{"id":{"repo_id":"vt","oai_identifier":"oai:vtechworks.lib.vt.edu:10919/135507"},"canonical_url":"https://search.dev.ndltd.org/etd/vt/oai:vtechworks.lib.vt.edu:10919/135507","repository":{"repo_id":"vt","name":"Virginia Tech","base_url":"https://vtechworks.lib.vt.edu/oai/request"},"display":{"title":"Reinforcement Learning with a Lost Person Model for Search and Rescue Path Planning","abstract":"In this thesis, we train a reinforcement learning agent to plan paths for search and rescue applications using a model of lost person behavior trained on past search incidents. We propose an improved method for producing occupancy maps from the trajectories of an agent-based lost person model. We demonstrate that through an end-to-end learning approach our agent can generalize to novel search incidents without directly observing the probability distribution describing search risk.","abstract_html":"In this thesis, we train a reinforcement learning agent to plan paths for search and rescue applications using a model of lost person behavior trained on past search incidents. We propose an improved method for producing occupancy maps from the trajectories of an agent-based lost person model. We demonstrate that through an end-to-end learning approach our agent can generalize to novel search incidents without directly observing the probability distribution describing search risk.","abstract_has_math":false,"creators":["Howell, Bryson L."],"institution":"Virginia Tech","degree_name":"Master of Science","degree_level":"masters","degree_discipline":"Computer Engineering","degree_department":"Electrical and Computer Engineering","school":null,"contributors":[],"advisors":[],"committee_chairs":["Williams, Ryan K."],"committee_members":["Lau, Nathan","Doan, Thinh T."],"year":2025,"date_issued":"2025-05-12","date_published":"2025-05-12","updated_at":"2026-07-22T22:20:41Z","subjects":["Reinforcement Learning","Search and Rescue","Path Planning"],"languages":["en"],"rights":["In Copyright"],"rights_urls":["http://rightsstatements.org/vocab/InC/1.0/"],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/10919/135507","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.committeechair","label":"Committee Chair","values":["Williams, Ryan K."]},{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Lau, Nathan","Doan, Thinh T."]},{"key":"dc:contributor.department","label":"Department","values":["Electrical and Computer Engineering"]},{"key":"dc:creator","label":"Author","values":["Howell, Bryson L."]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2025-06-13T13:23:43Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2025-06-13T13:23:43Z"]},{"key":"dc:date.issued","label":"Date","values":["2025-05-12"]},{"key":"dc:publisher","label":"Institution","values":["Virginia Tech"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"dc:type.dcmitype","label":"Dc Type Dcmitype","values":["Text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["masters"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["Virginia Polytechnic Institute and State University"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Reinforcement Learning","Search and Rescue","Path Planning"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["In Copyright"]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://rightsstatements.org/vocab/InC/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/10919/135507"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["In this thesis, we train a reinforcement learning agent to plan paths for search and rescue applications using a model of lost person behavior trained on past search incidents. We propose an improved method for producing occupancy maps from the trajectories of an agent-based lost person model. We demonstrate that through an end-to-end learning approach our agent can generalize to novel search incidents without directly observing the probability distribution describing search risk."]},{"key":"dc:description.abstractgeneral","label":"General Abstract","values":["We enable an aerial robot to plan paths for search and rescue applications that maximize the chance that a missing person will be found quickly. We investigate improved methods of creating search plans from a behavioral model replicating the movement of a missing person, and demonstrate that our robot is capable of learning from a varied set of past search experiences to perform well in search tasks it has not seen before."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["Master of Science"]},{"key":"dc:format.medium","label":"Dc Format Medium","values":["ETD"]},{"key":"dc:format.mimetype","label":"Dc Format Mimetype","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Reinforcement Learning with a Lost Person Model for Search and Rescue Path Planning"]}]}],"canonical_facts":{"dc:contributor.committeechair":["Williams, Ryan K."],"dc:contributor.committeemember":["Lau, Nathan","Doan, Thinh T."],"dc:contributor.department":["Electrical and Computer Engineering"],"dc:creator":["Howell, Bryson L."],"dc:date.accessioned":["2025-06-13T13:23:43Z"],"dc:date.available":["2025-06-13T13:23:43Z"],"dc:date.issued":["2025-05-12"],"dc:description.abstract":["In this thesis, we train a reinforcement learning agent to plan paths for search and rescue applications using a model of lost person behavior trained on past search incidents. We propose an improved method for producing occupancy maps from the trajectories of an agent-based lost person model. We demonstrate that through an end-to-end learning approach our agent can generalize to novel search incidents without directly observing the probability distribution describing search risk."],"dc:description.abstractgeneral":["We enable an aerial robot to plan paths for search and rescue applications that maximize the chance that a missing person will be found quickly. We investigate improved methods of creating search plans from a behavioral model replicating the movement of a missing person, and demonstrate that our robot is capable of learning from a varied set of past search experiences to perform well in search tasks it has not seen before."],"dc:description.degree":["Master of Science"],"dc:format.medium":["ETD"],"dc:format.mimetype":["application/pdf"],"dc:identifier.uri":["https://hdl.handle.net/10919/135507"],"dc:language.iso":["en"],"dc:publisher":["Virginia Tech"],"dc:rights":["In Copyright"],"dc:rights.uri":["http://rightsstatements.org/vocab/InC/1.0/"],"dc:subject":["Reinforcement Learning","Search and Rescue","Path Planning"],"dc:title":["Reinforcement Learning with a Lost Person Model for Search and Rescue Path Planning"],"dc:type":["Thesis"],"dc:type.dcmitype":["Text"],"thesis:degree_discipline":["Computer Engineering"],"thesis:degree_level":["masters"],"thesis:degree_name":["Master of Science"],"thesis:institution_name":["Virginia Polytechnic Institute and State University"]},"updated_at":"2026-07-22T22:20:41Z"}