Improved Genetic Algorithm-Based Path Planning for Multi-Vehicle Pickup in Smart Transportation

Abstract

Highlights: What are the main findings? This study proposes an Improved Genetic Algorithm (IGA) specifically designed for multi-vehicle path planning in large-scale and dynamic ride-hailing applications, which includes vehicle capacity constraints, incomplete station connectivity, and edge-based passenger distribution. Comparative experiments on four benchmark simulation environments demonstrate that the proposed IGA significantly reduces both maximum and average sub-path lengths, while improving computational efficiency relative to the classical MSTC* approach. What is the implication of the main finding? The proposed IGA framework effectively addresses the operational challenges of multi-vehicle coordination in complex and intelligent transportation systems, offering a scalable and efficient solution for real-time vehicle path planning with shared-ride constraints. These findings provide methodological support for the development of intelligent dispatching strategies in intelligent transportation systems, with potential application in dynamic and resource-constrained urban mobility scenarios. With the rapid development of intelligent transportation systems and online ride-hailing platforms, the demand for promptly responding to passenger requests while minimizing vehicle idling and travel costs has grown substantially. This paper addresses the challenges of suboptimal vehicle path planning and partially connected pickup stations by formulating the task as a Capacitated Vehicle Routing Problem (CVRP). We propose an Improved Genetic Algorithm (IGA)-based path planning model designed to minimize total travel distance while respecting vehicle capacity constraints. To handle scenarios where certain pickup points are not directly connected, we integrate graph-theoretic techniques to ensure route continuity. The proposed model incorporates a multi-objective fitness function, a rank-based selection strategy with adjusted weights, and Dijkstra-based path estimation to enhance convergence speed and global optimization performance. Experimental evaluations on four benchmark maps from the Carla simulation platform demonstrate that the proposed approach can rapidly generate optimized multi-vehicle path planning solutions and effectively coordinate pickup tasks, achieving significant improvements in both route quality and computational efficiency compared to traditional methods.