Collision Risk Level Analysis Based on the Computed Distance and Closing Time of an Autonomous Surface Vessel and Other Objects

The first part of paper focuses on the results of a fuzzy system study for analyzing the collision level of marine autonomous surface vessels (MASV) with located sea crafts encountered in the path of a ship. In this system, the MASV risk collision level is determined depending on two input variables (first is the distance at closest point of approach and second is the time to closest point of approach). The system makes a decision using the Mamdani fuzzy inference algorithm. For improving the system characteristics quality was developed the neuro-fuzzy model for measure MASV collision risk level is constructed and implemented by hybridizing the fuzzy system with neural network technologies based on the Adaptive Neuro-Fuzzy Inference System. The neuro-fuzzy system study describes on second part of the paper. The presented results of the investigation of the designed models show satisfactory outcomes and relevance of the model data to the problems being solved.