车联网环境下交叉口车辆路径优化控制研究

摘要

On the connected-vehicle network and automated driving background,vehicle control problem on intersection is studied.On the basis of defining the different zone of the intersection,by using the spanning tree method to solve the accessible sequence and safe driving combination of the vehicles,Artificial Bee Colony algorithm is used to obtain the parameters of the variable speed zone in order to improve the efficiency of the algorithm,at the same time,the rolling horizon is used to prevent the result from falling into the local optimal solution.At last,the simula tion environment of intersection is built to validate the model,the results show that the cooperative control model of unsignalized intersection in Connected-vehicle Network Environment can effectively improve the traffic capacity of the intersection,significantly reduce the time required for vehicle to pass through the intersection compared with ex isting signal control technology.In comparison with the non-rolling optimization of the Connected-vehicle Network control,the rolling optimization of the Connected-vehicle Network control model's efficiency has been further enhanced.%在车联网及车辆自动驾驶背景下,研究了交叉口车辆路径控制问题.在定义交叉口分区控制的基础上,利用生成树方法遍历求解车辆可通行序列及安全通过组合,并引入人工蜂群算法求解变速区控制参数以提高运算效率,同时为防止结果陷入局部最优解利用滚动算法对模型进行优化.最后搭建交叉口仿真环境对相关模型进行验证,结果表明,车联网下车辆协同控制模型与现有的信号控制技术相比,能有效地提高交叉口的通行能力,显著降低车辆通过交叉口所需时间;同时,滚动优化下的车联网控制模型相较于无滚动优化的车联网控制效率进一步提升.