Efficient Safety Verification of Autonomous Vehicles with Neural Network Operator

TL;DR

This paper introduces a neural network operator-based method for safety verification of autonomous vehicles, significantly improving efficiency in reachability analysis while maintaining accuracy.

Contribution

It proposes a novel neural network operator approach to compute reachable sets, replacing traditional set operators for faster safety verification.

Findings

Demonstrates superior efficiency over classical methods

Maintains comparable accuracy in safety verification

Validated through experiments in typical driving scenarios

Abstract

When autonomous vehicles encounter untrained scenarios, ensuring safety hinges on effective safety verification to prevent accidents stemming from unexpected model decisions. Reachability analysis, a method of safety verification, offers relatively high precision but at the cost of significant computational complexity. Our method leverages end-to-end neural network operators to compute reachable sets, replacing traditional mathematical set operators, thereby achieving higher efficiency in safety verification without substantially compromising accuracy or increasing conservativeness. We define vehicle dynamics on discrete time series and detail the safety verification process and safety standard based on reachable sets. Experimental evaluations conducted in several typical road driving scenarios demonstrate the superior efficiency performance of our proposed operator over classical methods.