Deep RL for MPC control of Quadruped Robot Locomotion

New repo collection for NVIDIA Cosmos: https://github.com/nvidia-cosmos

A generative world for general-purpose robotics & embodied AI learning.

Implementation of rectified flow and some of its followup research / improvements in Pytorch

Imitation learning benchmark focusing on complex locomotion tasks using MuJoCo.

Robot-centric elevation mapping for rough terrain navigation

c++ cubic spline library

Linear optimization software

The Advanced Proximal Optimization Toolbox

Optimizing Dynamic Programming-Based Algorithms

Fast and embedded solvers for nonlinear optimal control and nonlinear model predictive control

C++ interface for hpipm, a high-performance interior point MPC solver

A fast and flexible implementation of Rigid Body Dynamics algorithms and their analytical derivatives

High-performance interior-point-method QP and QCQP solvers

Model-based design and verification for robotics.

Elevation Mapping on GPU.

qpSWIFT is a light-weight sparse quadratic programming solver

Optimal Control for Switched Systems

Multi-Joint dynamics with Contact. A general purpose physics simulator.

An Eigen-based, light-weight C++ Interface to Nonlinear Programming Solvers (Ipopt, Snopt)

Solutions of Reinforcement Learning, An Introduction

Great resources for learning optimal control

Robotics software featuring legged locomotion algorithms and a momentum-based controller core with optimization. Supporting software for world-class robots including humanoids, running birds, exosk…

A Python-embedded modeling language for convex optimization problems.