{"id":{"repo_id":"denver","oai_identifier":"oai:digitalcommons.du.edu:etd-3463"},"canonical_url":"https://search.ndltd.org/etd/denver/oai:digitalcommons.du.edu:etd-3463","repository":{"repo_id":"denver","name":"University of Denver","base_url":"https://digitalcommons.du.edu/do/oai/"},"display":{"title":"Heterogeneous Multi-Robot Person-Following in Constrained Environments","abstract":"Maintaining visibility of a person requires effective systems. Security cameras or ground robots might be ideal, but they often fail in uncontrolled or unknown environments. A single ground robot struggles to navigate and track an agent at the same time. This work addresses the challenge by developing a multi-robot system with a slow ground robot and an agile aerial robot. Three methods are evaluated: FORWARD-PF, RL-Person Following (RL), and a baseline closed-loop method. FORWARD-PF proved the most reliable, completing all nine paths and reaching targets nearly twice as fast as RL. Despite completing seven paths, RL faltered on complex tasks. The closed-loop method succeeded only 33% of the time, managing just the easiest paths. These findings underscore FORWARD-PF’s efficiency and reveal both the potential and limitations of RL, demonstrating the promise of heterogeneous multi-robot systems for person-following in unpredictable settings.","abstract_html":"Maintaining visibility of a person requires effective systems. Security cameras or ground robots might be ideal, but they often fail in uncontrolled or unknown environments. A single ground robot struggles to navigate and track an agent at the same time. This work addresses the challenge by developing a multi-robot system with a slow ground robot and an agile aerial robot. Three methods are evaluated: FORWARD-PF, RL-Person Following (RL), and a baseline closed-loop method. FORWARD-PF proved the most reliable, completing all nine paths and reaching targets nearly twice as fast as RL. Despite completing seven paths, RL faltered on complex tasks. The closed-loop method succeeded only 33% of the time, managing just the easiest paths. These findings underscore FORWARD-PF’s efficiency and reveal both the potential and limitations of RL, demonstrating the promise of heterogeneous multi-robot systems for person-following in unpredictable settings.","abstract_has_math":false,"creators":["Miller, Ori A."],"institution":null,"degree_name":"M.S. in Computer Science","degree_level":"Masters Thesis","degree_discipline":null,"degree_department":null,"school":null,"contributors":["Christopher Reardon","Jason M. Gregory","Kerstin S. Haring","Naomi Reshotko"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T07:55:07Z","subjects":["Heterogenous robot team","Multi-robot systems","Person following","Artificial Intelligence and Robotics","Computer Engineering","Computer Sciences","Engineering","Robotics"],"languages":["English (eng)"],"rights":["<p>Copyright is held by the author. User is responsible for all copyright compliance.</p>","Ori A. Miller"],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://digitalcommons.du.edu/etd/2490","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://digitalcommons.du.edu/etd/2490","record_label":"Repository record","record_kind":"record","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://digitalcommons.du.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Adigitalcommons.du.edu%3Aetd-3463","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Christopher Reardon","Jason M. Gregory","Kerstin S. Haring","Naomi Reshotko"]},{"key":"dc:creator","label":"Author","values":["Miller, Ori A."]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.copyright","label":"Dc Date Copyright","values":["2024-08-01T07:00:00Z"]},{"key":"dc:date.created","label":"Dc Date Created","values":["2024-08-24T07:00:00Z"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Masters Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S. in Computer Science"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Heterogenous robot team","Multi-robot systems","Person following","Artificial Intelligence and Robotics","Computer Engineering","Computer Sciences","Engineering","Robotics"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["English (eng)"]},{"key":"dc:rights","label":"Dc Rights","values":["<p>Copyright is held by the author. User is responsible for all copyright compliance.</p>"]},{"key":"dc:rights.holder","label":"Dc Rights Holder","values":["Ori A. Miller"]},{"key":"dc:rights.license","label":"Dc Rights License","values":["all_rights_reserved"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.du.edu/etd/2490"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Maintaining visibility of a person requires effective systems. Security cameras or ground robots might be ideal, but they often fail in uncontrolled or unknown environments. A single ground robot struggles to navigate and track an agent at the same time. This work addresses the challenge by developing a multi-robot system with a slow ground robot and an agile aerial robot. Three methods are evaluated: FORWARD-PF, RL-Person Following (RL), and a baseline closed-loop method. FORWARD-PF proved the most reliable, completing all nine paths and reaching targets nearly twice as fast as RL. Despite completing seven paths, RL faltered on complex tasks. The closed-loop method succeeded only 33% of the time, managing just the easiest paths. These findings underscore FORWARD-PF’s efficiency and reveal both the potential and limitations of RL, demonstrating the promise of heterogeneous multi-robot systems for person-following in unpredictable settings."]},{"key":"dc:description.provenance","label":"Dc Description Provenance","values":["Received from Author"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:format.extent","label":"Dc Format Extent","values":["87 pgs","4.8 MB"]},{"key":"dc:title","label":"Title","values":["Heterogeneous Multi-Robot Person-Following in Constrained Environments"]}]}],"canonical_facts":{"dc:contributor":["Christopher Reardon","Jason M. Gregory","Kerstin S. Haring","Naomi Reshotko"],"dc:creator":["Miller, Ori A."],"dc:date.copyright":["2024-08-01T07:00:00Z"],"dc:date.created":["2024-08-24T07:00:00Z"],"dc:description.abstract":["Maintaining visibility of a person requires effective systems. Security cameras or ground robots might be ideal, but they often fail in uncontrolled or unknown environments. A single ground robot struggles to navigate and track an agent at the same time. This work addresses the challenge by developing a multi-robot system with a slow ground robot and an agile aerial robot. Three methods are evaluated: FORWARD-PF, RL-Person Following (RL), and a baseline closed-loop method. FORWARD-PF proved the most reliable, completing all nine paths and reaching targets nearly twice as fast as RL. Despite completing seven paths, RL faltered on complex tasks. The closed-loop method succeeded only 33% of the time, managing just the easiest paths. These findings underscore FORWARD-PF’s efficiency and reveal both the potential and limitations of RL, demonstrating the promise of heterogeneous multi-robot systems for person-following in unpredictable settings."],"dc:description.provenance":["Received from Author"],"dc:format":["application/pdf"],"dc:format.extent":["87 pgs","4.8 MB"],"dc:identifier":["https://digitalcommons.du.edu/etd/2490"],"dc:language":["English (eng)"],"dc:rights":["<p>Copyright is held by the author. User is responsible for all copyright compliance.</p>"],"dc:rights.holder":["Ori A. Miller"],"dc:rights.license":["all_rights_reserved"],"dc:subject":["Heterogenous robot team","Multi-robot systems","Person following","Artificial Intelligence and Robotics","Computer Engineering","Computer Sciences","Engineering","Robotics"],"dc:title":["Heterogeneous Multi-Robot Person-Following in Constrained Environments"],"thesis:degree_level":["Masters Thesis"],"thesis:degree_name":["M.S. in Computer Science"]},"updated_at":"2026-11-19T07:55:07Z"}