Real-Time Whole-Body Control of Legged Robots with Model-Predictive Path Integral Control
Authors:
- 19 May 2025
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 14721-14727
Abstract
This paper presents a system for enabling real-time synthesis of whole-body locomotion and manipulation policies for real-world legged robots. Motivated by recent advancements in robot simulation, we leverage the efficient parallelization capabilities of the MuJoCo simulator on a multi-core CPU to achieve fast sampling over the robot state and action trajectories. Our results show surprisingly effective real-world locomotion and manipulation capabilities with a very simple control strategy. We demonstrate our approach on several hardware and simulation experiments: robust locomotion over flat and uneven terrains, climbing over a box whose height is comparable to the robot, and pushing a box to a goal position. To our knowledge, this is the first successful deployment of whole-body sampling-based MPC on real-world legged robot hardware. Experiment videos and code can be found at: whole-body-mppi.github.io.Keywords
All Related Versions
Funding Information
- Universidad de Guadalajara (V/2022/397)
This publication has 26 references indexed in Scilit:
- Extreme Parkour with Legged Robots2024
- ReLU-QP: A GPU-Accelerated Quadratic Programming Solver for Model-Predictive Control2024
- Reference-Free Model Predictive Control for Quadrupedal LocomotionIEEE Access, 2023
- DribbleBot: Dynamic Legged Manipulation in the Wild2023
- Contact Optimization for Non-Prehensile Loco-Manipulation via Hierarchical Model Predictive Control2023
- Aquarium: A Fully Differentiable Fluid-Structure Interaction Solver for Robotics Applications2023
- Information theoretic MPC for model-based reinforcement learning2017
- Aggressive driving with model predictive path integral control2016
- Optimization-based locomotion planning, estimation, and control design for the atlas humanoid robotAutonomous Robots, 2015
- MuJoCo: A physics engine for model-based control2012