ONTOLOGY FOR AUTONOMOUS SURFACE VESSEL COLLISION AVOIDANCE DECISION AID
Loading...
Authors
Timberlake, James W.
Subjects
ontology
autonomous vessels
maritime autonomous surface ships
rules of the road
Convention on the International Regulations for Preventing Collisions at Sea
COLREGs
collision avoidance
decision aid
automated theorem prover
ATP
Suggested Upper Merged Ontology
SUMO
autonomous vessels
maritime autonomous surface ships
rules of the road
Convention on the International Regulations for Preventing Collisions at Sea
COLREGs
collision avoidance
decision aid
automated theorem prover
ATP
Suggested Upper Merged Ontology
SUMO
Advisors
Pease, R A.
Date of Issue
2025-03
Date
Publisher
Monterey, CA; Naval Postgraduate School
Language
Abstract
Maritime collision avoidance is essential for both manned and unmanned vessels, yet effectively applying the Convention on the International Regulations for Preventing Collisions at Sea (COLREGs) remains challenging. This research addresses this by formalizing key COLREGs rules within the machine-interpretable Suggested Upper Merged Ontology (SUMO) and validating its reasoning capabilities using the Vampire Automated Theorem Prover (ATP). The study tested 288 maritime scenarios covering no-situation, crossing, overtaking, and head-on encounters. The ATP identified situations and determined appropriate vessel actions with a 99.4% true-positive rate, while providing transparency and traceability for each conclusion. The model demonstrated local logical consistency, and although global satisfiability could not be confirmed due to computational complexity, no evidence of unsatisfiability was found. This work establishes a foundation for a transparent, traceable autonomous vessel decision aid. Beyond unmanned systems, the model shows promise as a decision-support tool for manned vessels and a training aid for mariners. Future research should expand the ontology to handle complex multi-vessel scenarios, incorporate temporal reasoning, and integrate with real-time maritime simulation software to enhance validation and scalability.
Type
Thesis
Description
Series/Report No
Department
Computer Science (CS)
Organization
Identifiers
NPS Report Number
Sponsors
Funder
Format
Citation
Distribution Statement
Distribution Statement A. Approved for public release: Distribution is unlimited.
Rights
This publication is a work of the U.S. Government as defined in Title 17, United States Code, Section 101. Copyright protection is not available for this work in the United States.