cyy/go2_rl_robotlab
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update readme: fix installation guide, add difference from go2_rl_gym; rename terrains.py.

Browse Source
This commit is contained in:
wertyuilife
2026-04-20 21:35:41 +08:00
parent 34ba7465a9
commit 52b14b0c3f
3 changed files with 11 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
README.md
View File

@@ -19,23 +19,21 @@ It is a reproduction of [go2_rl_gym](https://github.com/wty-yy/go2_rl_gym), adap
### 1. Install IsaacLab
Install IsaacLab v2.3.0 by following the [guide](https://isaac-sim.github.io/IsaacLab/v2.3.0/source/setup/quickstart.html#). Please make sure to clone the IsaacLab repository and perform the installation using the release/2.3.0 branch.
After installation, your environment should satisfies:
Install IsaacLab follow [official guide](https://isaac-sim.github.io/IsaacLab/v2.3.2/source/setup/installation/isaaclab_pip_installation.html):
```bash
isaacsim <= 5.1.0.0 # tested on 5.1.0.0
isaaclab <= 0.54.3 # tested on 0.54.3, 0.53.1
isaaclab-rl <= 0.4.7 # tested on 0.4.7, 0.4.4
conda create -n go2_rl_robotlab python=3.11
conda activate go2_rl_robotlab
pip install --upgrade pip
pip install isaaclab[isaacsim,all]==2.3.2.post1 --extra-index-url https://pypi.nvidia.com
pip install -U torch==2.7.0 torchvision==0.22.0 --index-url https://download.pytorch.org/whl/cu128
```
Higher version may cause conflicts with our customized `rsl_rl==3.3.0` and `robot_lab==2.3.0`.
---
### 2. Install Customized RSL-RL and RobotLab
We uses a customized version of `rsl_rl` and `robot_lab`. Install them in editable mode:
We uses a customized version of `rsl_rl==3.3.0` and `robot_lab==2.3.0`. Install them in editable mode:
```bash
python -m pip install -e source/robot_lab
@@ -183,7 +181,9 @@ xml_path: "{ROOT_DIR}/resources/go2/your-custom-scene.xml"
## Differences from `go2_rl_gym`
- Different tracking reward formulation (fixed sigma vs. dynamic sigma)
- Different reward weights (e.g., lower dof_acc_l2 weight in Lab due to physics-step level implementation and sensitivity to outliers)
- Different rewards:
- lower dof_acc_l2 weight in Lab due to physics-step level implementation and sensitivity to outliers
- extra joint_pos_penalty_l1 reward in Lab due to better performance
- Lack domain_rand: randomize_motor_strength
---

2
source/robot_lab/robot_lab/tasks/go2/env_cfg.py
View File

@@ -18,7 +18,7 @@ from isaaclab.utils.noise import AdditiveUniformNoiseCfg as Unoise
import robot_lab.tasks.go2.mdp as mdp
from robot_lab.assets.unitree import GO2_CFG_ROBOTLAB, GO2_CFG_UNITREE
from robot_lab.tasks.go2.mdp.terrain import TERRAIN_CFG
from robot_lab.tasks.go2.mdp.terrains import TERRAIN_CFG
JOINT_NAMES = [
"FL_hip_joint", "FL_thigh_joint", "FL_calf_joint",

0
source/robot_lab/robot_lab/tasks/go2/mdp/terrain.py → source/robot_lab/robot_lab/tasks/go2/mdp/terrains.py
View File