One-Step Integration of AMP into IsaacLab

A flexible optimization framework for whole-body loco-manipulation, built with Pinocchio and CasADi. Supports multiple dynamics formulations and solver backends.

UMI on Legs: Making Manipulation Policies Mobile with Manipulation-Centric Whole-body Controllers

[RSS 2023] Diffusion Policy Visuomotor Policy Learning via Action Diffusion

Code for the paper "Planning with Diffusion for Flexible Behavior Synthesis"

Adversarial Motion Priror(AMP) for Isaaclab manager based env

Batched SRBD-MPC tailored for learning and model-based combined research.

GPU-Accelerated Trajectory Optimization

Numerical Inverse Kinematics solver based on JAX + MJX

Model Predictive Control in JAX

Fast QP Solver in JAX

GPU-friendly, auto-differentiable LQR solver with JAX.

Official implementation of OpenWBT.

TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videos

Code for ECCV 2020 paper "Contacts and Human Dynamics from Monocular Video".

Python inverse kinematics based on MuJoCo

Whole-Body Nonlinear MPC for Realtime Humanoid Loco-Manipulation Planning and Control

Locomotion tasks for bipedal robots in IsaacLab

[Humanoids 2025 Oral] Universal Humanoid Robot Pose Learning from Internet Human Videos

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)

Official code of "HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation", CVPR 2021

Fatrop is a nonlinear optimal control problem solver that aims to be fast, support a broad class of optimal control problems and achieve a high numerical robustness.

Numerical experiments for the paper: "MPCGPU: Real-Time Nonlinear Model Predictive Control through Preconditioned Conjugate Gradient on the GPU"

🐕 Quadruped manipulator planner and controller using MPC and WBC based on OCS2: Unitree AlienGo + Z1

RAPTOR: RAPid and Robust Trajectory Optimization for Robots