汽车工程

汽车工程 ›› 2019, Vol. 41 ›› Issue (9): 1036-1042.doi: 10.19562/j.chinasae.qcgc.2019.09.008

• • 上一篇    下一篇

基于行为识别和曲率约束的车辆轨迹预测方法研究*

谢枫1, 娄静涛2, 赵凯2, 齐尧1   

  1. 1.陆军军事交通学院,天津 300161;
    2.军事交通运输研究所,天津 300161
  • 收稿日期:2018-11-26 修回日期:2019-03-13 出版日期:2019-09-25 发布日期:2019-10-12
  • 通讯作者: 娄静涛,讲师,博士,E-mail:loujt_1984@126.com
  • 基金资助:
    国家重点研发计划项目智能电动汽车路径规划及自主决策方法(2016YFB0100903)资助

A Research on Vehicle Trajectory Prediction Method Based onBehavior Recognition and Curvature Constraints

Xie Feng1, Lou Jingtao2, Zhao Kai2 & Qi Yao1   

  1. 1.Army Military Transportation University, Tianjin 300161;
    2.Institute of Military Transportation, Tianjin 300161
  • Received:2018-11-26 Revised:2019-03-13 Online:2019-09-25 Published:2019-10-12

PDF (PC)

689

赞

摘要： 为对智能车周围环境中车辆的行驶轨迹做出合理、有效的预测,提出了一种基于行为识别和曲率约束的车辆轨迹预测方法。首先,接收感知得到的障碍物信息,结合高精度地图提供的车道线信息,对车辆进行行为识别;然后建立s-l坐标系,将车辆运动分解为沿车道线方向(纵向)的运动和垂直于车道线方向(横向)的运动,依据行为识别结果得到车辆在横、纵向运动的多项式方程;再以高精度地图中的车道线曲率作为约束,筛选出一条最优的预测轨迹。实车实验结果表明,在车道保持、换道和转弯3种基本行为下,车辆在4 s内的轨迹平均预测误差分别为:0.52,0.51和1.03 m,较CTRA模型预测误差分别减小了1.81,4.48和5.49 m,单个车辆轨迹预测平均耗时为0.103 ms,验证了本文中所提方法的有效性、准确性和实时性。

关键词: 车辆轨迹预测, 行为识别, 曲率约束, 高精度地图

Abstract: In order to make a reasonable and effective prediction of vehicle's trajectory in the environment around the intelligent vehicle, a vehicle trajectory prediction method based on behavior recognition and curvature constraints is proposed. Firstly, it receives the perceived obstacle information and performs behavior recognition on vehicle combined with the lane line information provided by the high-precision map. Then the s-l coordinate system is established to decompose the vehicle motion into the motion along the lane line direction (longitudinal direction) and the motion perpendicular to the lane line direction (lateral direction). According to the behavior recognition result, the polynomial equation of the vehicle in the horizontal and vertical motion is obtained. Then the curvature of the lane line in the high-precision map is used as a constraint to select an optimal prediction trajectory. The actual vehicle experiment results show that under the three basic behaviors of lane keeping, lane changing and turning, the average vehicle trajectory prediction error within 4 s is 0.52, 0.51 and 1.03 m respectively, which is reduced by 1.81, 4.48 and 5.49 m compared with the prediction error of the CTRA model, and the average time of single vehicle trajectory prediction is 0.103 ms, which verifies the validity, accuracy and real-time of the proposed method.

Key words: vehicle trajectory prediction, behavior recognition, curvature constraints, high-precision map