Robot Squid Game: Quadrupedal Locomotion for Traversing Narrow Tunnels

TL;DR

This paper presents a reinforcement learning framework that enables quadruped robots to traverse complex narrow tunnels by combining procedural environment generation and policy distillation, improving robustness and adaptability.

Contribution

It introduces a novel RL approach using teacher-student policy transfer with procedural environment synthesis for confined space navigation.

Findings

Robust traversal across diverse tunnel geometries achieved in simulation and real-world.

Elimination of complex reward shaping simplifies training process.

Unified policy generalizes well to various confined environments.

Abstract

Quadruped robots demonstrate exceptional potential for navigating complex terrain in critical applications such as search and rescue missions and infrastructure inspection However autonomous traversal of confined 3D environments including tunnels caves and collapsed structures remains a significant challenge Existing methods often struggle with rigid gait patterns limited adaptability to diverse geometries and reliance on oversimplified environmental assumptions This paper introduces a Reinforcement Learning RL framework that combines procedural environment generation with policy distillation to enable robust locomotion across various tunnel configurations Our approach leverages a teacher student training paradigm where specialized expert policies trained on procedurally generated tunnel geometries transfer their knowledge to a unified student policy This strategy eliminates the need for complex reward shaping in end-to-end RL training simplifying the process by breaking down complicated tasks into smaller more manageable components that are easier for the robot to learn By synthesizing diverse tunnel structures during training and distilling navigation strategies into a generalizable policy our method achieves consistent traversal across complex spatial constraints where conventional approaches fail We demonstrate through both simulation and real world experiments that our method enables quadruped robots to successfully traverse challenging confined tunnel environments