Learning to Walk in the Real World with Minimal Human Effort

TL;DR

This paper presents a deep reinforcement learning system enabling legged robots to learn stable walking in real-world environments with minimal human effort, addressing data collection and safety challenges.

Contribution

It introduces a multi-task learning and safety-constrained RL framework for autonomous real-world locomotion learning on legged robots.

Findings

Successfully learned walking on flat, soft mattress, and creviced doormat.

Minimal human intervention required for training.

Demonstrated effective real-world robot locomotion learning.

Abstract

Reliable and stable locomotion has been one of the most fundamental challenges for legged robots. Deep reinforcement learning (deep RL) has emerged as a promising method for developing such control policies autonomously. In this paper, we develop a system for learning legged locomotion policies with deep RL in the real world with minimal human effort. The key difficulties for on-robot learning systems are automatic data collection and safety. We overcome these two challenges by developing a multi-task learning procedure and a safety-constrained RL framework. We tested our system on the task of learning to walk on three different terrains: flat ground, a soft mattress, and a doormat with crevices. Our system can automatically and efficiently learn locomotion skills on a Minitaur robot with little human intervention. The supplemental video can be found at: \url{https://youtu.be/cwyiq6dCgOc}.