Evaluation and Coordination of UAVs in Humanitarian Logistics

Unmanned Aerial Vehicles (UAVs), also known as drones, have the potential to improve humanitarian operations, yet they are currently not deployed to deliver relief goods. This thesis addresses the challenge of effectively operating cargo UAVs in humanitarian logistics from an operations research perspective. We investigate the role UAVs could have had in a range of historical disasters with a variety of humanitarian complexities, for instance, vehicle diversity, inaccessibility, scarcity of supplies, security threats (e.g., risks of vehicle attacks), and uncertainties in demand and travel times. We analyze aspects such as response times, human suffering, demand coverage, and equality alongside cost efficiency, aligning with the non-financial objectives of humanitarian organizations.

We propose a generic simulation-based modeling framework for UAV-aided humanitarian logistics and develop efficient algorithmic methods, including mathematical models and reinforcement learning approaches, to get the most value out of the mixed vehicle fleets and gain insights into the effective deployment of UAVs. With this knowledge, better decisions can be made regarding the number of UAVs to deploy, where to send them, and how to do this in a way that is both cost-efficient and effective in terms of aiding people in need.

Results demonstrate that humanitarian cargo UAVs generally can reduce costs, improve predictability and flexibility, alleviate human suffering, mitigate risks, and improve response times and location coverage. These results are not achieved by taking over the whole operation, but mainly by tackling the most challenging and hard-to-reach destinations. In this way, UAVs create a less complicated and more reliable operation for the conventional vehicles to serve the remaining majority of beneficiaries.