Efficient marine navigation through obstructions is still one of the many problems faced by the mariner. Many accidents can be traced to human error, recently increased traffic densities and the average cruise speed of ships impedes the collision avoidance decision making process further in the sense that decisions have to be made in reduced time. It seems logical that the decision making process be computerised and automated as a step forward to reduced the risk of collision. This article reviews the development of collision avoidance techniques and path planning for ships, particularly when engaged in close range encounters. In addition, previously published works have been categorised and their shortcomings highlighted in order to identify the 'state of the art' and issues in close range marine navigation.

https://www.cambridge.org/core/services/aop-cambridge-core/content/view/S0373463308005134

Review of collision avoidance and path planning methods for ships in close range encounters

There are limited studies on the use of ship domain as the safety criterion for ship navigation within confined waters. In this paper, a free-form ship domain has been developed empirically for navigation in confined waters. Two individual domains of an asymmetrical polygonal shape have been assumed around the own ship and target ship, and the size of the ship domains is assumed to be dynamically enlarged with increased ship speeds. The required safe distance modelled using the proposed ship domain takes into account dynamic changes in relative bearing and heading. The model is calibrated using the data of vessel movements in Singapore Strait and Singapore Port. An innovative process has been adopted that iteratively adjusts the parameters in the basic ship domain of a stationary ship; a speed function as well as a weight function to maximise the usage of the dataset. The resulting ship domain model compares well with existing ship domains for typical encounters, such as those of Fujii and Coldwell but represents non-typical encounters more effectively than existing models.

/pdf/an-empirically-calibrated-ship-domain-as-a-safety-criterion-521d3hs5o3.pdf

An Empirically-Calibrated Ship Domain as a Safety Criterion for Navigation in Confined Waters

By taking into account certain boundaries of the maneuvering region, along with navigation obstacles and other moving ships, the problem of avoiding collisions in navigation traffic areas was reduced to a dynamic optimization task with static and dynamic constraints. In heavy navigation traffic areas and within coastal zones, correct selection of a ship's speed, when accompanied by the necessary trajectory changes, is a crucial element of safe navigation. This paper presents a modernized version of the evolutionary ship trajectory planning system in which a new parameter was introduced, namely changes of the ship's speed along particular sections of the trajectory. Generally, a safe trajectory is estimated using specialized genetic operators for modifying the trajectory. Here, an additional operator was added to the system that mutates the ship's speed. Sample results present the safe trajectory for a ferry meeting other moving ships and navigational constraints on its way.

Evolutionary trajectory planning of ships in navigation traffic areas

The motion planning problem for mobile robots is typically formulated as follows: given a robot and a description of an environment, plan a path of the robot between two specified locations, which is collision-free and satisfies certain optimization criteria. Traditionally there are two approaches to the problem: Off-line planning, which assumes perfectly known and stable environment, and on-line planning, which focuses on dealing with uncertainties when the robot traverses the environment. On-line planning is also referred to by many researchers as the navigation problem. Additional difficulties in approaching navigation problem is that some environments are dynamic, i.e., the obstacles which are present there, need not be static. In this paper we consider a particular instance of a navigation problem, namely, a problem of computing a near-optimum trajectory of a ship. By taking into account certain boundaries of the maneuvering region, along with navigation obstacles and other moving ships, the problem of avoiding collisions at sea was reduced to a dynamic optimization task with static and dynamic constrains. The paper presents a modified version of the Evolutionary Planner/Navigator algorithm, θEP/N++, to address the problem. The introduction of a time parameter, the variable speed of the ship, and time-varying constraints representing movable ships, are the main features of the new system. Sample results, having the form of ship trajectories obtained using the program for navigation situations

Path Planning in Dynamic Environments.

Suitable route planning is related to the safety and economy of navigation. However, route planning has become increasingly complex over the years and the planning process requires a large amount of oceanic environmental information. In order to use the oceanic environmental information effectively and improve the efficiency of route planning, this research employed a Geographic Information System (GIS) as the platform for enabling two-phase automatic route generation design. Firstly, through GIS's spatial data management, spatial analysis and geometric computation capability, the presence of the obstacle is detected and candidate routes are automatically generated. These are provided to the evolutionary algorithm as the basis for preliminary population calculation. Then, a specially designed evolutionary algorithm is used for route elimination to obtain the optimal route, resulting in the most-recommended routes that encompass safety and economy. This technique is more efficient than evolutionary computation techniques that use traditional random searches. At the same time, this targets safety and economy, providing a reference for developing a route planning strategy.

C. T. Stockel

Papers

An Automatic Collision Avoidance and Guidance System for Marine Vehicles in Confined Waters