提出三种驾驶努力度量，精准评估自动驾驶感知错误的危险程度。
Effort-Based Criticality Metrics for Evaluating 3D Perception Errors in Autonomous Driving
- 用速度损失和制动需求量化误检与漏检的后果
- 93%的感知错误低于设定临界阈值，证明指标有效性
- 适合用于筛选和分析感知系统缺陷，不替代闭环安全测试
现有碰撞紧迫度量（如时间到碰撞）无法区分误报和漏报的运行后果。本文提出两种针对错误类型的代价度量：误检导致的累计速度损失（FSR）和漏检引发的最大减速度需求（MDR），基于纵向运动模型；同时引入横向避让加速度（LEA），结合可达性分析确定碰撞规避所需最小转向努力。采用动态保守、语义无过滤的可达性门控机制，在帧级评分与轨迹级聚合前筛选候选交互。在nuScenes和Argoverse 2数据集上的评估显示，65%至93%的感知错误低于预设临界阈值。相关性与阈值分析表明，该度量体系能提供互补的故障筛选排序，不可替代闭环安全验证。
原文摘要 · Abstract (English)
Criticality metrics such as time-to-collision (TTC) quantify collision urgency but do not distinguish the operational consequences of false-positive (FP) and false-negative (FN) perception errors. We formulate two error-specific effort metrics: False Speed Reduction (FSR), the cumulative velocity loss associated with persistent phantom detections, and Maximum Deceleration Rate (MDR), the peak braking demand associated with missed objects under a longitudinal kinematic model. These longitudinal metrics are complemented by Lateral Evasion Acceleration (LEA), adapted from prior lateral-evasion kinematics and coupled with reachability-based collision timing. The collision check quantifies the minimum steering effort required to avoid a predicted collision. A dynamically conservative, semantically unfiltered reachability gate selects candidate interactions before frame-level scoring and track-level aggregation. Evaluation on nuScenes and Argoverse 2 shows that 65% to 93% of errors fall below the chosen criticality thresholds. Correlation and threshold analysis indicate that the proposed metrics provide complementary rankings for screening and mining perception failures and are not substitutes for closed-loop safety validation.
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。