An intelligent method of ship's trajectory planning at sea

Abstract

In a navigation situation at sea, the decision support system should help the operator to choose a proper manoeuvre in given circumstances, teach him good habits, and enhance his general intuition on how to behave in similar situations in future. An accepted approach in those cases is a multiple criterion decision problem. In the paper a modified version of the Evolutionary Planner /Navigator algorithm, has been used as a major component of such a decision support system for computing the near optimum trajectory of a ship in given environment. By taking into account certain boundaries of the manoeuvring region, along with navigation obstacles and other moving ships, the problem of avoiding collisions at sea was reduced to a dynamic optimisation task with static and dynamic constrains. The introduction of a time parameter and moving constrains representing the passing ships is the main distinction of the new system. Sample results, having the form of ship trajectories obtained using the program for typical navigation situations are given.

A review of ship collision risk assessment, hotspot detection and path planning for maritime traffic control in restricted waters

“…Path planning in different circumstances can be reduced to the optimisation task with static and dynamic constraints through considering the available manoeuvring region with the determined boundary derived from obstacles and the surrounding moving ships. The area-based static obstructions such as shallow regions and shorelines can be represented as polygons or convex hulls (Smierzchalski, 1999a) and then the ship collision risk is checked through the intersections with the polygon. The moving ships can be represented as the ship domain shape or the occupied grids or circles (Lyu and Yin, 2019).…”

“…𝜑 𝑖 the course of gene i Smierzchalski (1999aSmierzchalski ( , 1999b proposed the evolutionary algorithm to solve the trajectory planning model that assumed the speed of ships is constant The navigation path optimisation based on the evolution algorithm (Tam and Bucknall, 2010b) Φ 𝑝,𝑖 = ∪ 𝜏 𝑝,𝑖 𝑠=1 𝜙 𝑝,𝑖,𝑠 where 𝜙 𝑝,𝑖,𝑠 is the waypoint along Φ 𝑝,𝑖 ,𝑠 ∈ [1, 𝜏 𝑝,𝑖 ] is the index The ship path associated with the coordinates and heading based on the Q-learning algorithm (Chen et al, 2019a) [(𝑥 1 , 𝑦 1 , 𝜓 1 ), (𝑥 2 , 𝑦 2 , 𝜓 2 ), • • • , (𝑥 𝑛 , 𝑦 𝑛 , 𝜓 𝑛 )]; 𝐿 = (𝑥 − 𝑥 𝑔𝑜𝑎𝑙 ) 2 + (𝑦 − 𝑦 𝑔𝑜𝑎𝑙 ) 2 where x,𝑦 and 𝜓are respectively the x-coordinate, y-coordinate and heading. Here, L represents how the path close to the goal, and the reward for each step equal to 𝑟 = 1 − −0 • 003 × 𝐿 The optimality criterion for the shortest path (Lazarowska, 2015b) min…”

Safe Ship Control Method with the Use of Ant Colony Optimization

“…Dynamic constraints representing encountered ships are modeled in the form of hexagons. The ship domain in the form of hexagon was developed by Śmierzchalski [22]. Domain used in the algorithm is based on this approach, but the dimensions of the domain are different.…”