Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Sim-to-real RL training and deployment tools for the Unitree Go1 robot.
| Date | Stars |
|---|---|
| 2026-07-24 | 1422 |
| 2026-07-25 | 1422 |
| 2026-07-28 | 1422 |
| 2026-07-30 | 1422 |
| 2026-08-06 | 1422 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Go1 Sim-to-Real Locomotion Starter Kit
# Table of contents
1. [Overview](#overview)
2. [System Requirements](#requirements)
3. [Training a Model](#simulation)
1. [Installation](#installation)
2. [Environment and Model Configuration](#configuration)
3. [Training and Logging](#training)
4. [Analyzing the Policy](#analysis)
4. [Deploying a Model](#realworld)
1. [Installing the Deployment Utility](#robotconfig)
2. [Running the Controller](#runcontroller)
3. [RC Configuration](#rcconfig)
2. [Deploying a Custom Model](#configuration)
4. [Deployment and Logging](#deployment)
5. [Analyzing Real-world Performance](#plotting)
5. [Debugging Common Errors](#debugging)
## Overview <a name="overview"></a>
This repository provides an implementation of the paper:
<td style="padding:20px;width:75%;vertical-align:middle">
<a href="https://gmargo11.github.io/walk-these-ways/" target="_blank">
<b> Walk these Ways: Tuning Robot Control for Generalization with Multiplicity of Behavior </b>
</a>
<br>
<a href="https://gmargo11.github.io/" target="_blank">Gabriel B. Margolis</a> and <a href="https://people.csail.mit.edu/pulkitag" target="_blank">Pulkit Agrawal</a>
<br>
<em>Conference on Robot Learning</em>, 2022
<br>
<a href="https://openreview.net/pdf?id=52c5e73SlS2">paper</a> /
<a href="https://gmargo11.github.io/walk-these-ways/" target="_blank">project page</a>
<br>
</td>
<br>
If you use this repository in your work, consider citing:
```
@article{margolis2022walktheseways,
title={Walk These Ways: Tuning Robot Control for Generalization with Multiplicity of Behavior},
author={Margolis, Gabriel B and Agrawal, Pulkit},
journal={Conference on Robot Learning},
year={2022}
}
```
<br>
This environment builds on the [legged gym environment](https://leggedrobotics.github.io/legged_gym/) by Nikita
Rudin, Robotic Systems Lab, ETH Zurich (Paper: https://arxiv.org/abs/2109.11978) and the Isaac Gym simulator from
NVIDIA (Paper: https://arxiv.org/abs/2108.10470). Training code builds on the
[rsl_rl](https://github.com/leggedrobotics/rsl_rl) repository, also by Nikita
Rudin, Robotic Systems Lab, ETH Zurich. All redistributed code retains its
original [license](LICENSES/legged_gym/LICENSE).
Our initial release provides the following features:
* Train reinforcement learning policies for the Go1 robot using PPO, IsaacGym, Domain Randomization, and Multiplicity of Behavior (MoB).
* Evaluate a pretrained MoB policy in simulation.
* Deploy learned policies on the Go1 using the `unitree_legged_sdk`.
## System Requirements <a name="requirements"></a>
**Simulated Training and Evaluation**: Isaac Gym requires an NVIDIA GPU. To train in the default configuration, we recommend a GPU with at least 10GB of VRAM. The code can run on a smaller GPU if you decrease the number of parallel environments (`Cfg.env.num_envs`). However, training will be slower with fewer environments.
**Hardware Deployment**: We provide deployment code for the Unitree Go1 Edu robot. This relatively low-cost, commercially available quadruped can be purchased here: https://shop.unitree.com/. You will need the Edu version of the robot to run and customize your locomotion controller.
## Training a Model <a name="simulation"></a>
### Installation <a name="installation"></a>
#### Install pytorch 1.10 with cuda-11.3:
```bash
pip3 install torch==1.10.0+cu113 torchvision==0.11.1+cu113 torchaudio==0.10.0+cu113 -f https://download.pytorch.org/whl/cu113/torch_stable.html
```
#### Install Isaac Gym
1. Download and install Isaac Gym Preview 4 from https://developer.nvidia.com/isaac-gym
2. unzip the file via:
```bash
tar -xf IsaacGym_Preview_4_Package.tar.gz
```
3. now install the python package
```bash
cd isaacgym/python && pip install -e .
```
4. Verify the installation by try running an example
```bash
python examples/1080_balls_of_solitudExcerpt of 11,784 characters
Read on GitHub
22
1
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:1facedc0f357c6b5, topic:reinforcement-learning, readme:reinforcement learning
matched fp:1facedc0f357c6b5, topic:robotics, readme:robot learning