基于交叉口不等待概率的路径规划研究
Research on Path Planning Based on Non-Waiting Probability of Intersection

随着城市化进程的加速，城市交通拥堵问题日益严重，已成为制约城市应急响应效率的核心因素。应急物流车辆在复杂的城市路网中快速通行是确保应急救援成功的关键。然而，传统路径规划方法多基于静态路网的最短距离原则，忽略了交通流量波动、信号控制策略以及车辆行为等动态因素，导致规划路径在实际场景中频繁陷入拥堵，无法满足应急响应的高效性需求。为解决这一问题，本文提出一种融合交通流动态特性、信号控制优化及车辆行为模型的综合路径规划方法。该方法通过图论理论构建加权路网模型，将城市道路网络抽象为一个由节点(交叉口)和边(道路)组成的加权有向图，并引入交叉口不等待通行概率作为路径代价函数的重要组成部分。在此基础上，本文对经典的Dijkstra算法进行改进，以实现多目标路径优化，同时兼顾路径的最短时间和交通信号优化原则。实验部分，本文采用3 × 3网格型路网进行模拟验证，设置了一系列与交通流量、信号控制及车道通行能力相关的参数。结果表明，该方法能够有效规避高流量路段，使总行程时间降低18.7%，交叉口平均等待时间减少23.5%。此外，通过引入交通信号相位、车道通行能力及转向行为等因素，路径规划结果更加贴合实际交通环境，显著提高了应急车辆的通行效率和应急响应速度。综上所述，本文提出的基于交叉口不等待概率的路径规划方法为智能交通系统与应急物流管理提供了理论支持与实践参考。
With the acceleration of urbanization, the problem of urban traffic congestion has become increasingly serious and has become a core factor restricting the efficiency of urban emergency response. The rapid passage of emergency logistics vehicles in the complex urban road network is the key to ensuring the success of emergency rescue. However, traditional path planning methods are mostly based on the principle of the shortest distance in static road networks, ignoring dynamic factors such as traffic flow fluctuations, signal control strategies, and vehicle behavior, resulting in planned paths frequently getting stuck in congestion in actual scenarios and failing to meet the efficiency requirements of emergency response. To address this issue, this paper proposes a comprehensive path planning method that integrates the dynamic characteristics of traffic flow, signal control optimization, and vehicle behavior models. This method constructs a weighted road network model through graph theory, abstracting the urban road network into a weighted directed graph composed of nodes (intersections) and edges (roads), and introduces the probability of no waiting at intersections as an important component of the path cost function. On this basis, this paper improves the classic Dijkstra algorithm to achieve multi-objective path optimization, taking into account both the shortest travel time and the principle of traffic signal optimization. In the experimental part, this paper uses a 3 × 3 grid-type road network for simulation verification and sets a series of parameters related to traffic flow, signal control, and lane capacity. The results show that this method can effectively avoid high-traffic sections, reducing the total travel time by 18.7% and the average waiting time at intersections by 23.5%. In addition, by introducing factors such