A cyber-physical social system for autonomous drone trajectory planning in last-mile superchilling delivery

Logistics drones are theoretically advantageous in automating last-mile delivery activities, but practically challenging in urban environments, including public concerns about risk of crashes and privacy. In view of the above concerns existing in the trajectory planning of logistics drones, this paper presents a parallel automatic delivery model following the cyber-physical social system (CPSS) for the last mile delivery of superchilling products, revealing the social value of logistics drone operations. Considering the operational constraints of logistics drone, a multi-objective optimisation model is established to balance the social value, energy efficiency and productivity of using logistics drones in the last-mile superchilling delivery. To effectively achieve the above optimisation, improved strategies, including the material exchange mechanism based on the random proportion rule and the Universe-Particle search strategy, are developed, resulting in an improved two-stage heuristic algorithm. Finally, simulation experiments are carried out in a simulated environment with 154 buildings, and compared with other frontier algorithms used for unmanned aerial vehicle (UAV) trajectory planning. The results show that the proposed framework can effectively reduce the threats to public life safety and improve the energy efficiency of logistics drones, while ensuring the productivity in the delivery process.