Reference-Free Sampling-Based Model Predictive Control

TL;DR

This paper introduces a sampling-based MPC framework that autonomously discovers diverse locomotion behaviors, including gaits and jumps, on quadruped and humanoid robots, without predefined patterns or offline training.

Contribution

It proposes a novel cubic Hermite spline parameterization for MPPI that enables real-time, contact-adaptive control on standard CPUs, facilitating emergent behaviors without handcrafted gaits.

Findings

Successfully demonstrated emergent gaits on the Go2 quadruped robot.

Achieved complex behaviors like backflips and handstands in simulation.

Operated in real-time on CPU hardware without GPU acceleration.

Abstract

We present a sampling-based model predictive control (MPC) framework that enables emergent locomotion without relying on handcrafted gait patterns or predefined contact sequences. Our method discovers diverse motion patterns, ranging from trotting to galloping, robust standing policies, jumping, and handstand balancing, purely through the optimization of high-level objectives. Building on model predictive path integral (MPPI), we propose a cubic Hermite spline parameterization that operates on position and velocity control points. Our approach enables contact-making and contact-breaking strategies that adapt automatically to task requirements, requiring only a limited number of sampled trajectories. This sample efficiency enables real-time control on standard CPU hardware, eliminating the GPU acceleration typically required by other state-of-the-art MPPI methods. We validate our approach on the Go2 quadrupedal robot, demonstrating a range of emergent gaits and basic jumping capabilities. In simulation, we further showcase more complex behaviors, such as backflips, dynamic handstand balancing and locomotion on a Humanoid, all without requiring reference tracking or offline pre-training.