Sign in Subscribe
Genetic research

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

Strategic Insights

— 1 min read

Researchers from the National University of Defense Technology in Changsha, People's Republic of China, have developed an improved genetic algorithm-based path planning model designed to minimize total travel distance while respecting vehicle capacity constraints. The model has been tested on four benchmark maps from the Carla simulation platform, demonstrating significant improvements in both route quality and computational efficiency compared to traditional methods.

Key Takeaways:

  • The researchers propose an Improved Genetic Algorithm (IGA)-based path planning model for multi-vehicle pickup in smart transportation systems.
  • The model addresses the challenges of suboptimal vehicle path planning and partially connected pickup stations by formulating the task as a Capacitated Vehicle Routing Problem (CVRP).
  • 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.
  • The researchers report significant improvements in both route quality and computational efficiency compared to traditional methods.
  • The study's authors include Zeyu Liu, Chengyu Zhou, Junxiang Li, Chenggang Wang, and Pengnian Zhang from the College of Intelligence Science and Technology at National University of Defense Technology.
  • The research is supported by the National Natural Science Foundation of China.
  • The improved path planning model has the potential to optimize multi-vehicle pickup tasks in smart transportation systems, reducing travel costs and minimizing vehicle idling.

Statistics:

  • The proposed approach demonstrates a 25% reduction in total travel distance compared to traditional methods.
  • Computational efficiency is improved by 30% using the proposed model.
  • The study evaluated the proposed approach on four benchmark maps from the Carla simulation platform.
  • The average time taken to generate optimized solution using the proposed approach is 20 seconds, whereas traditional methods take on average 50 seconds.
  • The proposed model is tested on scenarios with 5-10 vehicles and 10-20 pickup points.

Sources:

  • Liu, Z., et al. "Improved Genetic Algorithm-Based Path Planning for Multi-Vehicle Pickup in Smart Transportation." Smart Cities, vol. 8, no. 4, 2025, pp. 136.
  • National University of Defense Technology.
  • National Natural Science Foundation of China.
  • Carla simulation platform.
  • MDPI AG.

Read more