Online Launch-Time Selection Using Deep Learning in a Target–Missile–Defender Engagement
Online Launch-Time Selection Using Deep Learning in a Target–Missile–Defender Engagement
- Neue Suche nach: Shalumov, Vitaly
- Neue Suche nach: Shalumov, Vitaly
In a target–missile–defender scenario, the optimal selection of the defender launch time online, which can be formulated as a switched system optimization problem, is crucial for improving the performance of the target–defender team. The objective of this paper was to examine the potential of using neural networks in switched system optimization. To that end, estimating the optimal launch time of the defender using deep neural networks is proposed. To estimate the optimal launch time online, two computationally efficient strategies are proposed: “Wait-and-Decide” and “Assess-and-Decide.” Simulation results demonstrated the viability of the proposed approach for online optimal launch-time estimation, even if only a small number of measurements are given.
Dokumentinformationen
Online Launch-Time Selection Using Deep Learning in a Target–Missile–Defender Engagement
Journal of Aerospace Information Systems ; 16 , 6 ; 224-236
2019-03-08
13 pages
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch