{"id":{"repo_id":"unr","oai_identifier":"oai:scholarwolf.unr.edu:11714/10954"},"canonical_url":"https://search.dev.ndltd.org/etd/unr/oai:scholarwolf.unr.edu:11714/10954","repository":{"repo_id":"unr","name":"University of Nevada - Reno","base_url":"https://scholarwolf.unr.edu/server/oai/request"},"display":{"title":"Comparing Potential Fields and Velocity Obstacles for Rules of the Road Compliant Ship Driving","abstract":"We propose two algorithms for nautical rules of the road compliant ship driving and collision avoidance: one that uses genetic algorithm trained potential fields, and one that determines a new trajectory from velocity obstacles and the closest point of approach. Prior work has used a variety of methods for ship driving, including genetic algorithms and velocity obstacles. However, the usage of potential fields in ship driving is unexplored and many ship driving algorithms are not tested on environments with multiple vessels. Therefore, we aim to provide new methods of ship driving and show that these methods are viable. We develop a 3D simulation environment that is able to more quickly process through situations by disabling the graphics component. We use this simulation environment to train our Genetic Algorithm Tuned Potential Fields for Ship Driving (GAPFS). Our potential fields use a distinct algorithm that is based on the angles of the vessels, and we use a fitness function that is based on a programmer defined path. We then develop the Velocity Obstacle COLREGs Colision Avoidance Algorithm (VOCCAA) to handle scenarios with multiple entities. This algorithm uses velocity obstacles to determine whether or not two ships will collide with each other, as well as to provide trajectories that do not lead to further risk-of-collision situations. Experimental results using the simulation environment show that both methods have potential to be viable approaches to ship driving. GAPFS is able to closely follow the specified paths for both vessels in the situation, despite the paths requiring different behavior. VOCCAA is able to plan new trajectories for multiple vessels in ambiguous situations. A comparison between the two algorithms shows that VOCCAA can handle random situations better than the potential fields method.","abstract_html":"We propose two algorithms for nautical rules of the road compliant ship driving and collision avoidance: one that uses genetic algorithm trained potential fields, and one that determines a new trajectory from velocity obstacles and the closest point of approach. Prior work has used a variety of methods for ship driving, including genetic algorithms and velocity obstacles. However, the usage of potential fields in ship driving is unexplored and many ship driving algorithms are not tested on environments with multiple vessels. Therefore, we aim to provide new methods of ship driving and show that these methods are viable. We develop a 3D simulation environment that is able to more quickly process through situations by disabling the graphics component. We use this simulation environment to train our Genetic Algorithm Tuned Potential Fields for Ship Driving (GAPFS). Our potential fields use a distinct algorithm that is based on the angles of the vessels, and we use a fitness function that is based on a programmer defined path. We then develop the Velocity Obstacle COLREGs Colision Avoidance Algorithm (VOCCAA) to handle scenarios with multiple entities. This algorithm uses velocity obstacles to determine whether or not two ships will collide with each other, as well as to provide trajectories that do not lead to further risk-of-collision situations. Experimental results using the simulation environment show that both methods have potential to be viable approaches to ship driving. GAPFS is able to closely follow the specified paths for both vessels in the situation, despite the paths requiring different behavior. VOCCAA is able to plan new trajectories for multiple vessels in ambiguous situations. A comparison between the two algorithms shows that VOCCAA can handle random situations better than the potential fields method.","abstract_has_math":false,"creators":["DiArchangel, Korben"],"institution":"University of Nevada, Reno","degree_name":"Master of Science","degree_level":"Master's Degree","degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":["Louis, Sushil"],"committee_chairs":[],"committee_members":["Hand, Emily","Houmanfar, Ramona"],"year":2024,"date_issued":"2024","date_published":"2024","updated_at":"2026-07-27T21:46:41Z","subjects":["CORLEGs","Genetic Algorithms","Potential Fields","Ship Driving","Velocity Obstacles"],"languages":[],"rights":["Creative Commons Attribution 4.0 International"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://scholarwolf.unr.edu/handle/11714/10954","outbound_label":"Repository record","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Louis, Sushil"]},{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Hand, Emily","Houmanfar, Ramona"]},{"key":"dc:creator","label":"Author","values":["DiArchangel, Korben"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2024-08-22T17:09:44Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2024-08-22T17:09:44Z"]},{"key":"dc:date.issued","label":"Date","values":["2024"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Master's Degree"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Nevada, Reno"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["CORLEGs","Genetic Algorithms","Potential Fields","Ship Driving","Velocity Obstacles"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["Creative Commons Attribution 4.0 International"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://scholarwolf.unr.edu/handle/11714/10954"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["We propose two algorithms for nautical rules of the road compliant ship driving and collision avoidance: one that uses genetic algorithm trained potential fields, and one that determines a new trajectory from velocity obstacles and the closest point of approach. Prior work has used a variety of methods for ship driving, including genetic algorithms and velocity obstacles. However, the usage of potential fields in ship driving is unexplored and many ship driving algorithms are not tested on environments with multiple vessels. Therefore, we aim to provide new methods of ship driving and show that these methods are viable. We develop a 3D simulation environment that is able to more quickly process through situations by disabling the graphics component. We use this simulation environment to train our Genetic Algorithm Tuned Potential Fields for Ship Driving (GAPFS). Our potential fields use a distinct algorithm that is based on the angles of the vessels, and we use a fitness function that is based on a programmer defined path. We then develop the Velocity Obstacle COLREGs Colision Avoidance Algorithm (VOCCAA) to handle scenarios with multiple entities. This algorithm uses velocity obstacles to determine whether or not two ships will collide with each other, as well as to provide trajectories that do not lead to further risk-of-collision situations. Experimental results using the simulation environment show that both methods have potential to be viable approaches to ship driving. GAPFS is able to closely follow the specified paths for both vessels in the situation, despite the paths requiring different behavior. VOCCAA is able to plan new trajectories for multiple vessels in ambiguous situations. A comparison between the two algorithms shows that VOCCAA can handle random situations better than the potential fields method."]},{"key":"dc:format","label":"Dc Format","values":["PDF"]},{"key":"dc:title","label":"Title","values":["Comparing Potential Fields and Velocity Obstacles for Rules of the Road Compliant Ship Driving"]}]}],"canonical_facts":{"dc:contributor.advisor":["Louis, Sushil"],"dc:contributor.committeemember":["Hand, Emily","Houmanfar, Ramona"],"dc:creator":["DiArchangel, Korben"],"dc:date.accessioned":["2024-08-22T17:09:44Z"],"dc:date.available":["2024-08-22T17:09:44Z"],"dc:date.issued":["2024"],"dc:description.abstract":["We propose two algorithms for nautical rules of the road compliant ship driving and collision avoidance: one that uses genetic algorithm trained potential fields, and one that determines a new trajectory from velocity obstacles and the closest point of approach. Prior work has used a variety of methods for ship driving, including genetic algorithms and velocity obstacles. However, the usage of potential fields in ship driving is unexplored and many ship driving algorithms are not tested on environments with multiple vessels. Therefore, we aim to provide new methods of ship driving and show that these methods are viable. We develop a 3D simulation environment that is able to more quickly process through situations by disabling the graphics component. We use this simulation environment to train our Genetic Algorithm Tuned Potential Fields for Ship Driving (GAPFS). Our potential fields use a distinct algorithm that is based on the angles of the vessels, and we use a fitness function that is based on a programmer defined path. We then develop the Velocity Obstacle COLREGs Colision Avoidance Algorithm (VOCCAA) to handle scenarios with multiple entities. This algorithm uses velocity obstacles to determine whether or not two ships will collide with each other, as well as to provide trajectories that do not lead to further risk-of-collision situations. Experimental results using the simulation environment show that both methods have potential to be viable approaches to ship driving. GAPFS is able to closely follow the specified paths for both vessels in the situation, despite the paths requiring different behavior. VOCCAA is able to plan new trajectories for multiple vessels in ambiguous situations. A comparison between the two algorithms shows that VOCCAA can handle random situations better than the potential fields method."],"dc:format":["PDF"],"dc:identifier.uri":["https://scholarwolf.unr.edu/handle/11714/10954"],"dc:rights":["Creative Commons Attribution 4.0 International"],"dc:subject":["CORLEGs","Genetic Algorithms","Potential Fields","Ship Driving","Velocity Obstacles"],"dc:title":["Comparing Potential Fields and Velocity Obstacles for Rules of the Road Compliant Ship Driving"],"dc:type":["Thesis"],"thesis:degree_level":["Master's Degree"],"thesis:degree_name":["Master of Science"],"thesis:institution_name":["University of Nevada, Reno"]},"updated_at":"2026-07-27T21:46:41Z"}