Navigation Situation Clustering Model of Human-Operated Ships for Maritime Autonomous Surface Ship Collision Avoidance Tests

Taewoong Hwang,Ik-Hyun Youn

doi:10.3390/jmse9121458

Abstract

The collision avoidance system is one of the core systems of MASS (Maritime Autonomous Surface Ships). The collision avoidance system was validated using scenario-based experiments. However, the scenarios for the validation were designed based on COLREG (International Regulations for Preventing Collisions at Sea) or are arbitrary. Therefore, the purpose of this study is to identify and systematize objective navigation situation scenarios for the validation of autonomous ship collision avoidance algorithms. A data-driven approach was applied to collect 12-month Automatic Identification System data in the west sea of Korea, to extract the ship’s trajectory, and to hierarchically cluster the data according to navigation situations. Consequently, we obtained the hierarchy of navigation situations and the frequency of each navigation situation for ships that sailed the west coast of Korea during one year. The results are expected to be applied to develop a collision avoidance test environment for MASS.

Highlights

Ship collisions are frequent accidents that account for more than 50% of all maritime accidents [1], causing large scale of casualties and property and environmental damage [2].Collision accidents are a concern even in the development of MASS (Maritime AutonomousSurface Ship) [3]
The MASS collision avoidance system is one of the core systems of MASS. Compared to this importance, because the scenario design being used in the test was subjective and did not reflect the characteristics of human-operated ships encountered by the actual MASS, it is necessary to develop an objective scenario
The navigation situation of human-operated ships was distinguished for the validation of systematic

Summary

Introduction

Ship collisions are frequent accidents that account for more than 50% of all maritime accidents [1], causing large scale of casualties and property and environmental damage [2].Collision accidents are a concern even in the development of MASS (Maritime AutonomousSurface Ship) [3]. Ship collisions are frequent accidents that account for more than 50% of all maritime accidents [1], causing large scale of casualties and property and environmental damage [2]. The collision avoidance and path finding system of the MASS is considered one of the core systems of MASS [4]. Numerous studies were conducted on this collision avoidance system and path finding/control systems [5,6,7]. This system was tested in navigation scenarios to validate safety integrity. Perera et al presented an experimental evaluation of autonomous ship collision avoidance. Five COLREGbased encounter situations were set up for the experimental evaluation of autonomous navigation and collision avoidance [8]

Objectives

Findings

Discussion

Conclusion