Optimized Scheduling for Multi-drop Vehicle-Drone Collaboration with Delivery Constraints Using Large Language Models and Genetic Algorithms

With the rapid development of e-commerce and globalization, logistics distribution systems have become integral to modern economies, directly impacting transportation efficiency, resource utilization, and supply chain flexibility. However, solving the Vehicle-Multi-Drone Cooperative Delivery Problem (MDVCP-DR) is challenging due to complex constraints, including limited payloads, short endurance, regional restrictions, and multi-objective optimization. Traditional optimization methods, particularly genetic algorithms (GAs), struggle to address these complexities, often relying on static rules or single-objective optimization that fails to balance exploration and exploitation, resulting in local optima and slow convergence. To overcome these challenges, this paper proposes a novel logistics scheduling method called Loegised, which integrates Large Language Models (LLMs) with genetic algorithms. Loegised incorporates three innovative modules: a Cognitive Initialization Module to accelerate convergence by generating high-quality initial solutions, a Dynamic Operator Parameter Adjustment Module to optimize the crossover and mutation rates in real-time for better global search, and a Local Optimum Escape Mechanism to prevent stagnation and improve solution diversity. Experimental results, comparing Loegised with traditional methods and the Gurobi solver, demonstrate its superior performance in terms of solution quality, computational efficiency, and scalability, particularly in large-scale and complex scenarios. The findings validate that Loegised provides a robust, scalable solution to the MDVCP-DR, offering significant potential for real-world logistics optimization applications.