Improving the Generalization of Unseen Crowd Behaviors for Reinforcement Learning based Local Motion Planners

TL;DR

This paper presents a method to improve reinforcement learning-based local motion planners for mobile robots by increasing agent diversity, leading to better generalization to unseen crowd behaviors and safer navigation.

Contribution

It introduces an information-theoretic approach to enhance agent diversity within a single policy, improving robustness against unpredictable pedestrian movements.

Findings

Behavior-conditioned policies outperform existing methods in diverse crowd scenarios.

The proposed method reduces potential collisions without increasing travel time.

Enhanced agent diversity improves adaptability to unseen crowd behaviors.

Abstract

Deploying a safe mobile robot policy in scenarios with human pedestrians is challenging due to their unpredictable movements. Current Reinforcement Learning-based motion planners rely on a single policy to simulate pedestrian movements and could suffer from the over-fitting issue. Alternatively, framing the collision avoidance problem as a multi-agent framework, where agents generate dynamic movements while learning to reach their goals, can lead to conflicts with human pedestrians due to their homogeneity. To tackle this problem, we introduce an efficient method that enhances agent diversity within a single policy by maximizing an information-theoretic objective. This diversity enriches each agent's experiences, improving its adaptability to unseen crowd behaviors. In assessing an agent's robustness against unseen crowds, we propose diverse scenarios inspired by pedestrian crowd behaviors. Our behavior-conditioned policies outperform existing works in these challenging scenes, reducing potential collisions without additional time or travel.