Robust Composition of Drone Delivery Services under Uncertainty

TL;DR

This paper introduces a robust framework for composing drone delivery services that adapt to wind uncertainties and dynamic service arrivals, using a novel probabilistic search algorithm tested on real data.

Contribution

It presents a new probabilistic forward search algorithm for robust drone service composition considering environmental uncertainties and dynamic service availability.

Findings

The approach effectively handles wind variability in drone delivery planning.

Experimental results demonstrate improved robustness and efficiency.

The framework adapts to real-world drone operation scenarios.

Abstract

We propose a novel robust composition framework for drone delivery services considering changes in the wind patterns in urban areas. The proposed framework incorporates the dynamic arrival of drone services at the recharging stations. We propose a Probabilistic Forward Search (PFS) algorithm to select and compose the best drone delivery services under uncertainty. A set of experiments with a real drone dataset is conducted to illustrate the effectiveness and efficiency of the proposed approach.