With the continuous development of science and technology, unmanned ship has gradually become a hot spot in the field of marine research. In practical applications, unmanned ships need to have long-range navigation and high efficiency, so that they can accurately perform tasks in the marine environment. As one of the key technologies of unmanned ship, path planning is of great significance to improve the endurance of unmanned ship. In order to meet the requirements, this paper proposes a path planning method for long distance unmanned ships based on reinforcement learning angle precedence ant colony improvement algorithm. Firstly, canny operator is used to automatically extract navigation environment information, and then MAKLINK graph theory is applied for environment modelling. Finally, the basic ant colony algorithm is improved and applied to the path planning of unmanned ship to generate an optimal path. The experimental results show that, compared with the traditional ant colony algorithm, the path planning method based on the improved ant colony algorithm can achieve a voyage duration of nearly 7 km for unmanned ships under the same sailing environment, which has certain practicability and popularization value.

본 연구는 지형공간정보체계 기반에서 리스크 요인의 변동을 고려한 의사결정을 적용하여 정량적 평가를 수행할 수 있는 기법을 연구한 결과, 다음과 같은 결론을 얻을 수 있었다. 첫째, 리스크 요인의 변동을 고려한 의사결정을 통하여, 기존의 노선에 대한 평가를 정량적인 값으로 산출 할 수 있었으며, 이를 신설될 노선에 대하여 적용하면 도로 계획 및 기본 설계시에 객관적이고 신뢰성 있는 설계를 할 수 있을 것으로 판단된다. 둘째, 리스크 요인의 변동을 고려한 평면선형과 종단선형을 지형공간정보체계 기반에서 쉽게 추출할 수 있었으며, 도로의 계획에서 의사결정에 의한 신속한 3차원 선형 계획 및 분석이 가능하다. 셋째, 본 연구에서 구축된 정량적 평가 시스템을 이용하면 노선선정이 자동화됨으로서, 비교적 많은 비교안을 짧은 시간 내에 리스크 분석을 할 수 있으므로, 도로설계기술발전에 기여 할 수 있다고 판단된다.

The -advent of electronic navigation equipment and trustworthy computer which provides people with convenience made the management system by one-man bridge operation or the least people who are needed possible through the integration of communication network with various navigation equipment and related institution. One of the most needed ultra-modem navigation device for a mate, ECDIS is a core equipment for navigation in ENS that notifies peril to mate as well as supervises all tasks in hydrographical chart, voyage planning, course monitoring and voyage recording. We should make coast and ocean voyage planning first, for the secure navigation which is considering the course circumstances and next, for the reduction of voyage dates in economical aspect. There needs a thoughtful consideration about the feature of the ship itself and the course with weather condition in taking up the course and also we have to take into accounts about appropriate distance between ships. Considering the essential conditions of ECDIS the indispensable device in the future, it was developed the basic principle for voyage planning algorithm for officer and programmed to real implementation available. In this paper including most of the requirements in ECDIS performance standard I mentioned about such a basic and a core Principle with real application by using the Visual C++ programming language. The voyage plan includes the function that indicate and modifies all the way points in the course from department port to arrival port with erasing the wrong way points. Also, it provides in a document form that shows ETA at glance in average speed sailing.

Recently, the Track Control System which was separated from the Course Control System so-called Auto-Pilot has been developed for track-keeping in coastal area. From this year, the NAV Sub-committee in IMO commenced to consider the Performance Standard for the Track Control System vigorously. This system will be integrated with ECDIS and IBS so that captain/officers should analysis ship's motion characteristics accurately in the route planning using the electronic nautical charts. In this paper, a new Route Analysis Algorithm using fuzzy reasoning in route planning was proposed for 2, 700 TEU container ship. In order to verify the track-keeping, the author established a ship mathematical model and executed the simulation of the Route Analysis Algorithm at on-line condition with Pentium PC. The results of ship trajectories of the Route Analysis Algorithm were found to be effective to get track control automatically.