Blind Bipedal Stair Traversal via Sim-to-Real Reinforcement Learning

TL;DR

This paper demonstrates that sim-to-real reinforcement learning enables a bipedal robot to traverse stairs reliably using only proprioceptive feedback, without relying on external perception or terrain models.

Contribution

It introduces a novel approach of training a bipedal robot with RL on randomized stair terrains, achieving real-world stair traversal without perception-based sensing.

Findings

Successful real-world stair traversal by Cassie using RL

No external perception or terrain models needed

Robustness to stair-like disturbances demonstrated

Abstract

Accurate and precise terrain estimation is a difficult problem for robot locomotion in real-world environments. Thus, it is useful to have systems that do not depend on accurate estimation to the point of fragility. In this paper, we explore the limits of such an approach by investigating the problem of traversing stair-like terrain without any external perception or terrain models on a bipedal robot. For such blind bipedal platforms, the problem appears difficult (even for humans) due to the surprise elevation changes. Our main contribution is to show that sim-to-real reinforcement learning (RL) can achieve robust locomotion over stair-like terrain on the bipedal robot Cassie using only proprioceptive feedback. Importantly, this only requires modifying an existing flat-terrain training RL framework to include stair-like terrain randomization, without any changes in reward function. To our knowledge, this is the first controller for a bipedal, human-scale robot capable of reliably traversing a variety of real-world stairs and other stair-like disturbances using only proprioception.