{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/145058"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/145058","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Success Classification for Object Navigation","abstract":"Object navigation is the embodied task of navigating to an instance of a specified object in unseen environments. Previous work has made impressive progress on the problem, but there remains much room for improvement with current state-of-the-art methods reaching a success rate of less than one in three. In this work, we evaluate a state-of-the-art approach, identifying false positives in object detection as the main point of failure. We propose introducing a new module to verify success when the agent attempts to stop. We introduce a learning-based classifier that learns and compares embeddings for visual observations and object categories and find that it works well at predicting success, outperforming both naive baselines and a heuristic­-based classifier. We also find no improvement when using a ensemble model for semantic segmentation, although we believe there is more to be tested before arriving at a conclusive judgement.","abstract_html":"Object navigation is the embodied task of navigating to an instance of a specified object in unseen environments. Previous work has made impressive progress on the problem, but there remains much room for improvement with current state-of-the-art methods reaching a success rate of less than one in three. In this work, we evaluate a state-of-the-art approach, identifying false positives in object detection as the main point of failure. We propose introducing a new module to verify success when the agent attempts to stop. We introduce a learning-based classifier that learns and compares embeddings for visual observations and object categories and find that it works well at predicting success, outperforming both naive baselines and a heuristic­-based classifier. We also find no improvement when using a ensemble model for semantic segmentation, although we believe there is more to be tested before arriving at a conclusive judgement.","abstract_has_math":false,"creators":["Yue, Albert"],"institution":"Massachusetts Institute of Technology","degree_name":"Master","degree_level":null,"degree_discipline":null,"degree_department":"Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science","school":null,"contributors":[],"advisors":["Agrawal, Pulkit"],"committee_chairs":[],"committee_members":[],"year":2022,"date_issued":"2022-05","date_published":"2022-05","updated_at":"2026-07-22T22:22:25Z","subjects":[],"languages":[],"rights":["In Copyright - Educational Use Permitted","Copyright MIT"],"rights_urls":["http://rightsstatements.org/page/InC-EDU/1.0/"],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1721.1/145058","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Agrawal, Pulkit"]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"]},{"key":"dc:creator","label":"Author","values":["Yue, Albert"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2022-08-29T16:30:07Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2022-08-29T16:30:07Z"]},{"key":"dc:date.issued","label":"Date","values":["2022-05"]},{"key":"dc:publisher","label":"Institution","values":["Massachusetts Institute of Technology"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master","Master of Engineering in Electrical Engineering and Computer Science"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["In Copyright - Educational Use Permitted","Copyright MIT"]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://rightsstatements.org/page/InC-EDU/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1721.1/145058"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Object navigation is the embodied task of navigating to an instance of a specified object in unseen environments. Previous work has made impressive progress on the problem, but there remains much room for improvement with current state-of-the-art methods reaching a success rate of less than one in three. In this work, we evaluate a state-of-the-art approach, identifying false positives in object detection as the main point of failure. We propose introducing a new module to verify success when the agent attempts to stop. We introduce a learning-based classifier that learns and compares embeddings for visual observations and object categories and find that it works well at predicting success, outperforming both naive baselines and a heuristic­-based classifier. We also find no improvement when using a ensemble model for semantic segmentation, although we believe there is more to be tested before arriving at a conclusive judgement."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["M.Eng."]},{"key":"dc:title","label":"Title","values":["Success Classification for Object Navigation"]}]}],"canonical_facts":{"dc:contributor.advisor":["Agrawal, Pulkit"],"dc:contributor.department":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"],"dc:creator":["Yue, Albert"],"dc:date.accessioned":["2022-08-29T16:30:07Z"],"dc:date.available":["2022-08-29T16:30:07Z"],"dc:date.issued":["2022-05"],"dc:description.abstract":["Object navigation is the embodied task of navigating to an instance of a specified object in unseen environments. Previous work has made impressive progress on the problem, but there remains much room for improvement with current state-of-the-art methods reaching a success rate of less than one in three. In this work, we evaluate a state-of-the-art approach, identifying false positives in object detection as the main point of failure. We propose introducing a new module to verify success when the agent attempts to stop. We introduce a learning-based classifier that learns and compares embeddings for visual observations and object categories and find that it works well at predicting success, outperforming both naive baselines and a heuristic­-based classifier. We also find no improvement when using a ensemble model for semantic segmentation, although we believe there is more to be tested before arriving at a conclusive judgement."],"dc:description.degree":["M.Eng."],"dc:identifier.uri":["https://hdl.handle.net/1721.1/145058"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["In Copyright - Educational Use Permitted","Copyright MIT"],"dc:rights.uri":["http://rightsstatements.org/page/InC-EDU/1.0/"],"dc:title":["Success Classification for Object Navigation"],"dc:type":["Thesis"],"thesis:degree_name":["Master","Master of Engineering in Electrical Engineering and Computer Science"]},"updated_at":"2026-07-22T22:22:25Z"}