# isaac_berkeley_humanoid

**Repository Path**: Yu1377/isaac_berkeley_humanoid

## Basic Information

- **Project Name**: isaac_berkeley_humanoid
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2025-11-04
- **Last Updated**: 2025-11-19

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# Berkeley Humanoid Traning Code

[![IsaacSim](https://img.shields.io/badge/IsaacSim-4.0.0-silver.svg)](https://docs.omniverse.nvidia.com/isaacsim/latest/overview.html)
[![Isaac Lab](https://img.shields.io/badge/IsaacLab-1.0.0-silver)](https://isaac-sim.github.io/IsaacLab)
[![Python](https://img.shields.io/badge/python-3.10-blue.svg)](https://docs.python.org/3/whatsnew/3.10.html)
[![Linux platform](https://img.shields.io/badge/platform-linux--64-orange.svg)](https://releases.ubuntu.com/20.04/)

## Overview

This repository shows the training code for Berkeley Humanoid with IsaacLab.



```bash
├── scripts
│   ├── rsl_rl
│   │   ├── cli_args.py
│   │   ├── play.py
│   │   └── train.py
└── source
    └── isaaclab_extension_tutorial
        ├── config
        │   └── extension.toml
        ├── docs
        │   └── CHANGELOG.rst
        ├── isaaclab_extension_tutorial
        │   ├── actuators                # 关节执行器模型
        │   ├── assets                   # 资源。机器人
        │   │   ├── actuators.py
        │   │   ├── duck.py
        │   │   ├── __init__.py
        │   │   └── robots
        │   ├── __init__.py
        │   ├── tasks                    # 任务，核心部分。包括奖励/事件/课程等
        │   │   ├── __init__.py
        │   │   ├── manager_based
        │   │   │   ├── __init__.py
        │   │   │   ├── isaaclab_extension_tutorial
        │   │   │   │   ├── agents
        │   │   │   │   │   ├── __init__.py
        │   │   │   │   │   └── rsl_rl_ppo_cfg.py
        │   │   │   │   ├── __init__.py
        │   │   │   │   ├── isaaclab_extension_tutorial_env_cfg.py
        │   │   │   │   ├── mdp
        │   │   │   │   │   ├── __init__.py
        │   │   │   │   │   ├── observations.py
        │   │   │   │   │   └── rewards.py
        │   ├── terrains                 # 地形
        │   │   ├── __init__.py
        │   │   ├── __pycache__
        │   │   │   ├── __init__.cpython-311.pyc
        │   │   │   └── terrain_generator_cfg.cpython-311.pyc
        │   │   └── terrain_generator_cfg.py
        │   └── ui_extension_example.py
        ├── pyproject.toml
        └── setup.py
        
soft_joint_pos_limit_factor=0.95, # 软关节姿态限制：执行器实际物理限制的95%
```



## Publications

If you use this work in an academic context, please consider citing the following publications:

```bash
@misc{2407.21781,
Author = {Qiayuan Liao and Bike Zhang and Xuanyu Huang and Xiaoyu Huang and Zhongyu Li and Koushil Sreenath},
Title = {Berkeley Humanoid: A Research Platform for Learning-based Control},
Year = {2024},
Eprint = {arXiv:2407.21781},
}
```

### Installation

- Install Isaac Lab, see
  the [installation guide](https://isaac-sim.github.io/IsaacLab/source/setup/installation/index.html). **Please use
  [IsaacLab v1.0.0 with IsaacSim 4.0.0](https://github.com/isaac-sim/IsaacLab/blob/3ad18a8e1a5c166ad1a22f105d47a5c578de68d7/docs/source/setup/installation/pip_installation.rst)**.

- Using a python interpreter that has Isaac sLab installed, install the library

```bash
cd exts/skyentific_poclegs/
python -m pip install -e .
```

## Run

Training an agent with RSL-RL on Velocity-Rough-Berkeley-Humanoid-v0:

```bash
# run script for training
python scripts/rsl_rl/train.py --task Velocity-Rough-Skyentific-Poclegs-v0 --headless
# run script for playing
python scripts/rsl_rl/play.py --task Velocity-Rough-Skyentific-Poclegs-Play-v0
# 查看日志
tensorboard --logdir=logs
```

## FAQ
**Q: Why doesn't the maximum torque of each joint match the values in the paper?**

**A:** The maximum torque is limited for safety reasons.

**Q: Where is the joint armature from?**

**A:** From CAD system.

**Q: Why does the friction of each joint so large?**

**A:** The motor we used has large cogging torque, we include it in the friction of the actuator model.