Journal of the Korean Society of Marine Environment & Safety (해양환경안전학회지)

The Korean Society of Marine Environment and safety (해양환경안전학회)
권호 표지
DOI QR코드

DOI QR Code

Study on Improving the Navigational Safety Evaluation Methodology based on Autonomous Operation Technology

자율운항기술 기반의 선박 통항 안전성 평가 방법론 개선 연구

  • Jun-Mo Park (Division of Navigation Science, Mokpo National Maritime University)
  • 박준모 (목포해양대학교 항해학부 )
  • Received : 2024.02.02
  • Accepted : 2024.02.23
  • Published : 2024.02.28
Download PDF
⟨ Previous Next ⟩

Abstract

In the near future, autonomous ships, ships controlled by shore remote control centers, and ships operated by navigators will coexist and operate the sea together. In the advent of this situation, a method is required to evaluate the safety of the maritime traffic environment. Therefore, in this study, a plan to evaluate the safety of navigation through ship control simulation was proposed in a maritime environment, where ships directly controlled by navigators and autonomous ships coexisted, using autonomous operation technology. Own ship was designed to have autonomous operational functions by learning the MMG model based on the six-DOF motion with the PPO algorithm, an in-depth reinforcement learning technique. The target ship constructed maritime traffic modeling data based on the maritime traffic data of the sea area to be evaluated and designed autonomous operational functions to be implemented in a simulation space. A numerical model was established by collecting date on tide, wave, current, and wind from the maritime meteorological database. A maritime meteorology model was created based on this and designed to reproduce maritime meteorology on the simulator. Finally, the safety evaluation proposed a system that enabled the risk of collision through vessel traffic flow simulation in ship control simulation while maintaining the existing evaluation method.

곧 다가올 미래에는 자율운항선박, 육상 원격제어센터에서 제어되는 선박, 그리고 항해사가 탑승하여 운항하는 선박이 함께 공존하며 해상을 운항할 것이며, 이러한 상황이 도래했을 때 해상 교통 환경의 안전을 평가할 수 있는 방법이 필요할 것으로 사료된다. 이에 본 연구에서는 자율운항기술을 사용하여 항해사가 직접 조종하는 선박과 자율운항선박이 공존하는 해상환경 하에서 선박조종시뮬레이션을 통해 통항 안전성을 평가하기 위한 방안을 제시하였다. 자선은 6-자유도 운동 기반의 MMG 모델을 심층 강화학습기법 중 하나인 PPO 알고리즘으로 학습하여 자율운항 기능을 갖출 수 있도록 설계하였다. 타선은 평가 대상 해역의 해상 교통 모델링 자료로부터 선박이 생성되도록 하였고, 기 학습된 선박모델을 기반으로 자율운항 기능을 구현되도록 하였다. 그리고 해양기상 자료 데이터베이스로부터 조위, 파랑, 조류, 바람에 대한 자료를 수집하여 수치 모델을 수립하고 이를 기반으로 해양기상 모델을 생성하여 시뮬레이터 상에서 해양 기상이 재현되도록 설계하였다. 마지막으로 안전성 평가는 기존의 평가 방법을 그대로 유지하되, 선박조종시뮬레이션에서 해상교통류 시뮬레이션을 통한 충돌 위험성 평가가 가능하도록 하는 시스템을 제안하였다.

Keywords

Acknowledgement

본 연구는 2022년도 목포해양대학교 교내연구비의 지원을 받아 수행한 연구결과임.

References

  1. Choi, W. J., H. I. Kim, and S. H. Jun(2019), Development of the Ship Manoeuvring PC Simulator Based on the Network, Journal of Navigation and Port Rsearch, Vol. 43, No. 6, pp. 403-412. 
  2. Gong, I. Y., Y. H. Kim, S. M. Kim, and I. H. Youn(2022), Review of Operation Concept and System Requirements for Shore Remote Control Simulator System for MASS, Journal of the Korean Society of Marine Environment & Safety, Vol. 28, No. 5, pp. 937-945.  https://doi.org/10.7837/kosomes.2022.28.6.937
  3. Guan, W., Z. Cui, and X. Zhang(2022), Intelligent Smart Marine Autonomous Surface Ship Decision System Based on Improved PPO Algorithm, Sensors, Vol. 22, No. 5732, pp. 1-33.  https://doi.org/10.1109/JSEN.2021.3136033
  4. Hong, S. J. and J. H. Kim(2021), Reinforcement Learning Based Tugboats Control for Autonomous Ship Berthing, Journal of the Korea Society for Naval Science & Technology, Vol. 4, No. 1, pp. 72-77. 
  5. Kim, H. J.(2019), Basic Research on the Agent Based M&S for Maritime Traffic Analysis, Proceedings of the 2019 Spring Conference of the Korean Navigation and Port Research, Vol. 1, No. 1, pp. 10-11. 
  6. Lee, Y. S.(2011), A Study on Adequacy of Audit Techniques and Advancement of Ship-Handling Simulation for Maritime Safety Audit, Journal of the Korean Society of Marine Environment & Safety, Vol. 17, No. 4, pp. 391-398.  https://doi.org/10.7837/kosomes.2011.17.4.391
  7. MOF(2022), Guidelines for the Implementation of Maritime Safety Audit, Ministry of Oceans and Fisheries, pp. 1-10. 
  8. Nomoto, K., K. Taguchi, K. Honda, and S. Hirono(1957), On the Steering Qualities of Ships, ISP, Vol. 4. 
  9. Park, S. K., J. Y. Oh, and H. J. Kim(2019), The Analysis of Reinforcement Learning Environment for Intelligent Ship Navigation Agents, Proceedings of the 2019 Spring Conference of the Korean Navigation and Port Research, Vol. 1, No. 1, pp. 3-4. 
  10. Deraj, R., R. S. Sanjeev Kumar, Md Shadab Alam, and Abhilash Somayajul(2023), Deep reinforcement learning based controller for ship navigation, Ocean Engineering, Vol. 273, No. 113937, pp. 1-18.  https://doi.org/10.1016/j.oceaneng.2023.113937
  11. Seong, Y. C.(2010), The Study on Development of Intergrated Ship's Traffic Flow Simulation Model based on Collision Avoidance Function, Journal of the Korean Society of Marine Environment & Safety, Vol. 16, No. 1, pp. 101-106. 
  12. Wang, C., X. Zhang, Z. Yang, M. Bashir, and K. Lee(2023), Collision avoidance for autonomous ship using deep reinforcement learning and prior-knowledge-based approximate representation, Frontiers in Marine Science, pp. 1-14. 
  13. Wu, D., Y. Lei, M. He, C. Zhang, and L. Ji(2022), Deep Reinforcement Learning-Based Path Control and Optimization for Unmanned Ships, Wireless Communications and Mobile Computing, Vol. 2022, No. 7135043, pp. 1-8.