A difficult problem in search applications is computing the optimal aircraft trajectory in real-time onboard a high performance aircraft, where the objective is to increase the aircraft survivability and mission effectiveness by penetrating enemy threats and minimizing threat radar exposure. The mathematical model which is the basis for this architecture is based on an application of electrostatic field theory. It describes the problem of finding the best path through a region which contains a variable cost function as a problem in mathematical physics. An artificial neural network is defined which computes solutions to field theory. Experimental investigation of this technique has shown promising results. The solutions generated by the architectures have been checked against known admissible algorithm results and shown to be correct.
Neural network solutions to mathematical models of parallel search for optimal trajectory generation
Lösungen mathematischer Modelle der parallelen Suche für die Generierung optimaler Trajektorien mit neuronalen Netzen
1991
9 Seiten, 5 Bilder, 1 Tabelle, 7 Quellen
Conference paper
English
Trajectory Generation using Deep Neural Network
AIAA | 2018
|Prediction of the optimal hybrid train trajectory by using artificial neural network models
DOAJ | 2024
|Prediction of the optimal hybrid train trajectory by using artificial neural network models
Wiley | 2024
|SAGE Publications | 2015
|