Genetic Algorithm-Based Task Allocation and Path Planning for Multiple Automated Guided Vehicles in Automated Warehouses

Automated warehouses increasingly rely on multiple Automated Guided Vehicles (AGVs) to improve logistics efficiency. However, coordinating multiple AGVs presents significant challenges in task allocation, path planning, and collision avoidance. This study proposes a Genetic Algorithm (GA)-based task allocation and path planning method for multi-AGV warehouse systems. The proposed approach simultaneously optimizes task assignment and routing while minimizing total travel distance under vehicle capacity constraints. An order batching strategy is introduced to combine nearby orders, reducing unnecessary travel, and improving AGV utilization. In addition, the A* algorithm is employed to generate high-quality initial paths for the genetic algorithm. A collision detection mechanism is incorporated into the fitness function to eliminate infeasible solutions and ensure safe vehicle coordination. The simulation results demonstrate that the proposed method successfully completed fifteen dynamically generated orders without collisions, achieving a total travel distance of 666 distance units. The proposed approach effectively improves transportation efficiency, resource utilization, and operational reliability, providing an efficient solution for task allocation and path planning in automated warehouse systems.