用真实数据生成逼真碰撞场景，评估自动驾驶避障能力。
Realistic Extreme Behavior Generation for Improved AV Testing
- 基于真实轨迹数据生成对抗性扰动，模拟多样化碰撞
- 通过聚类识别出可解释的典型碰撞场景，覆盖不同角度与速度
- 适用于评估自动驾驶系统的安全边界，适合测试团队使用
本文提出一个框架，通过从真实无碰撞数据中提取的自动驾驶行为模型，生成合成但逼真的潜在碰撞场景，以诊断自动驾驶车辆（AV）避撞技术的优劣。该框架通过对学习到的车辆行为模型预测轨迹施加扰动，生成具有多样碰撞属性（如碰撞角度、速度）的反事实碰撞事件。核心贡献在于将这些对抗性扰动建立在行为模型参数空间中的数据对齐基础上，确保其行为合理性。随后，对生成的合成场景进行聚类，提取出合理且具代表性的碰撞模式，构成下游自动驾驶系统评估的测试集。我们采用两个最先进的行为预测模型作为扰动生成源，验证了该框架能有效揭示基准避撞策略的可解释性失效模式。
原文摘要 · Abstract (English)
This work introduces a framework to diagnose the strengths and shortcomings of Autonomous Vehicle (AV) collision avoidance technology with synthetic yet realistic potential collision scenarios adapted from real-world, collision-free data. Our framework generates counterfactual collisions with diverse crash properties, e.g., crash angle and velocity, between an adversary and a target vehicle by adding perturbations to the adversary's predicted trajectory from a learned AV behavior model. Our main contribution is to ground these adversarial perturbations in realistic behavior as defined through the lens of data-alignment in the behavior model's parameter space. Then, we cluster these synthetic counterfactuals to identify plausible and representative collision scenarios to form the basis of a test suite for downstream AV system evaluation. We demonstrate our framework using two state-of-the-art behavior prediction models as sources of realistic adversarial perturbations, and show that our scenario clustering evokes interpretable failure modes from a baseline AV policy under evaluation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。