Snake Robot with Tactile Perception Navigates on Large-scale Challenging Terrain

TL;DR

This paper presents a hierarchical reinforcement learning framework for snake robots equipped with tactile sensors, enabling effective navigation across large-scale, challenging terrains such as caves, by improving adaptability and motion efficiency.

Contribution

The study introduces a novel tactile perception-based control framework with distributed training for snake robots, enhancing their terrain adaptability and navigation performance.

Findings

Improved navigation efficiency in complex terrains.

Effective integration of tactile perception in control architecture.

Successful large-scale cave exploration simulation.

Abstract

Along with the advancement of robot skin technology, there has been notable progress in the development of snake robots featuring body-surface tactile perception. In this study, we proposed a locomotion control framework for snake robots that integrates tactile perception to augment their adaptability to various terrains. Our approach embraces a hierarchical reinforcement learning (HRL) architecture, wherein the high-level orchestrates global navigation strategies while the low-level uses curriculum learning for local navigation maneuvers. Due to the significant computational demands of collision detection in whole-body tactile sensing, the efficiency of the simulator is severely compromised. Thus a distributed training pattern to mitigate the efficiency reduction was adopted. We evaluated the navigation performance of the snake robot in complex large-scale cave exploration with challenging terrains to exhibit improvements in motion efficiency, evidencing the efficacy of tactile perception in terrain-adaptive locomotion of snake robots.