arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2409.17429cs.RO
收藏

真实世界数据启发的交互式网联交通场景生成

Real-World Data Inspired Interactive Connected Traffic Scenario Generation

University of Wisconsin-Madison(威斯康星大学麦迪逊分校)

Junwei You, Pei Li, Yang Cheng, Keshu Wu, Rui Gan, Steven T. Parker, Bin Ran

AI总结:

针对真实世界V2X数据未有效集成到仿真中的问题,本研究利用RSUs的真实SPaT数据并开发AV动态响应算法,构建高保真交互式网联交通场景生成环境,输出多模态数据以弥合理论研究和实际部署的差距。

摘要:

仿真是确保网联自动驾驶车辆(CAVs)测试与验证准确、高效和逼真的关键步骤。随着CAVs的加速普及,将真实世界数据集成到仿真环境中变得日益关键。在CAVs使用的各种技术中,车联网(V2X)通信在确保CAVs、基础设施和其他道路使用者之间无缝信息传输方面发挥着至关重要的作用。然而,现有研究大多集中在开发和测试V2X的通信协议、资源分配策略和数据分发技术上。在将真实世界V2X数据集成到仿真中以生成多样且高保真交通场景方面仍存在空白。为填补这一研究空白,我们利用来自路侧单元(RSUs)的真实世界信号相位与配时(SPaT)数据来提升CAV仿真的保真度。此外,我们开发了一种算法,使自动驾驶车辆(AVs)能够对实时交通信号数据做出动态响应,从而模拟真实的V2X通信场景。这种高保真仿真环境能够为各种交通场景生成多模态数据,包括轨迹、语义相机、深度相机和鸟瞰图数据。生成的场景和数据为AVs与交通基础设施及其他道路使用者的交互提供了宝贵见解。这项工作旨在弥合CAVs理论研究和实际部署之间的差距,促进更智能、更安全交通系统的发展。

英文摘要:

Simulation is a crucial step in ensuring accurate, efficient, and realistic Connected and Autonomous Vehicles (CAVs) testing and validation. As the adoption of CAV accelerates, the integration of real-world data into simulation environments becomes increasingly critical. Among various technologies utilized by CAVs, Vehicle-to-Everything (V2X) communication plays a crucial role in ensuring a seamless transmission of information between CAVs, infrastructure, and other road users. However, most existing studies have focused on developing and testing communication protocols, resource allocation strategies, and data dissemination techniques in V2X. There is a gap where real-world V2X data is integrated into simulations to generate diverse and high-fidelity traffic scenarios. To fulfill this research gap, we leverage real-world Signal Phase and Timing (SPaT) data from Roadside Units (RSUs) to enhance the fidelity of CAV simulations. Moreover, we developed an algorithm that enables Autonomous Vehicles (AVs) to respond dynamically to real-time traffic signal data, simulating realistic V2X communication scenarios. Such high-fidelity simulation environments can generate multimodal data, including trajectory, semantic camera, depth camera, and bird's eye view data for various traffic scenarios. The generated scenarios and data provide invaluable insights into AVs' interactions with traffic infrastructure and other road users. This work aims to bridge the gap between theoretical research and practical deployment of CAVs, facilitating the development of smarter and safer transportation systems.

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。

↑