Overview

This repository provides basic reinforcement learning implementations for quadruped locomotion in IsaacLab. It includes support for different robots available at DLS, along with scripts for both sim-to-sim and sim-to-real transfer.

Features:

• Cuncurrent State Estimator
• Rapid Motor Adaptation
• Morphological Symmetries
• Adversarial Motion Priors (big thanks to Giuseppe L'erario and Giulio Romualdi)
• Sim-to-Sim in Mujoco
• Sim-to-Real in ROS1 and ROS2

A list of robots and environments available are 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.

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},
}