RMA: Rapid Motor Adaptation for Legged Robots

TLDR

Successful real‑world deployment of legged robots requires real‑time adaptation to unseen scenarios such as changing terrains, payloads, and wear. This paper introduces Rapid Motor Adaptation (RMA) to enable real‑time online adaptation in quadruped robots. RMA comprises a base policy and an adaptation module trained entirely in simulation with bioenergetics‑inspired rewards, enabling the A1 robot to adapt to diverse terrains in fractions of a second without fine‑tuning. RMA achieves state‑of‑the‑art performance on a wide range of real‑world and simulated terrains. Project webpage and videos are available at https://ashish-kmr.github.io/rma-legged-robots/.

Abstract

Successful real-world deployment of legged robots would require them to adapt in real-time to unseen scenarios like changing terrains, changing payloads, wear and tear. This paper presents Rapid Motor Adaptation (RMA) algorithm to solve this problem of real-time online adaptation in quadruped robots. RMA consists of two components: a base policy and an adaptation module. The combination of these components enables the robot to adapt to novel situations in fractions of a second. RMA is trained completely in simulation without using any domain knowledge like reference trajectories or predefined foot trajectory generators and is deployed on the A1 robot without any fine-tuning. We train RMA on a varied terrain generator using bioenergetics-inspired rewards and deploy it on a variety of difficult terrains including rocky, slippery, deformable surfaces in environments with grass, long vegetation, concrete, pebbles, stairs, sand, etc. RMA shows state-of-the-art performance across diverse real-world as well as simulation experiments. Project Webpage and Videos: https://ashish-kmr.github.io/rma-legged-robots/