Reactive and Safe Road User Simulations using Neural Barrier Certificates

TL;DR

This paper introduces a neural barrier certificate-based reactive agent model for traffic simulation that enhances safety, generalizes well to unseen conditions, and maintains realistic behavior compared to existing methods.

Contribution

It presents a novel reactive agent framework combining high-level decision learning with decentralized barrier certificates for improved safety and generalization in traffic simulations.

Findings

Significant safety improvements over state-of-the-art imitation learning.

Better generalization to unseen traffic scenarios.

Reactive agents react more effectively to other road users.

Abstract

Reactive and safe agent modelings are important for nowadays traffic simulator designs and safe planning applications. In this work, we proposed a reactive agent model which can ensure safety without comprising the original purposes, by learning only high-level decisions from expert data and a low-level decentralized controller guided by the jointly learned decentralized barrier certificates. Empirical results show that our learned road user simulation models can achieve a significant improvement in safety comparing to state-of-the-art imitation learning and pure control-based methods, while being similar to human agents by having smaller errors to the expert data. Moreover, our learned reactive agents are shown to generalize better to unseen traffic conditions, and react better to other road users and therefore can help understand challenging planning problems pragmatically.