arXiv 2605.285522026-05-27cs.AI

使用Smooth-Mamba深度强化学习建模安全关键交互中车辆类型特定的行人碰撞规避行为

Modeling Vehicle-Type-Specific Pedestrian Crash Avoidance Behavior in Safety-Critical Interactions Using Smooth-Mamba Deep Reinforcement Learning

Transportation Informatics Lab, Department of Civil and Environmental Engineering, Old Dominion University（交通信息实验室，土木与环境工程系，旧 Dominion 大学）；Department of Electrical and Computer Engineering, Old Dominion University（电气与计算机工程系，旧 Dominion 大学）；Department of Transportation and Urban Infrastructure Studies, SMARTER Center, Morgan State University（交通与城市基础设施研究系，SMARTER 中心，莫根州立大学）

Qingwen Pu, Kun Xie, Hong Yang, Di Yang, Junqing Wang

备注：: 37 page. 15 Figure, 9 table

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本研究利用Smooth-Mamba深度确定性策略梯度框架（SMamba-DDPG）从Argoverse 2数据集中提取安全关键交互，建模行人与自动驾驶车辆（AV）和人类驾驶车辆（HDV）的碰撞规避行为，发现行人对AV反应更快、穿越速度更低，且AV场景冲突率更低。

摘要：

随着自动驾驶车辆（AV）越来越多地与人类驾驶车辆（HDV）共享道路，理解行人在安全关键交互中如何应对不同车辆类型对于自动驾驶技术的安全部署至关重要。本研究从Argoverse 2数据集中提取安全关键的行人-车辆交互，以捕捉涉及AV和HDV的真实碰撞规避行为。为了建模车辆类型特定的行人碰撞规避行为，我们开发了Smooth-Mamba深度确定性策略梯度框架（称为SMamba-DDPG），该框架将平滑动作约束与高效的时序表示学习相结合。为了量化行人行为差异，该框架分别为行人与AV和HDV的交互训练了碰撞规避策略。结果表明，SMamba-DDPG在复现行人碰撞规避行为方面优于基线强化学习和监督学习模型。重构轨迹表现出强烈的行为真实性，准确复现了AV和HDV场景中的碰撞规避运动学。反应时间分析表明，该模型捕捉到了类人的响应延迟，并揭示行人对AV的反应比HDV更快。反事实分析进一步表明，行人在与AV交互时采用更低的穿越速度。对模型生成数据的大规模安全分析显示，与行人-HDV交互相比，行人-AV交互始终产生更低的冲突率和更高的行人让行率。这些发现强调了在混合交通环境中，将车辆类型特定的行人行为模型纳入更安全的自动驾驶系统设计和更真实的交通模拟中的重要性。

英文摘要：

As automated vehicles (AVs) increasingly share roadways with human-driven vehicles (HDVs), understanding how pedestrians respond to different vehicle types in safety-critical interactions is essential for the safe deployment of automated driving technologies. This study extracts safety-critical pedestrian-vehicle interactions from the Argoverse 2 dataset to capture real-world crash avoidance behaviors in encounters involving AVs and HDVs. To model vehicle-type-specific pedestrian crash avoidance behavior, we develop a Smooth-Mamba Deep Deterministic Policy Gradient framework, termed SMamba-DDPG, which integrates smooth action constraints with efficient temporal representation learning. To quantify pedestrian behavioral differences, the framework trains separate crash avoidance policies for pedestrian interactions with AVs and HDVs. Results show that SMamba-DDPG outperforms baseline reinforcement learning and supervised learning models in reproducing pedestrian crash avoidance behaviors. Reconstructed trajectories demonstrate strong behavioral realism, accurately reproducing crash avoidance kinematics in both AV and HDV scenarios. Reaction time analysis shows that the model captures human-like response delays and reveals that pedestrians respond more quickly to AVs than to HDVs. Counterfactual analysis further indicates that pedestrians adopt lower crossing speeds when interacting with AVs. Large-scale safety analysis of model-generated data revealed that pedestrian-AV interactions consistently yielded lower conflict rates and higher pedestrian yielding rates compared to pedestrian-HDV interactions. The findings highlight the importance of incorporating vehicle-type-specific pedestrian behavioral models for safer automated driving system design and more realistic traffic simulations in mixed-traffic environments.

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。