Enhancing unmanned aerial vehicles logistics for dynamic delivery: a hybrid non-dominated sorting genetic algorithm II with Bayesian belief networks

Abstract

To address the complexities of managing networks of unmanned aerial vehicles (UAVs) and Just-in-Time problem solving, this study introduces a cutting-edge multi-objective location-routing optimization model. This model integrates time window constraints, concurrent pick-up and delivery demands, and rechargeable battery functionality, significantly enhancing the efficiency of UAV operations. It reduces battery consumption and transportation costs while optimizing delivery times and reducing operational risks. The model improves the refinement of delivery schedules by accounting for uncertain traffic scenarios, thereby increasing its accuracy and reliability in dynamic environments. Additionally, a Bayesian belief networks approach for risk assessment introduces a new layer to operational risk management. The model’s performance and its trade-offs are demonstrated through advanced data visualizations such as 3D Pareto fronts, pair plots, and network graphs, with validation via the NSGA-II approach confirming its reliability and practical applicability. This research represents a major leap forward in drone routing strategies, focusing on efficiency, adaptability, and risk management in UAV logistics and provides a comprehensive framework that bridges the gap between theoretical exploration and practical application.