Collaborative Truck-UAV Delivery Routing Optimization Under Dynamic Weather Conditions and Customer Demands

Unmanned Aerial Vehicles (UAVs) have emerged as core tools for logistics in smart cities, demonstrating significant potential due to their efficiency and flexibility. However, their capabilities in long-distance deliveries are constrained by payload and battery limitations. Additionally, most existing studies focus on route planning in static environments and largely overlook practical factors such as fluctuating winds and customer demands, all of which significantly impact UAV logistics efficiency. Thus, this paper explores a collaborative truck-UAV delivery model and develops an Adaptive Collaborative Logistics Algorithm (ACLA) for real-time path planning. To be specific, the model employs Normal-Weibull mixture and von Mises distribution to capture the stochastic nature of wind speed and direction, enabling real-time adjustments to UAV flight speeds for optimized route planning. Customer demands fluctuations are modeled by using Poisson distribution and associating a density clustering approach to dynamically redefine UAV service areas. To further enhance routing and scheduling efficiency, the proposed algorithm integrates a genetic algorithm with tabu search to ensure efficient task allocation and route planning under varying environmental conditions. The simulation results demonstrate that the proposed method performs exceptionally well in complex dynamic environments, significantly reducing total UAV energy consumption and delivery time while improving overall logistics efficiency.