Awesome
Unitree RL GYM
This is a simple example of using Unitree Robots for reinforcement learning, including Unitree Go2, H1, H1_2, G1
1. Installation
-
Create a new python virtual env with python 3.8
-
Install pytorch 2.3.1 with cuda-12.1:
pip install torch==2.3.1 torchvision==0.18.1 torchaudio==2.3.1 --index-url https://download.pytorch.org/whl/cu121
-
Install Isaac Gym
- Download and install Isaac Gym Preview 4 from https://developer.nvidia.com/isaac-gym
cd isaacgym/python && pip install -e .
- Try running an example
cd examples && python 1080_balls_of_solitude.py
- For troubleshooting check docs isaacgym/docs/index.html
-
Install rsl_rl (PPO implementation)
- Clone https://github.com/leggedrobotics/rsl_rl
cd rsl_rl && git checkout v1.0.2 && pip install -e .
-
Install unitree_rl_gym
- Navigate to the folder
unitree_rl_gym
pip install -e .
- Navigate to the folder
-
Install unitree_sdk2py (Optional for deploy on real robot)
- Clone https://github.com/unitreerobotics/unitree_sdk2_python
cd unitree_sdk2_python & pip install -e .
2. Train in Isaac Gym
-
Train:
python legged_gym/scripts/train.py --task=go2
- To run on CPU add following arguments:
--sim_device=cpu
,--rl_device=cpu
(sim on CPU and rl on GPU is possible). - To run headless (no rendering) add
--headless
. - Important : To improve performance, once the training starts press
v
to stop the rendering. You can then enable it later to check the progress. - The trained policy is saved in
logs/<experiment_name>/<date_time>_<run_name>/model_<iteration>.pt
. Where<experiment_name>
and<run_name>
are defined in the train config. - The following command line arguments override the values set in the config files:
- --task TASK: Task name.
- --resume: Resume training from a checkpoint
- --experiment_name EXPERIMENT_NAME: Name of the experiment to run or load.
- --run_name RUN_NAME: Name of the run.
- --load_run LOAD_RUN: Name of the run to load when resume=True. If -1: will load the last run.
- --checkpoint CHECKPOINT: Saved model checkpoint number. If -1: will load the last checkpoint.
- --num_envs NUM_ENVS: Number of environments to create.
- --seed SEED: Random seed.
- --max_iterations MAX_ITERATIONS: Maximum number of training iterations.
- To run on CPU add following arguments:
-
Play:
python legged_gym/scripts/play.py --task=go2
- By default, the loaded policy is the last model of the last run of the experiment folder.
- Other runs/model iteration can be selected by setting
load_run
andcheckpoint
in the train config.
2.1 Play Demo
Go2 | G1 | H1 | H1_2 |
---|---|---|---|
3. Sim in Mujoco
3.1 Mujoco Usage
To execute sim2sim in mujoco, execute the following command:
python deploy/deploy_mujoco/deploy_mujoco.py {config_name}
config_name
: The file name of the configuration file. The configuration file will be found under deploy/deploy_mujoco/configs/
, for example g1.yaml
, h1.yaml
, h1_2.yaml
.
example:
python deploy/deploy_mujoco/deploy_mujoco.py g1.yaml
3.2 Mujoco Demo
G1 | H1 | H1_2 |
---|---|---|
4. Deploy on Physical Robot
reference to Deploy on Physical Robot(English) | 实物部署(简体中文)