汽车工程

汽车工程 ›› 2025, Vol. 47 ›› Issue (6): 1177-1187.doi: 10.19562/j.chinasae.qcgc.2025.06.016

• • 上一篇    

基于V2X车场协同的地下停车场全域感知方法

胡钊政1,谭娟1,张佳楠1,杨昌军2,崔娜2,孟杰1,3()   

  1. 1.武汉理工大学智能交通系统研究中心，武汉 430063
    2.鑫源汽车有限公司，重庆 408000
    3.武汉理工大学重庆研究院，重庆 401120
  • 收稿日期:2024-12-13 修回日期:2025-02-13 出版日期:2025-06-25 发布日期:2025-06-20
  • 通讯作者: 孟杰 E-mail:mengjie09@whut.edu.cn
  • 基金资助:
    第二十七届中国科协年会学术论文。国家自然科学基金(52472453);湖北省重点研发计划项目(2022BAA082);重庆市自然科学基金（CSTB2022NSCQ-MSX1566）和重庆市涪陵区科研项目（FLKJ,2024AAG2003）资助

V2X Vehicle-Parking Cooperative Perception for the Whole-Area of Underground Parking Lots

Zhaozheng Hu1,Juan Tan1,Jianan Zhang1,Changjun Yang2,Na Cui2,Jie Meng1,3()   

  1. 1.Intelligent Transportation Systems Research Center，Wuhan University of Technology，Wuhan 430063
    2.Brilliance Shineray Chongqing Automobile Co. ，Ltd. ，Chongqing 408000
    3.Chongqing Research Institute，Wuhan University of Technology，Chongqing 401120
  • Received:2024-12-13 Revised:2025-02-13 Online:2025-06-25 Published:2025-06-20
  • Contact: Jie Meng E-mail:mengjie09@whut.edu.cn

RichHTML

4

PDF (PC)

68

赞

摘要：

精确的环境感知是实现自主代客泊车（automated valet parking，AVP）功能的基础，传统的AVP系统主要依赖于单车的感知，但随着场端智能技术的不断发展，车端与场端之间协同交互成为自主代客泊车落地的必然趋势。本文提出了一种基于V2X车场协同的地下停车场全域感知方法，该方法将地下停车场的全域感知问题转化为大规模图模型的构建与优化问题。通过输入场端激光雷达、摄像头的传感器信息以及智能网联车的感知数据，以车辆位姿为节点，建立多种边约束关系。为了提高感知精度，本文提出了一种融合车道级地图信息的大规模图模型方法，通过将停放车辆作为半静态信息约束，并结合车道级地图信息构建横向约束，在求解过程中引入滑动窗口以减小图模型的规模，最终以地图形式输出感知结果供车端使用。通过仿真实验和在占地面积为2 500 m2以上的地下停车场场景中进行实地实验，结果表明，该方法显著提升了在复杂停车场环境下的感知能力，实现了地下停车场的全域感知。

关键词: 地下停车场, V2X车场协同, 全域感知, 车道级地图, 图模型

Abstract:

Accurate environmental perception is fundamental to the realization of Automated Valet Parking （AVP） functions. Traditional AVP systems primarily rely on single-vehicle perception； however， with the continuous development of intelligent technologies at parking facilities， collaborative interaction between vehicles and facilities has become an inevitable trend for the implementation of AVP. A V2X （Vehicle-to-Everything） collaborative whole-areas perception method for underground parking lots is proposed， transforming the global perception challenge into a large-scale graph model problem. By integrating sensor data from facility-side lidar and cameras， along with perception data from connected vehicles， the method establishes various edge constraints based on vehicle poses. To enhance perception accuracy， a large-scale graph model method that incorporates lane-level map information is proposed in this paper， which takes parked vehicles as semi-static constraints while integrates lane-level map data for lateral constraints. A sliding window is introduced during the solving process to reduce the scale of the graph model， with final perception results output in map form for vehicle use. Through simulation experiments and field experiments in underground parking lot scenarios with an area of over 2 500 square meters， the results show that this method significantly improves the perception ability in complex parking lot environment and achieves whole-area perception of underground parking lots.

Key words: underground parking lot, V2X vehicle-parking collaboration, whole-area perception, lane-level map, graph model