Rapid Locomotion via Reinforcement Learning

TL;DR

This paper introduces a reinforcement learning-based controller enabling the MIT Mini Cheetah to perform rapid, agile movements like sprinting and turning on various terrains, demonstrating high speed and robustness in real-world conditions.

Contribution

It presents a novel end-to-end neural network controller trained in simulation and successfully transferred to real robots for record-breaking agility in legged locomotion.

Findings

Achieved speeds up to 3.9 m/s in real-world tests.

Demonstrated robust performance on natural terrains.

Enabled rapid maneuvers with stable control.

Abstract

Agile maneuvers such as sprinting and high-speed turning in the wild are challenging for legged robots. We present an end-to-end learned controller that achieves record agility for the MIT Mini Cheetah, sustaining speeds up to 3.9 m/s. This system runs and turns fast on natural terrains like grass, ice, and gravel and responds robustly to disturbances. Our controller is a neural network trained in simulation via reinforcement learning and transferred to the real world. The two key components are (i) an adaptive curriculum on velocity commands and (ii) an online system identification strategy for sim-to-real transfer leveraged from prior work. Videos of the robot's behaviors are available at: https://agility.csail.mit.edu/