Optimization of last mile delivery with unmanned aerial vehicle assistance

Abstract

In this thesis, we present an approach to optimizing the last-mile delivery route of a truck using coordination with unmanned aerial vehicles (UAVs). First, a traveling salesman problem is formulated to determine the truck’s route. Then, a scheduling problem is formulated to determine the routes for the UAVs. A genetic algorithm is used to solve these problems, and simulated results are presented. The algorithm’s complexity is analyzed. In preparation for future research, a small scale test bed plat-form is discussed and used to verify research on applying machine learning for traffic control. It demonstrates the first successful zero-shot transfer of an autonomous driving policy directly from simulator to a scaled autonomous vehicle under stochastic disturbances.