소형 무인선의 충돌회피를 위한 자율운항에 관한 연구

Abstract

According to the development of information and communication technology, the International Maritime Organization (IMO) adopted the term of Maritime Autonomous Surface Ships (MASS) as a concept of future ship at the Maritime Safety Committee (MSC) in 2017. Since 2011, KRISO have developed a multi-purpose intelligent unmanned surface vehicle (USV) under the financial support of KOREA Ministry of Oceans and Fisheries. In 2018, the final prototype USV, ARAGON3 was built as a kind of small MASS. It has a planning hull with the length of 8 meters and the displacement of 3 tons. For safe navigation, it should keep the convention on the international regulations for preventing collisions at sea, 1972 (COLREGs). For this, autonomous navigation system is needed without human operation. Collision avoidance algorithm is implemented by using changeable action space searching, which can be flexibly changed according to the collision risk (CR). CR is estimated by using fuzzy inference. Obstacle information is estimated through the data fusion of multiple sensors of AIS, Radar, Lidar and Camera. Route for collision avoidance is optimized considering the cost functions of collision risk, efficiency and their combinations. Sea trial tests are conducted for the validation of the autonomous navigation system. Scenarios are tested on the colliding situations of head-on, crossing and overtaking with multiple traffic ships. Five powerboat