A Decision Support System for Dynamic Heterogeneous Unmanned Aerial System Fleets

Abstract

The Dynamic Unmanned Aerial System Routing Problem (DUASRP) is a variant of the classicVehicle Routing Problem (VRP) in which both planned and unplanned targets are observed by afleet of Unmanned Aerial Systems (UASs). In the dynamic environment of UAS, the rapidresponse for the new important targets is a very critical process, especially for the militaryoperations in battle space conditions. This study describes a heuristic method for the solution ofthe dynamic heterogeneous UAS routing problems without causing the initial tour to becompletely changed. For the dynamic routing of Unmanned Aerial Vehicles (UAV), it isnecessary to determine a combination of the least additional costs of vehicle routes through a setof geographically scattered targets, and quick responses for immediate targets during thereconnaissance missions. The most frequent cases assumed in the existing literature of classicalDUASs consider all UASs as identical (homogenous), all targets as having two geographicalcoordinates, and the thread of the targets are ignored. In this paper, a dynamic routing decisionsupport system based on both fuzzy clustering and leveraged cheapest insertion neighborhoodmethod is studied for pop-up threat in the case where the UAV fleet is heterogeneous, andtargets have both three-dimensional information and threads. Instead of selecting an a prioricode, the proposed control methodology dynamically starts with the route based on observedbehavior of the new target and the routes. It describes an efficient heuristic method capable ofproducing quick dynamic solutions on a series of empirical test problems.