Related Experiment Video
Updated: May 8, 2026
09:22
Quantitatively Measuring In situ Flows using a Self-Contained Underwater Velocimetry Apparatus SCUVA
Published on: October 31, 2011
13.0K
Advanced Bayesian study on inland navigational risk of remotely controlled autonomous ship
Cunlong Fan1, Victor Bolbot2, Jakub Montewka3
1College 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.
Accident; Analysis and Prevention
|May 10, 2024
Summary
This study introduces a novel framework for assessing navigational risks in remotely controlled Maritime Autonomous Surface Ships (MASS). Key factors influencing MASS safety include environment, traffic, and shore-ship collaboration.
Area of Science:
- Maritime Safety
- Autonomous Systems
- Risk Assessment
Background:
- The increasing prevalence of autonomous ships necessitates advanced risk assessment methodologies.
- Current methods may not adequately address the unique challenges posed by remotely controlled Maritime Autonomous Surface Ships (MASS).
Purpose of the Study:
- To propose a new framework for navigational risk assessment specifically for remotely controlled MASS.
- To identify critical risk influencing factors and develop a robust Bayesian Network model for evaluating MASS safety.
Main Methods:
- Development of a Bayesian Network model incorporating risk factors, expert knowledge, and experimental data from MASS trials.
- Utilizing Interval Type 2 Fuzzy Sets for generating Conditional Probability Tables based on expert feedback.
- Validation through axiom tests, extreme scenarios analysis, and sensitivity analysis.
Main Results:
- Identified critical factors for inland MASS navigational accidents: navigational environment, natural environment, traffic complexity, and shore-ship collaboration performance.
- Shore-ship collaboration performance is significantly influenced by target ship autonomy, cyber risk, and remote control transitions.
Conclusions:
- The developed Bayesian model effectively quantifies accident probability and consequence for remotely controlled MASS.
- The framework provides a validated approach to enhance the safety of autonomous shipping operations.
