ├── PF_P441A
    ├── PF_P441B
    ├── PF_P441C
    ├── PF_P441C2
    ├── PF_TRON1A
    ├── SF_TRON1A
    └── WF_TRON1A
    

  • Set the robot model type (using PF_P441C as an example; replace with your actual robot type):

    echo 'export ROBOT_TYPE=PF_P441C' >> ~/.bashrc && source ~/.bashrc

• Run the MuJoCo simulator:

  python tron1-mujoco-sim/simulator.py

2. Running the Control Algorithm

This repository is the control algorithm code — no need to clone it again. cd into your local clone of tron1-rl-deploy-python, then:

• Open a Bash terminal in this repository.

• Install the motion control development library (if not already installed):

  • For Linux x86_64 environment:

    pip install limxsdk-lowlevel/python3/amd64/limxsdk-*-py3-none-any.whl

  • For Linux aarch64 environment:

    pip install limxsdk-lowlevel/python3/aarch64/limxsdk-*-py3-none-any.whl

• Set the robot type:

  • List the available robot types using the Shell command:

    tree -L 1 controllers/model

    Example output:

    controllers/model
    ├── PF_P441A
    ├── PF_P441B
    ├── PF_P441C
    ├── PF_P441C2
    ├── PF_TRON1A
    ├── SF_TRON1A
    └── WF_TRON1A
    

  • Set the robot model type (using PF_P441C as an example; replace with your actual robot type):

    echo 'export ROBOT_TYPE=PF_P441C' >> ~/.bashrc && source ~/.bashrc

• Select training environment

  The currently supported training environments are isaacgym and isaaclab. Taking isaacgym as an example, set the training environment type:

  echo 'export RL_TYPE=isaacgym' >> ~/.bashrc && source ~/.bashrc

• Run the control algorithm:

  python main.py

3. Virtual Joystick

• Open a Bash terminal.

• Run the robot-joystick:

  ./tron1-mujoco-sim/robot-joystick/robot-joystick

4. Demonstration of Results