Towards Fully Autonomous Drone-Based Last-Mile Delivery

TL;DR

This paper introduces the autonomous vehicle routing problem with drones (A-VRPD), aiming to fully automate last-mile delivery by integrating autonomous vehicles with drone delivery, formulated as an ILP and solved with a greedy algorithm.

Contribution

It defines a new optimization problem (A-VRPD), formulates it as an ILP, and proposes a greedy algorithm to improve last-mile delivery efficiency using autonomous vehicles and drones.

Findings

The proposed algorithm increases profits for delivery companies and AV owners.

Simulations show effective cost reduction and operational efficiency improvements.

The approach adapts to real-world traffic and load conditions.

Abstract

The drone-based last-mile delivery is an emerging technology to deliver parcels using drones loaded on a truck. As more and more autonomous vehicles (AVs) will be available for delivery services, an opportunity is arising to fully automate drone-based last-mile delivery. In this paper, we integrate AVs with drone-based last-mile delivery aiming to fully automate the last-mile delivery process. We define a new problem called the autonomous vehicle routing problem with drones (A-VRPD). A-VRPD is to select AVs from a pool of available AVs and to schedule them to serve customers with an objective of minimizing the total operational cost. We formulate A-VRPD as an Integer Linear Programming (ILP) and propose a greedy algorithm to solve the problem based on real-world operational costs for different types of AVs, traveling distances calculated considering the current traffic conditions, and varying load capacities of AVs. Extensive simulations performed under various random delivery scenarios demonstrate that the proposed algorithm effectively increases profits for both the delivery company and AV owners compared with traditional VRP-D (and TSP-D) algorithm-based approaches.