legged-locomotion

Companion repository for "Evolution of Humanoid Locomotion Control" in Science Robotics (2026)

Whole body Inverse Kinematics based on Pinocchio and qpmad

Reproduction of the Walk These Ways low-level locomotion controller in a MuJoCo environment for the AlienGo quadruped, enabling sim-to-sim evaluation of policies originally trained in Isaac Gym.

ASTRA: open-source 9.5 kg quadruped with a 3-DoF active spine. CAD + STM32 firmware + ROS 2 stack + thesis.

A legged locomotion project

Custom 18-DoF hexapod robot — Kuramoto-CPG locomotion controller, real-time gait visualiser, IMU heading-hold autonomous firmware, full mechanical CAD, and a 34-test verification suite.

Trot and walk gait generation for a quadruped with support polygon and stability margin analysis.

Unitree Go2 based on legged_gym

Unitree H1 humanoid walking via DeepMimic-style imitation learning — MuJoCo MJX + JAX, 4096 parallel envs, 9000 FPS, full 19-DOF control against real human mocap data

This repository contains a simulation for a flexible spine quadruped robot, designed to model and analyze the dynamics of legged locomotion. The simulation incorporates both rigid and flexible spine models to investigate the effects of body compliance on gait efficiency, stability, and energy consumption.

ROS2 quadruped robotics framework for simulation and small prototypes.

PPO ANYmal C with variable impedance control across 6 terrains in Isaac Sim

Reinforcement learning for a moving center of mass robot that traverses uneven, unseen terrain at high speed from a single onboard camera. CMU Biorobotics thesis work, PPO in Isaac Gym and MuJoCo.

DM-Dog-RL is a reinforcement-learning locomotion project for a Damiao-motor quadruped robot. It contains both the training stack and the real-robot ROS deployment workspace.

Sampling-based MPC (MPPI / Predictive Sampling) on the true MuJoCo simulator — DM-Control walker and Unitree Go2.

Lab code for the book Bio-Inspired Robotics with MuJoCo: Quadruped Locomotion. Build a quadruped in MuJoCo 3.12, make it walk with a CPG, measure the gait, and refine it with Gymnasium + Stable Baselines3 PPO. Korean edition: wikidocs.net/book/21135

《MuJoCo로 알아보는 Bio-inspired Robotics: 사족보행편》 전자책 실습 코드. MuJoCo 3.12 + Gymnasium + Stable Baselines3 PPO로 사족보행 로봇을 만들고, 걷게 하고, 걸음을 측정하고, 강화학습으로 보정합니다. 책: https://wikidocs.net/book/21135