PPL: Point Cloud Supervised Proprioceptive Locomotion Reinforcement Learning for Legged Robots in Crawl Spaces

TL;DR

This paper introduces a point cloud supervised reinforcement learning framework that enables legged robots to navigate crawl spaces more efficiently using proprioceptive sensing and novel point cloud feature extraction techniques.

Contribution

The study presents a new RL framework with a state estimation network and point cloud feature extraction, improving crawl space locomotion without exteroceptive sensors.

Findings

Faster training iteration times compared to existing methods.

More agile and effective locomotion in crawl spaces.

Enhanced proprioceptive navigation capabilities.

Abstract

Legged locomotion in constrained spaces (called crawl spaces) is challenging. In crawl spaces, current proprioceptive locomotion learning methods are difficult to achieve traverse because only ground features are inferred. In this study, a point cloud supervised RL framework for proprioceptive locomotion in crawl spaces is proposed. A state estimation network is designed to estimate the robot's collision states as well as ground and spatial features for locomotion. A point cloud feature extraction method is proposed to supervise the state estimation network. The method uses representation of the point cloud in polar coordinate frame and MLPs for efficient feature extraction. Experiments demonstrate that, compared with existing methods, our method exhibits faster iteration time in the training and more agile locomotion in crawl spaces. This study enhances the ability of legged robots to traverse constrained spaces without requiring exteroceptive sensors.