RL-Augmented MPC for Non-Gaited Legged and Hybrid Locomotion

TL;DR

This paper introduces a hierarchical RL-MPC architecture for legged and hybrid robots, enabling effective gait learning and transfer from simulation to real-world without domain randomization.

Contribution

It presents a contact-explicit hierarchical framework coupling RL and MPC, allowing zero-shot sim-to-real transfer and minimal reward tuning for diverse robotic platforms.

Findings

Emergence of acyclic gaits and timing adaptations in simulation

Zero-shot sim-to-sim transfer across platforms

Successful zero-shot sim-to-real transfer on a humanoid robot

Abstract

We propose a contact-explicit hierarchical architecture coupling Reinforcement Learning (RL) and Model Predictive Control (MPC), where a high-level RL agent provides gait and navigation commands to a low-level locomotion MPC. This offloads the combinatorial burden of contact timing from the MPC by learning acyclic gaits through trial and error in simulation. We show that only a minimal set of rewards and limited tuning are required to obtain effective policies. We validate the architecture in simulation across robotic platforms spanning 50 kg to 120 kg and different MPC implementations, observing the emergence of acyclic gaits and timing adaptations in flat-terrain legged and hybrid locomotion, and further demonstrating extensibility to non-flat terrains. Across all platforms, we achieve zero-shot sim-to-sim transfer without domain randomization, and we further demonstrate zero-shot sim-to-real transfer without domain randomization on Centauro, our 120 kg wheeled-legged humanoid robot. We make our software framework and evaluation results publicly available at https://github.com/AndrePatri/AugMPC.