Aiming at the problems of miscellaneous navigation safety information and the difficulty of multi-source heterogeneous information fusion, a novel ontology-based collision avoidance decision making method is proposed in this paper. first of all, the structured ontology model of navigation situation is built on the basis of analysing the hierarchy and interactivity of various scene elements in driving scene and constructing the semantic model of entity class and binary attribute of scene elements, implement effective modelling of navigation scenarios. Secondly, the knowledge base of collision avoidance decision and online reasoning system are constructed based on the semantic expression of typical scene elements to realize the efficient utilization of navigation prior knowledge. Finally, the simulation experiment is carried out for the typical ship encounter scenarios in open water. The results show that the ontology method can effectively improve the cognition ability of Maritime Autonomous Surface Ships (MASS), and meet the requirements for real-time, safety and rationality of collision avoidance decision.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.