Improving the Generalization of Unseen Crowd Behaviors for Reinforcement Learning based Local Motion Planners
This work addresses the challenge of deploying safe mobile robot policies in unpredictable human pedestrian environments, representing an incremental improvement in domain-specific motion planning.
The paper tackles the problem of reinforcement learning-based motion planners overfitting to simulated pedestrian movements, which reduces their adaptability to unseen crowd behaviors, by introducing a method that enhances agent diversity within a single policy to improve generalization, resulting in behavior-conditioned policies that outperform existing works in challenging scenarios by reducing potential collisions without extra time or travel.
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.