Advanced Bayesian study on inland navigational risk of remotely controlled autonomous ship

Cunlong Fan; Victor Bolbot; Jakub Montewka; Di Zhang

doi:10.1016/j.aap.2024.107619

Advanced Bayesian study on inland navigational risk of remotely controlled autonomous ship

Accid Anal Prev. 2024 May 9:203:107619. doi: 10.1016/j.aap.2024.107619. Online ahead of print.

Authors

Cunlong Fan¹, Victor Bolbot², Jakub Montewka³, Di Zhang⁴

Affiliations

¹ College of Transport & Communications, Shanghai Maritime University, 1550 Haigang Avenue, Shanghai 201306, PR China; Department of Marine Technology, Norwegian University of Science and Technology, 7491 Trondheim, Norway.
² Marine Technology, Department of Mechanical Engineering, School of Engineering, Aalto University, 00340 Espoo, Finland; Kotka Maritime Research Centre, 48100, Kotka, Finland.
³ Gdańsk University of Technology, Gdańsk, Poland; Waterborne Transport Innovation, Gdańsk, Poland.
⁴ State Key Laboratory of Maritime Technology and Safety, Wuhan University of Technology, 1040 Heping Avenue, Wuhan, Hubei 430063, PR China; National Engineering Research Center for Water Transport Safety, Wuhan University of Technology, 1040 Heping Avenue, Wuhan, Hubei 430063, PR China; School of Transportation and Logistics Engineering, Wuhan University of Technology, 1040 Heping Avenue, Wuhan, Hubei 430063, PR China. Electronic address: zhangdi@whut.edu.cn.

PMID: 38729057
DOI: 10.1016/j.aap.2024.107619

Abstract

The arise of autonomous ships has necessitated the development of new risk assessment techniques and methods. This study proposes a new framework for navigational risk assessment of remotely controlled Maritime Autonomous Surface Ships (MASS). This framework establishes a set of risk influencing factors affecting safety of navigation of a remotely-controlled MASS. Next, model parameters are defined based on the risk factors, and the model structure is developed using Bayesian Networks. To this end, an extensive literature survey is conducted, enhanced with the domain knowledge elicited from the experts and improved by the experimental data obtained during representative MASS model trials carried out in an inland river. Conditional Probability Tables are generated using a new function employing expert feedback regarding Interval Type 2 Fuzzy Sets. The developed Bayesian model yields the expected utilities results representing an accident's probability and consequence, with the results visualized on a dedicated diagram. Finally, the developed risk assessment model is validated by conducting three axiom tests, extreme scenarios analysis, and sensitivity analysis. Navigational environment, natural environment, traffic complexity, and shore-ship collaboration performance are critical from the probability and consequence perspective for inland navigational accidents to a remotely controlled MASS. Lastly, important nodes to Shore-Ship collaboration performance include autonomy of target ships, cyber risk, and transition from other remote control centers.

Keywords: Bayesian Belief Network; Interval Type 2 Fuzzy number; Maritime Autonomous Surface Ships; Navigational risk; Remote control.