부산대학교 도서관

This paper considers a last-mile distribution system consisting of a fleet of electric vehicles, where each vehicle has the option to be equipped with a single drone. We formulate the system as a mixed-fleet electric vehicle-drone routing problem, with the objective of minimizing the total cost of the system. Subsequently, an adaptive memetic algorithm with a Q-learning-based operator selection mechanism is employed to solve the model. A set of extensive numerical experiments show that the proposed algorithm performs better than the state-of-the-art approaches. Further, we also demonstrate the importance of economies of scale in drone-aided routing problems.