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

Official implementation for the paper "Full-Order Sampling-Based MPC for Torque-Level Locomotion Control via Diffusion-Style Annealing". DIAL-MPC is a novel sampling-based MPC framework for legged robot full-order torque-level control with both precision and agility in a training-free manner.

Wild Visual Navigation: A system for fast traversability learning via pre-trained models and online self-supervision

All Terrain Autonomous Quadruped

Legged Robot environments for reinforcement learning in Genesis

CHAMP Package Config Generator

Probabilistic Contact State Estimation for Legged Robots in ROS

URDF descriptions for Upkie wheeled bipeds

RL applied to robotics.

Multiple experimental environments for Isaac Lab.

RL for Walk and Stop for quadruped legged robot (AlienGo - Unitree) + Examples. PPO (SKRL), DDPG (SKRL, SB3), TD3 (SB3).

Legged Contact Detection (LCD): A deep learning approach for Contact Estimation of Legged Robots using inertial and F/T measurements

Model predictive control to balance Upkie wheeled bipeds

Legged Contact Detection (LCD): A deep learning approach for Contact Estimation of Legged Robots using inertial and F/T measurements

Train a balancing policy for Upkie by reinforcement learning

The official Code for the paper "Safe Legged Locomotion using Collision Cone Control Barrier Functions (C3BFs)"

Control Spot legged robot with audio, build semantic navigation maps and support visual question answering

This package computes the Improved Feasible Region. This is an intersection between the Feasible Region (Orsolino, 2020) and the Reachable Region (a 2D level area representing the CoM reachable workspace). The details are explained in this preprint:

A SOFA environment is created for a tripedal soft legged robot model with Python scripts to be used for RL training along with system identification using PSO and GA algorithms for material parameters optimization.