交通运输工程与信息学报

随着城市现代化发展,交通问题越来越突出,为解决这些问题,智能交通加速发展,合理优化资源分配成为一大焦点。因此,提出一种动态重规划的多目标路径产生方法,主要分为路径选择模型以及路径优化算法两个方面。提出基于时间最短、距离最短、拥挤度最低三个目标的多目标路径选择模型,确定路径求解算法,改进竞争学习神经网络确定拥挤度分类,通过逆向A*算法进行全局路径优化。当检测到路网信息发生变化时,将新信息反馈到系统中,通过增量更新算法进行动态更新,从而实现实时动态路径规划。最后,根据北京市某片区路网情况进行模拟,验证算法的可行性和有效性。

With the development of urban modernization, traffic problems have become progressively more prominent. To solve these problems, intelligent transportation can accelerate development, and rational optimization of resource allocation has become a major focus. Therefore, a dynamic multi-objective path generation method for dynamic replanning is proposed. It is mainly divided into two aspects: a path selection model and a path optimization algorithm. A multi-objective path selection model based on the shortest time, the shortest distance, and the lowest congestion is proposed. The path solving algorithm is determined, the competitive learning neural network is improved to determine the degree of congestion classification, the global path planning is performed by the reverse A* algorithm, and the initial optimal path is given. When a change in the information of the road network is detected, the new information is fed back into the system, and a dynamic update is performed by the incremental update algorithm to achieve real-time dynamic path planning. Finally, according to the situation of the road network in a district of Beijing, the feasibility and validity of the algorithm are verified.