SIREN-Bench：行为驱动的应急车辆交互生成与评估
SIREN-Bench: Behavior-Driven Generation and Evaluation of Emergency-Vehicle Interactions
- Rochester Institute of Technology（罗切斯特理工学院）
- CVS Health（CVS健康公司）
- City University of Hong Kong（香港城市大学）
- New York University（纽约大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
该研究提出行为驱动的SIREN协同仿真平台，构建SIREN-Bench-v1基准，经3类任务评估揭示不同行为模式下的失效特性，为自动驾驶与交通安全研究提供可扩展平台。
AI中文摘要：
应急车辆（EMV）可通过周围民用车辆制动、变道或形成救援通道来重组周边交通。评估这些对安全至关重要的交互，需要对EMV特权和民用车辆响应进行行为级控制，同时配备一致的感知与真值数据。现有数据集和仿真基准无法直接提供这种组合。我们提出SIREN，一个行为驱动的SUMO-CARLA协同仿真平台，用于生成EMV与民用车辆的交互。SIREN将SUMO的网络级交通演化与行为逻辑，同CARLA的连续车辆控制及同步车载感知相结合；根据活动行为的不同，交互由SUMO、CARLA或二者共同控制。我们将该平台实例化为SIREN-Bench-v1，包含应急等级L1-L3下的7种参数化交互模板，以及3种行为族，配备同步传感器观测和模拟器原生标注。我们通过3项代表性任务展示该基准：3D目标检测、轨迹预测和视觉-语言风险理解。对9种轨迹预测器、4种基于LiDAR的检测器和5种视觉-语言模型的评估显示，存在行为依赖的失效模式：清交通交互对检测任务最难，特权路口通行对预测任务最难，平均而言没有任何学习型预测器优于恒速基准。视觉-语言模型在正常交通场景的表现远好于近事故和碰撞事件。这些结果证明了以行为为中心的基准测试的价值，并确立SIREN作为可扩展的数据生成与评估平台，适用于自动驾驶和交通安全性研究。
英文摘要：
Emergency vehicles (EMVs) can reorganize surrounding traffic as civilian vehicles brake, change lanes, or form rescue corridors in response to their passage. Evaluating these safety-critical interactions requires behavior-level control over both EMV privileges and civilian responses, together with consistent sensing and ground truth. Existing datasets and simulation benchmarks do not directly provide this combination. We present \textbf{SIREN}, a behavior-driven SUMO--CARLA co-simulation platform for generating EMV--civilian interactions. SIREN couples SUMO's network-level traffic evolution and behavior logic with CARLA's continuous vehicle control and synchronized onboard sensing; depending on the active behavior, the interaction is controlled by SUMO, CARLA, or jointly. We instantiate the platform as \textbf{SIREN-Bench-v1}, comprising seven parameterized interaction templates across emergency levels L1--L3 and three behavior families, with synchronized sensor observations and simulator-native annotations. We demonstrate the benchmark through three representative tasks: 3D object detection, trajectory prediction, and vision-language risk understanding. Evaluations of nine trajectory predictors, four LiDAR-based detectors, and five vision-language models reveal behavior-dependent failure modes. Traffic-clearance interactions are hardest for detection, privileged intersection traversal is hardest for prediction, and no learned predictor outperforms the constant-velocity reference on average. Vision-language models perform substantially better on normal traffic than on near-miss and collision events. These results demonstrate the value of behavior-centered benchmarking and establish SIREN as an extensible data-generation and evaluation platform for autonomous-driving and transportation safety research.
