OpenAI Gym environments for an open-source quadruped robot (SpotMicro)

Awesome Quadrupedal Robots

A model predictive controller for quadruped robots based on the single rigid body model and written in python. Gradient-based (acados) or Sampling-based (jax)

Learn how to train a quadruped robot to walk using reinforcement learning, from defining actions and observations to designing rewards and transitioning from simulation to reality.

Natural Locomotion, Jumping and Recovery of Quadruped Robot A1 with AMP

spotMicro机器狗中文攻略，纯新手教程！

Integrating Constraints in PPO (using Isaac Gym or Isaac Lab)

HyperDog is a quadruped robot which is fully based on ROS 2 and Micro-ROS

Model Predictive Control in JAX

Designed to improve some structures to achieve better performance, and learn the algorithms used in the pupper project.

Official implementation of "Learning Diverse Natural Behaviors for Enhancing the Agility of Quadrupedal Robots"

Official codebase for PRELUDE (Perceptive Locomotion Under Dynamic Environments)

Unofficial implementaton of the paper DTC: Deep Tracking Control

A training and deployment pipeline for visuomotor RL policy used to enhance the locomotion of Unitree Go1 robot dog.

RL applied to robotics.

StrideSim is a Nvidia Isaac Sim-based robot simulator, offering a realistic environment and compatibility with ROS2

Chance-Constrained MPC simulation for quadrupedal robots navigating uneven terrains and handling random payloads.

This is a quadruped simulated on pybullet physics engine, walking using trot and bound mechanisms

Personal legged_gym Unitree A1 implementation for paper 'Reinforcement Learning for Versatile, Dynamic, and Robust Bipedal Locomotion Control'. Homework repo for SJTU ACM class RL courses