Learning from Demonstration with Failure Awareness for Safe Robot Navigation

TL;DR

This paper introduces a failure-aware learning framework for robot navigation that effectively utilizes failure experiences to improve safety without compromising task success, applicable in offline RL settings.

Contribution

It proposes a novel decoupling approach that separates success and failure data, enhancing safety in robot navigation by leveraging failure experiences effectively.

Findings

Reduces collision rates in navigation tasks

Maintains high task success rates

Generalizes across environments and robot platforms

Abstract

Learning from demonstration is widely used for robot navigation, yet it suffers from a fundamental limitation: demonstrations consist predominantly of successful behaviors and provide limited coverage of unsafe states. This limitation leads to poor safety when the robot encounters scenarios beyond the demonstration distribution. Failure experiences, such as collisions, contain essential information about unsafe regions, but remain underutilized. The key difficulty lies in the fact that failure data do not provide valid guidance for action imitation, and their naive incorporation into policy learning often degrades performance. We address this challenge by proposing a failure-aware learning framework that explicitly decouples the roles of success and failure data. In this framework, failure experiences are used to shape value estimation in hazardous regions, while policy learning is restricted to successful demonstrations. This separation enables the effective use of failure data without corrupting policy behavior. We implement this design within an offline reinforcement learning (RL) setting and evaluate it in both simulation and real-world environments. The results show that our framework consistently reduces collision rates while preserving the task success rate, and demonstrate strong generalization across different environments and robot platforms.