Type-2 fuzzy ontology-based semantic knowledge for collision avoidance of autonomous underwater vehicles

The volume of obstacles encountered in the marine environment is rapidly increasing, which makes the development of collision avoidance systems more challenging. Several fuzzy ontology-based simulators have been proposed to provide a virtual platform for the analysis of maritime missions. However, due to the simulators’ limitations, ontology-based knowledge cannot be utilized to evaluate maritime robot algorithms and to avoid collisions. The existing simulators must be equipped with smart semantic domain knowledge to provide an efficient framework for the decision-making system of AUVs. This article presents type-2 fuzzy ontology-based semantic knowledge (T2FOBSK) and a simulator for marine users that will reduce experimental time and the cost of marine robots and will evaluate algorithms intelligently. The system reformulates the user’s query to extract the positions of AUVs and obstacles and convert them to a proper format for the simulator. The simulator uses semantic knowledge to calculate the degree of collision risk and to avoid obstacles. The available type-1 fuzzy ontology-based approach cannot extract intensively blurred data from the hazy marine environment to offer actual solutions. Therefore, we propose a type-2 fuzzy ontology to provide accurate information about collision risk and the marine environment during real-time marine operations. Moreover, the type-2 fuzzy ontology is designed using Protégé OWL-2 tools. The DL query and SPARQL query are used to evaluate the ontology. The distance to closest point of approach (DCPA), time to closest point of approach (TCPA) and variation of compass degree (VCD) are used to calculate the degree of collision risk between AUVs and obstacles. The experimental and simulation results show that the proposed architecture is highly efficient and highly productive for marine missions and the real-time decision-making system of AUVs.