Recent advancements in Vehicle-to-Everything communication technology have enabled autonomous vehicles to share sensory information to obtain better perception performance. With the rapid growth of autonomous vehicles and intelligent infrastructure, the V2X perception systems will soon be deployed at scale, which raises a safety-critical question: \textit{how can we evaluate and improve its performance under challenging traffic scenarios before the real-world deployment?} Collecting diverse large-scale real-world test scenes seems to be the most straightforward solution, but it is expensive and time-consuming, and the collections can only cover limited scenarios. To this end, we propose the first open adversarial scene generator V2XP-ASG that can produce realistic, challenging scenes for modern LiDAR-based multi-agent perception systems. V2XP-ASG learns to construct an adversarial collaboration graph and simultaneously perturb multiple agents' poses in an adversarial and plausible manner. The experiments demonstrate that V2XP-ASG can effectively identify challenging scenes for a large range of V2X perception systems. Meanwhile, by training on the limited number of generated challenging scenes, the accuracy of V2X perception systems can be further improved by 12.3\% on challenging and 4\% on normal scenes. Our code will be released at https://github.com/XHwind/V2XP-ASG.

翻译：近期车联网通信技术的进步使得自动驾驶车辆能够共享感知信息以获得更优的感知性能。随着自动驾驶车辆与智能基础设施的快速发展，V2X感知系统即将大规模部署，这引发了一个关键安全问题：在现实部署前，我们如何评估并改进其在复杂交通场景下的表现？收集多样化的大规模真实测试场景看似最直接的解决方案，但这种方式成本高昂且耗时，且采集场景仅能覆盖有限情况。为此，我们提出首个开源对抗场景生成器V2XP-ASG，能够为现代基于激光雷达的多智能体感知系统生成逼真且具挑战性的场景。V2XP-ASG通过学习构建对抗协作图，以对抗且合理的方式同时扰动多个智能体的位姿。实验表明，V2XP-ASG能有效识别多种V2X感知系统面临的挑战场景。同时，通过在生成的有限数量挑战性场景上进行训练，V2X感知系统在挑战场景中的准确率可提升12.3%，在常规场景中提升4%。我们的代码将发布于https://github.com/XHwind/V2XP-ASG。