Dynamic optimisation of safe ship trajectory with neural representation of encountered ships

This paper describes an application of the dynamic programming method to determine the safety of one’s own ship trajectory during encounter of other ships. A dynamic model of the process, with kinematic constraints of state and determined by a three-layer artificial neural network has been used for the development of control procedures. Non-linear activation functions in the first and second layers may be characterised by a tangent curve while the output layer is of a sigmoidal nature. The Neural Network Toolbox of the Matlab software has been used to model the network. The learning process used an algorithm of backward propagation of the error with an adaptively selected learning step. The considerations have been illustrated through an example implemented in a computer simulation using the algorithm for the determination of the safe ship trajectory in situations of encounter of multiple ships, recorded on the ship’s radar screen in real navigational situation in the Kattegat Strait.

---

Opracowanie ze środków MNiSW w ramach umowy 812/P-DUN/2016 na działalność upowszechniającą naukę (zadania 2017)