Fuzzy Inference and Sequence Model-Based Collision Risk Prediction System for Stand-On Vessel.

Area of Science:

• Maritime Safety
• Navigational Risk Assessment
• Collision Avoidance Systems

Background:

• International Regulations for Preventing Collision at Sea (COLREGs) guide vessel encounters but most accidents occur in crossing situations.
• Previous collision avoidance studies focused on current risk assessment, limiting timely decision-making for stand-on vessels.

Purpose of the Study:

• To develop a predictive collision risk system for stand-on vessels to improve collision avoidance decision-making.
• To enable stand-on vessels to assess future collision risk at the current time.

Main Methods:

• A fuzzy inference system based on near-collision (FIS-NC) was integrated with a sequence model.
• The system predicts the future collision risk index (CRI) at time (t+i) for the stand-on vessel at the current time (t).

Main Results:

• The developed system enables prediction of future collision risk for stand-on vessels.
• Navigators using the system can achieve greater clearance distances and time, enhancing safety.

Conclusions:

• The predictive collision risk system addresses limitations of current risk assessment methods.
• This approach facilitates quicker collision avoidance decisions, improving maritime safety in crossing situations.