A deterministic collision avoidance decision-making system for multi-MASS encounter situation

Abstract

Efficient identification of multi-ship encounter situation concerning action priority analysis is of vital significance for making effective and practical collision avoidance manoeuvres. However, action priority analysis is strongly involved in conflict urgency quantification, collision candidates relevance analysis as well as the contribution analysis within the encountering ships. In this paper, considering Maritime Autonomous Surface Ship, a deterministic collision avoidance decision-making system is established to estimate multi-MASS encounter situation. To this end, the approach index and asymmetrical Gaussian fitting method are deployed to assess collision risk, while the encountering ships are analytically distinguished into different clusters based on the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm. By virtue of the improved Sharpley value method, the collision avoidance action priority is elaboratively sorted for different clusters. Accordingly, each individual collision avoidance manoeuvres are collaboratively generated by the modified velocity obstacle algorithm with certain time delay. Eventually, the proposed decision-making system is synthesized by functional modules including data-processing, conflict assessment detection, relevance analysis, action priority analysis, path planning and performance monitor. Simulation results demonstrate that this proposed decision-making system can perform significant superiority in various maritime environment in line with the practice of coordination and navigation.