{"id":{"repo_id":"buffalo","oai_identifier":"oai:ubir.buffalo.edu:10477/80956"},"canonical_url":"https://search.dev.ndltd.org/etd/buffalo/oai:ubir.buffalo.edu:10477/80956","repository":{"repo_id":"buffalo","name":"Buffalo","base_url":"https://ubir.buffalo.edu/oai/request"},"display":{"title":"Autonomous Adaptive Modification of Unstructured Environments","abstract":"Ph.D.","abstract_html":"Ph.D.","abstract_has_math":false,"creators":["Saboia da Silva, Maira; 0000-0002-6277-1703"],"institution":"State University of New York at Buffalo","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":["Napp, Nils","Computer Science and Engineering"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2019,"date_issued":"2019-10-29T16:48:29Z","date_published":"2019-10-29T16:48:29Z","updated_at":"2026-07-27T19:05:28Z","subjects":["robotics"],"languages":["eng"],"rights":["Users of works found in University at Buffalo Institutional Repository (UBIR) are responsible for identifying and contacting the copyright owner for permission to reuse. University at Buffalo Libraries do not manage rights for copyright-protected works and cannot assist with permissions.","Copyright retained by author."],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/10477/80956","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Napp, Nils","Computer Science and Engineering"]},{"key":"dc:creator","label":"Author","values":["Saboia da Silva, Maira; 0000-0002-6277-1703"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2019-10-29T16:48:29Z","2019","2019-08-09 23:21:09"]},{"key":"dc:publisher","label":"Institution","values":["State University of New York at Buffalo"]},{"key":"dc:type","label":"Dc Type","values":["Text","Dissertation"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["robotics"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["Users of works found in University at Buffalo Institutional Repository (UBIR) are responsible for identifying and contacting the copyright owner for permission to reuse. University at Buffalo Libraries do not manage rights for copyright-protected works and cannot assist with permissions.","Copyright retained by author."]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/10477/80956"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Ph.D.","Robotic systems with construction capabilities can be used to support humans in remote and hostile environments, potentially increasing safety, reducing costs and streamlining the process. In this thesis, we show that by initiating environmental modification as a function of a structure's utility, we endow robots with the ability to act in an adaptive and robust way, building complex structures, driven by the continuous assessment of its environment. We call \"environment modification\" a type of construction in which assembly actions are adjusted to ensure that specific conditions are maintained rather than achieving a specific final shape of the structure, similar to the many biological construction systems.We designed a robotic system whose focus is on building motion support structures that enable agents to operate in areas where navigation is needed. The structure encoding, motion constraints, and the set of legal modifications are all linked by a single abstract model, and while factors such as limited perception, irregular building materials and uncertainty in the robot's actions can lead to different structure shapes, they are functionally equivalent.Our physical implementation is designed to resemble real-world operations in irregular settings. To simulate unstructured environments, we add stones and concrete rubble from an earthquake testing center. To simulate found construction materials, we use a mixture of irregular building material of various sizes and physical properties, such as compliant bags and rigid foam blocks. Understanding the benefits and limitations of each material type in terms of modification resolution, material usage efficiency, and structure stability allows the construction procedure to adaptively choose the most appropriate material type to use for each assembly action. The system can operate autonomously over many hours, with robots locating, choosing and depositing different building materials, to achieve and maintain mobility."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Autonomous Adaptive Modification of Unstructured Environments"]}]}],"canonical_facts":{"dc:contributor":["Napp, Nils","Computer Science and Engineering"],"dc:creator":["Saboia da Silva, Maira; 0000-0002-6277-1703"],"dc:date":["2019-10-29T16:48:29Z","2019","2019-08-09 23:21:09"],"dc:description":["Ph.D.","Robotic systems with construction capabilities can be used to support humans in remote and hostile environments, potentially increasing safety, reducing costs and streamlining the process. In this thesis, we show that by initiating environmental modification as a function of a structure's utility, we endow robots with the ability to act in an adaptive and robust way, building complex structures, driven by the continuous assessment of its environment. We call \"environment modification\" a type of construction in which assembly actions are adjusted to ensure that specific conditions are maintained rather than achieving a specific final shape of the structure, similar to the many biological construction systems.We designed a robotic system whose focus is on building motion support structures that enable agents to operate in areas where navigation is needed. The structure encoding, motion constraints, and the set of legal modifications are all linked by a single abstract model, and while factors such as limited perception, irregular building materials and uncertainty in the robot's actions can lead to different structure shapes, they are functionally equivalent.Our physical implementation is designed to resemble real-world operations in irregular settings. To simulate unstructured environments, we add stones and concrete rubble from an earthquake testing center. To simulate found construction materials, we use a mixture of irregular building material of various sizes and physical properties, such as compliant bags and rigid foam blocks. Understanding the benefits and limitations of each material type in terms of modification resolution, material usage efficiency, and structure stability allows the construction procedure to adaptively choose the most appropriate material type to use for each assembly action. The system can operate autonomously over many hours, with robots locating, choosing and depositing different building materials, to achieve and maintain mobility."],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/10477/80956"],"dc:language":["eng"],"dc:publisher":["State University of New York at Buffalo"],"dc:rights":["Users of works found in University at Buffalo Institutional Repository (UBIR) are responsible for identifying and contacting the copyright owner for permission to reuse. University at Buffalo Libraries do not manage rights for copyright-protected works and cannot assist with permissions.","Copyright retained by author."],"dc:subject":["robotics"],"dc:title":["Autonomous Adaptive Modification of Unstructured Environments"],"dc:type":["Text","Dissertation"]},"updated_at":"2026-07-27T19:05:28Z"}