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

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.

References in corpus (9)

• Adam: A Method for Stochastic Optimization
• Social Force Model for Pedestrian Dynamics
• High-Dimensional Continuous Control Using Generalized Advantage Estimation
• Learning to Communicate with Deep Multi-Agent Reinforcement Learning
• Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning
• Mapless Navigation among Dynamics with Social-safety-awareness: a reinforcement learning approach from 2D laser scans
• Celebrating Diversity in Shared Multi-Agent Reinforcement Learning
• Arena-Bench: A Benchmarking Suite for Obstacle Avoidance Approaches in Highly Dynamic Environments
• Social diversity and social preferences in mixed-motive reinforcement learning