基于努力的临界度量指标用于评估自动驾驶中的3D感知误差
Effort-Based Criticality Metrics for Evaluating 3D Perception Errors in Autonomous Driving
AI总结：
本文提出基于努力的临界度量指标，通过FSR、MDR和LEA量化自动驾驶中3D感知误差的严重性，揭示非关键性误差占比高，验证新指标能捕捉安全关键信息。
摘要：
临界度量指标如时间到碰撞（TTC）量化碰撞紧迫性，但将假阳性（FP）和假阴性（FN）感知误差的后果混为一谈。本文提出两种新的基于努力的指标：False Speed Reduction（FSR）和Maximum Deceleration Rate（MDR），以及Lateral Evasion Acceleration（LEA）。FSR是持续的幻影检测导致的累积速度损失，MDR是在恒定加速度模型下未检测到物体时的最大制动需求峰值。LEA基于先前的横向规避运动学，结合基于可达性的碰撞时间来量化避免预测碰撞所需的最小转向努力。基于可达性的椭球形碰撞过滤确保仅动态合理的威胁被评分，结合帧级匹配和轨迹级聚合。在nuScenes和Argoverse 2上评估不同感知管道时发现，65-93%的误差是非关键性的，Spearman相关性分析证实了这三个指标能够捕捉到现有基于时间、减速度或归一化临界度量无法获取的安全相关信息，从而能够有针对性地挖掘最严重的感知失败。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
