README.md

May 6, 2026 · View on GitHub

Overview

Reinforcement learning implementation of quadruped locomotion in IsaacLab. It includes support for different robots available at DLS, with scripts for both sim-to-sim and sim-to-real transfer.

Features:

Concurrent State Estimator
Rapid Motor Adaptation
Morphological Symmetries
Adversarial Motion Priors (big thanks to Giuseppe L'erario and Giulio Romualdi)
Identification of robot parameters for sim2real using pace via our repo sim2real-robot-identification
Sim-to-Sim in Mujoco
Sim-to-Real using ROS2

Features work in progress - done but not tested:

Dagger for depth-to-heightmap policy distillation
Depth-to-Heightmap NN for avoiding the distillation step above

Real-world deployment via:

muse for state estimation (if no concurrent state estimation is used)
unitree-ros2-dls for unitree robot communication

A list of robots and environments available is described below:

Robot Model	Environment Name Pattern
Aliengo, Go2, B2, HyQReal2	Locomotion-RobotModel-Flat-Blind Locomotion-RobotModel-Rough-Blind Locomotion-RobotModel-Rough-Vision

Installation and Runs

If you want only to deploy a trained policy on your robot, continue on README_DEPLOY otherwise on README_TRAIN.

For the train, check first the compatibility with IsaacLab and rsl-rl at the top of this readme. They indicate the releases that we tested.

Citing this work

If you find the work useful and you adopt Morphological Symmetries, please consider citing one of our works:

Leveraging Symmetry in RL-based Legged Locomotion Control (IROS-2024)

@inproceedings{suhuang2024leveraging,
  author={Su, Zhi and Huang, Xiaoyu and Ordoñez-Apraez, Daniel and Li, Yunfei and Li, Zhongyu and Liao, Qiayuan and Turrisi, Giulio and Pontil, Massimiliano and Semini, Claudio and Wu, Yi and Sreenath, Koushil},
  booktitle={2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)}, 
  title={Leveraging Symmetry in RL-based Legged Locomotion Control}, 
  year={2024},
  pages={6899-6906},
  doi={10.1109/IROS58592.2024.10802439}
}

Morphological symmetries in robotics (IJRR-2025):

@article{ordonez2025morphosymm,
  author = {Daniel Ordoñez-Apraez and Giulio Turrisi and Vladimir Kostic and Mario Martin and Antonio Agudo and Francesc Moreno-Noguer and Massimiliano Pontil and Claudio Semini and Carlos Mastalli},
  title ={Morphological symmetries in robotics},
  journal = {The International Journal of Robotics Research},
  year = {2025},
  volume = {44},
  number = {10-11},
  pages = {1743-1766},
  doi = {10.1177/02783649241282422},
}

How to contribute

PRs are very welcome (search for TODO in the issue, or add what you like)!

Maintainer

This repository is maintained by Giulio Turrisi.