{"id":{"repo_id":"usf","oai_identifier":"oai:digitalcommons.usf.edu:etd-8085"},"canonical_url":"https://search.ndltd.org/etd/usf/oai:digitalcommons.usf.edu:etd-8085","repository":{"repo_id":"usf","name":"University of South Florida","base_url":"https://digitalcommons.usf.edu/do/oai/"},"display":{"title":"Multi-Scale Spatial Cognition Models and Bio-Inspired Robot Navigation","abstract":"The rodent navigation system has been the focus of study for over a century. Discoveries made lately have provided insight on the inner workings of this system. Since then, computational approaches have been used to test hypothesis, as well as to improve robotics navigation and learning by taking inspiration on the rodent navigation system. This dissertation focuses on the study of the multi-scale representation of the rat’s current location found in the rat hippocampus. It first introduces a model that uses these different scales in the Morris maze task to show their advantages. The generalization power of larger scales of representation are shown to allow for the learning of more coherent and complete policies faster. Based on this model, a robotics navigation learning system is presented and compared to an existing algorithm on the taxi driver problem. The algorithm outperforms a canonical Q-Learning algorithm, learning the task faster. It is also shown to work in a continuous environment, making it suitable for a real robotics application. A novel task is also introduced and modeled, with the aim of providing further insight to an ongoing discussion over the involvement of the temporal portion of the hippocampus in navigation. The model is able to reproduce the results obtained with real rats and generates a set of empirically verifiable predictions. Finally, a novel multi-query path planning system is introduced, inspired in the way rodents represent location, their way of storing a topological model of the environment and how they use it to plan future routes. The algorithm is able to improve the routes in the second run, without disrupting the robustness of the underlying navigation system.","abstract_html":"The rodent navigation system has been the focus of study for over a century. Discoveries made lately have provided insight on the inner workings of this system. Since then, computational approaches have been used to test hypothesis, as well as to improve robotics navigation and learning by taking inspiration on the rodent navigation system. This dissertation focuses on the study of the multi-scale representation of the rat’s current location found in the rat hippocampus. It first introduces a model that uses these different scales in the Morris maze task to show their advantages. The generalization power of larger scales of representation are shown to allow for the learning of more coherent and complete policies faster. Based on this model, a robotics navigation learning system is presented and compared to an existing algorithm on the taxi driver problem. The algorithm outperforms a canonical Q-Learning algorithm, learning the task faster. It is also shown to work in a continuous environment, making it suitable for a real robotics application. A novel task is also introduced and modeled, with the aim of providing further insight to an ongoing discussion over the involvement of the temporal portion of the hippocampus in navigation. The model is able to reproduce the results obtained with real rats and generates a set of empirically verifiable predictions. Finally, a novel multi-query path planning system is introduced, inspired in the way rodents represent location, their way of storing a topological model of the environment and how they use it to plan future routes. The algorithm is able to improve the routes in the second run, without disrupting the robustness of the underlying navigation system.","abstract_has_math":false,"creators":["Llofriu Alonso, Martin I."],"institution":"University of South Florida","degree_name":"Doctor of Philosophy (Ph.D.)","degree_level":"Dissertation","degree_discipline":"Computer Science and Engineering","degree_department":null,"school":null,"contributors":["Alfredo Weitzenfeld, Ph.D.","Yu Sun, Ph.D.","David Diamond, Ph.D.","Miguel Labrador, Ph.D.","Wilfrido Moreno, Ph.D."],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2017,"date_issued":"2017-06-15T07:00:00Z","date_published":"2017-06-15T07:00:00Z","updated_at":"2026-11-19T08:43:17Z","subjects":["Reinforcement Learning","Hippocampus","NeuroRobotics","Path Planning","Long-Term Operation","Neurosciences","Robotics"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://digitalcommons.usf.edu/etd/6888","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://digitalcommons.usf.edu/etd/6888","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.usf.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Adigitalcommons.usf.edu%3Aetd-8085","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Alfredo Weitzenfeld, Ph.D.","Yu Sun, Ph.D.","David Diamond, Ph.D.","Miguel Labrador, Ph.D.","Wilfrido Moreno, Ph.D."]},{"key":"dc:creator","label":"Author","values":["Llofriu Alonso, Martin I."]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2017-06-15T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science and Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Dissertation","Ph.D."]},{"key":"thesis:degree_name","label":"Degree Name","values":["Doctor of Philosophy (Ph.D.)"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of South Florida"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Reinforcement Learning","Hippocampus","NeuroRobotics","Path Planning","Long-Term Operation","Neurosciences","Robotics"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.usf.edu/etd/6888"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["The rodent navigation system has been the focus of study for over a century. Discoveries made lately have provided insight on the inner workings of this system. Since then, computational approaches have been used to test hypothesis, as well as to improve robotics navigation and learning by taking inspiration on the rodent navigation system. This dissertation focuses on the study of the multi-scale representation of the rat’s current location found in the rat hippocampus. It first introduces a model that uses these different scales in the Morris maze task to show their advantages. The generalization power of larger scales of representation are shown to allow for the learning of more coherent and complete policies faster. Based on this model, a robotics navigation learning system is presented and compared to an existing algorithm on the taxi driver problem. The algorithm outperforms a canonical Q-Learning algorithm, learning the task faster. It is also shown to work in a continuous environment, making it suitable for a real robotics application. A novel task is also introduced and modeled, with the aim of providing further insight to an ongoing discussion over the involvement of the temporal portion of the hippocampus in navigation. The model is able to reproduce the results obtained with real rats and generates a set of empirically verifiable predictions. Finally, a novel multi-query path planning system is introduced, inspired in the way rodents represent location, their way of storing a topological model of the environment and how they use it to plan future routes. The algorithm is able to improve the routes in the second run, without disrupting the robustness of the underlying navigation system."]},{"key":"dc:title","label":"Title","values":["Multi-Scale Spatial Cognition Models and Bio-Inspired Robot Navigation"]}]}],"canonical_facts":{"dc:contributor":["Alfredo Weitzenfeld, Ph.D.","Yu Sun, Ph.D.","David Diamond, Ph.D.","Miguel Labrador, Ph.D.","Wilfrido Moreno, Ph.D."],"dc:creator":["Llofriu Alonso, Martin I."],"dc:date":["2017-06-15T07:00:00Z"],"dc:description":["The rodent navigation system has been the focus of study for over a century. Discoveries made lately have provided insight on the inner workings of this system. Since then, computational approaches have been used to test hypothesis, as well as to improve robotics navigation and learning by taking inspiration on the rodent navigation system. This dissertation focuses on the study of the multi-scale representation of the rat’s current location found in the rat hippocampus. It first introduces a model that uses these different scales in the Morris maze task to show their advantages. The generalization power of larger scales of representation are shown to allow for the learning of more coherent and complete policies faster. Based on this model, a robotics navigation learning system is presented and compared to an existing algorithm on the taxi driver problem. The algorithm outperforms a canonical Q-Learning algorithm, learning the task faster. It is also shown to work in a continuous environment, making it suitable for a real robotics application. A novel task is also introduced and modeled, with the aim of providing further insight to an ongoing discussion over the involvement of the temporal portion of the hippocampus in navigation. The model is able to reproduce the results obtained with real rats and generates a set of empirically verifiable predictions. Finally, a novel multi-query path planning system is introduced, inspired in the way rodents represent location, their way of storing a topological model of the environment and how they use it to plan future routes. The algorithm is able to improve the routes in the second run, without disrupting the robustness of the underlying navigation system."],"dc:identifier":["https://digitalcommons.usf.edu/etd/6888"],"dc:subject":["Reinforcement Learning","Hippocampus","NeuroRobotics","Path Planning","Long-Term Operation","Neurosciences","Robotics"],"dc:title":["Multi-Scale Spatial Cognition Models and Bio-Inspired Robot Navigation"],"thesis:degree_discipline":["Computer Science and Engineering"],"thesis:degree_level":["Dissertation","Ph.D."],"thesis:degree_name":["Doctor of Philosophy (Ph.D.)"],"thesis:institution_name":["University of South Florida"]},"updated_at":"2026-11-19T08:43:17Z"}