Automatic Testing of Interacting Autonomous Vehicles

2026-07-14

AI Summary

This work addresses the limitation of existing autonomous driving testing methods, which predominantly focus on single-vehicle scenarios and struggle to uncover safety-critical behaviors emerging from multi-vehicle interactions. To this end, the paper introduces EVITA, a novel approach that, for the first time, formulates multi-vehicle test scenario generation as a multi-objective optimization problem, simultaneously minimizing scenario complexity and maximizing interaction diversity. EVITA integrates multi-objective optimization algorithms, high-fidelity simulation, and structured scenario modeling to systematically construct and evaluate multi-vehicle interaction test cases. Experimental results demonstrate that EVITA consistently triggers richer and more challenging interaction patterns, significantly enhancing the ability to expose latent safety hazards in current autonomous driving systems.

Abstract

Autonomous vehicles (AVs) must be thoroughly tested to meet high safety standards and avoid endangering both AV passengers and road users. Scenario-based testing implements driving scenarios in virtual simulation environments as a cost-effective alternative to field testing. Common scenario-based testing approaches set the environment and the surrounding traffic and test a single AV. Recent studies show that the approaches that test single AVs miss critical behaviors that emerge from interactions among multiple AVs. Effective approaches to test scenarios that emerge from n-way interactions must address the combinatorial explosion that the presence of multiple AVs further exacerbates. In this paper, we propose EVITA, an approach that leverages multi-objective optimization to generate scenarios that trigger multiple and diverse AVs interactions, while minimizing the complexity of the generated scenarios, to effectively test multiple interacting AVs and reveal safety-critical scenarios that current approaches overlook. The experimental results that we discuss in this paper confirm that EVITA triggers a higher variety of AVs interactions than state-of-the-art approaches, thus improving the likelihood to reveal safety-critical behaviors.

Problem

• autonomous vehicles
• scenario-based testing
• multi-agent interaction
• combinatorial explosion
• safety-critical behaviors

Innovation

• multi-objective optimization
• autonomous vehicles
• scenario-based testing
• n-way interactions
• combinatorial explosion