A collision-prevention expert system for a Navy Officer of the deck.

Loading...
Thumbnail Image
Authors
Lewallen, Terry W.
Subjects
rule-based expert system
nautical navigation regulations
artificial intelligence
Advisors
Rowe, Neil C.
Date of Issue
1987-03
Date
March 1987
Publisher
Language
en_US
Abstract
The goal of this thesis is to automate recommendations to the Officer of the Deck, when decisions are made concerning situations that involve risk of collision. A rule-based expert system is designed and implemented as a solution to this task. The rules are based on regulations in the U.S. Coast Guard manual, Navigation Rules International-Inland. The expert system receives facts that describe the current situation, then searches the rule base for matching rules. The searching method is a hybrid form of forward chaining that searches cyclically through the rule base until all matches, intermediate and final, are located. The conclusions of the matching rules are displayed as a recommendation to the system user. The resulting system provides a valuable input to the Officer of the Deck, serving to increase the speed and reliability of the final decision by removing the necessity of manually looking up regulations or relying on memorization.
Type
Thesis
Description
Series/Report No
Department
Computer Science
Organization
Naval Postgraduate School (U.S.)
Identifiers
NPS Report Number
Sponsors
Funder
Format
74 p.
Citation
Distribution Statement
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.
Collections