Socially Aware Crowd Navigation with Multimodal Pedestrian Trajectory Prediction for Autonomous Vehicles

TL;DR

This paper introduces SARL-SGAN-KCE, a novel approach combining multimodal pedestrian trajectory prediction with a socially aware reinforcement learning framework, improving autonomous vehicle navigation safety in crowded environments.

Contribution

It presents a new method integrating multimodal human trajectory prediction with a socially aware reinforcement learning policy, considering vehicle kinematics for safer crowd navigation.

Findings

Outperforms state-of-the-art crowd navigation methods

Provides safer and more human-like navigation behaviors

Demonstrates effectiveness through ablation studies

Abstract

Seamlessly operating an autonomous vehicle in a crowded pedestrian environment is a very challenging task. This is because human movement and interactions are very hard to predict in such environments. Recent work has demonstrated that reinforcement learning-based methods have the ability to learn to drive in crowds. However, these methods can have very poor performance due to inaccurate predictions of the pedestrians' future state as human motion prediction has a large variance. To overcome this problem, we propose a new method, SARL-SGAN-KCE, that combines a deep socially aware attentive value network with a human multimodal trajectory prediction model to help identify the optimal driving policy. We also introduce a novel technique to extend the discrete action space with minimal additional computational requirements. The kinematic constraints of the vehicle are also considered to ensure smooth and safe trajectories. We evaluate our method against the state of art methods for crowd navigation and provide an ablation study to show that our method is safer and closer to human behaviour.