Optimal Strategies of Autonomous Reconnaissance Missions
L.K.M. Verlinde (TU Delft - Electrical Engineering, Mathematics and Computer Science)
R.P.M.J. Jurrius – Mentor (Netherlands Defense Academy (NLDA))
D. de Laat – Coach (TU Delft - Discrete Mathematics and Optimization)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
The role of Unmanned Aerial Vehicles (UAVs), more commonly known as drones, in society continues to become more significant every day, both in everyday life and in military operations. The extent to which unmanned vehicles are used for both offensive as well as reconnaissance missions is at an all-time high. To expand the number of operational systems while managing costs, it is desirable to deploy systems that can operate fully independently. For a survey mission, this requires a planning of the complete mission before the drone leaves for enemy territory. The setting of such a mission can be stated as follows: starting from a secure base, multiple surveillance locations need to be safely reached and the acquired information has to be transmitted back to the base. There are many possible strategies for gathering this information. This report investigates how to find the strategy that maximises the expected amount of retrieved information. Specifically, such an optimal strategy tells us which route the UAV should take in enemy territory and at what moments in the mission transmissions should be made. We present a mathematical framework for formulating the problem, as well as a genetic algorithm capable of finding the optimal strategy in different scenarios.