What is it about?
An optimally neural modified algorithm for determining a safe trajectory is presented. The possible shapes of the domains assigned to other ships as traffic restrictions for the particular ship were subjected to a detailed analysis. The codes for the computer program Neuro-Constraints for generating these domains are presented. The results of the simulation tests of the algorithm for a navigational situation are presented. The safe trajectories of the ship were compared at different distances, changing the sailing conditions and ship sizes.
Featured Image
Why is it important?
In terms of visibility at sea, ellipse‐shaped domains are the least sensitive in terms of extending the safe trajectory when visibility conditions at sea deteriorate; In terms of the ability to maneuver a ship, when maneuvering only the ship’s course, the most 191 effective domains are in the shape of a parabola, and when maneuvering the course and speed, they are domains in the shape of an ellipse; In terms of taking into account the size of a ship, the greatest optimality is provided by a parabolashaped domain; In terms of the discretization of calculations, hexagonal domains show the greatest sensitivity.
Perspectives
Testing the sensitivity of determining a safe path to inaccuracy and uncertainty of information regarding the state of the process from various measurement sources; Modification of the algorithm taking into account unforeseen maneuvering of other vessels, contrary to COLREGs, during the execution of a safe trajectory; Developing a version of the algorithm that takes into account the specificity of ship navigation in confined waters and in open waters.
Professor Józef Andrzej Lisowski
Read the Original
This page is a summary of: Effect of Ship Neural Domain Shape on Safe and Optimal Trajectory, TransNav the International Journal on Marine Navigation and Safety of Sea Transportation, January 2023, Faculty of Navigation,
DOI: 10.12716/1001.17.01.20.
You can read the full text:
Contributors
The following have contributed to this page







