计算机科学
运动规划
路径(计算)
算法设计
人工智能
算法
机器人
计算机网络
作者
Junhao Tian,Gui Gui,Quanjun Chen,Le Chang,Jianqiang Xue,Yuqian Zhao
标识
DOI:10.1109/ccdc65474.2025.11091085
摘要
Demand-responsive customized bus (DRCB) provides a new direction for the transformation of the traditional bus industry. However, most existing DRCB path planning strategies adopt heuristic algorithms and often fall short in terms of solution accuracy and computational efficiency, making them inadequate for practical application. Therefore, this paper proposes a path planning strategy that combines Dijkstra's algorithm with Q-learning. First, Dijkstra's algorithm is used to calculate the shortest path between any two nodes in the transportation network. Then, based on the results, the Q-learning algorithm is employed to explore the shortest path passing through multiple target nodes. Finally, experimental validation is conducted. The results demonstrate that Dijkstra's algorithm can enhance the speed and accuracy of the Q-learning algorithm in solving DRCB path planning problem.
科研通智能强力驱动
Strongly Powered by AbleSci AI