A faster heuristic for the Traveling Salesman Problem with Drone

TL;DR

This paper introduces a new heuristic for the Flying Sidekick Traveling Salesman Problem that significantly speeds up computation by leveraging the Lazy Drone Property, making it more scalable for larger delivery instances.

Contribution

The paper presents the Lazy Drone Property and an associated algorithm, reducing runtime and complexity for solving the FSTSP with a drone and truck.

Findings

Algorithm is over 84 times faster than previous methods.

Performance scales linearly with the number of customers.

Effectively decreases runtime for large instances.

Abstract

Given a set of customers, the Flying Sidekick Traveling Salesman Problem (FSTSP) consists of using one truck and one drone to perform deliveries to them. The drone is limited to delivering to one customer at a time, after which it returns to the truck, from where it can be launched again. The goal is to minimize the time required to service all customers and return both vehicles to the depot. In the literature, we can find heuristics for this problem that follow the order-first split-second approach: find a Hamiltonian cycle h with all customers, and then remove some customers to be handled by the drone while deciding from where the drone will be launched and where it will be retrieved. Indeed, they optimally solve the h-FSTSP, which is a variation that consists of solving the FSTSP while respecting a given initial cycle h. We present the Lazy Drone Property, which guarantees that only some combinations of nodes for launch and retrieval of the drone need to be considered by algorithms for the h-FSTSP. We also present an algorithm that uses the property, and we show experimental results which corroborate its effectiveness in decreasing the running time of such algorithms. Our algorithm was shown to be more than 84 times faster than the previously best-known ones over the literature benchmark. Moreover, on average, it considered a number of launch and retrieval pairs that is linear on the number of customers, indicating that the algorithm's performance should be sustainable for larger instances.