{"id":{"repo_id":"usf","oai_identifier":"oai:digitalcommons.usf.edu:etd-10671"},"canonical_url":"https://search.ndltd.org/etd/usf/oai:digitalcommons.usf.edu:etd-10671","repository":{"repo_id":"usf","name":"University of South Florida","base_url":"https://digitalcommons.usf.edu/do/oai/"},"display":{"title":"Predicting the Number of Objects in a Robotic Grasp","abstract":"Picking up the desired number of objects at once from a pile is still very difficult to dofor a robot. The main challenge is predicting the number of objects in the grasp. This thesis describes several deep-learning-based prediction models that predict the number of objects in the grasp of a Barrett hand using the tactile sensors on its fingers and palm and its joint angles and torque (strain gauge) readings. The deep learning models include various architectures using autoencoders and vision transformers. We evaluated the models with a dataset of grasping 0, 1, 2, 3, and 4 spheres. Then, we train the model using the dataset generated from the simulation system and use it on real-system data through transfer learning. Finally, we predict the number of objects a robot might have grasped before lifting the hand. We achieved an overall accuracy of 79% on the simulation and 60% on the real system dataset.","abstract_html":"Picking up the desired number of objects at once from a pile is still very difficult to dofor a robot. The main challenge is predicting the number of objects in the grasp. This thesis describes several deep-learning-based prediction models that predict the number of objects in the grasp of a Barrett hand using the tactile sensors on its fingers and palm and its joint angles and torque (strain gauge) readings. The deep learning models include various architectures using autoencoders and vision transformers. We evaluated the models with a dataset of grasping 0, 1, 2, 3, and 4 spheres. Then, we train the model using the dataset generated from the simulation system and use it on real-system data through transfer learning. Finally, we predict the number of objects a robot might have grasped before lifting the hand. We achieved an overall accuracy of 79% on the simulation and 60% on the real system dataset.","abstract_has_math":false,"creators":["Tamrakar, Utkarsh"],"institution":"University of South Florida","degree_name":"MS in Computer Science (M.S.C.S.)","degree_level":"Thesis","degree_discipline":"Computer Science and Engineering","degree_department":null,"school":null,"contributors":["Yu Sun, Ph.D.","Shaun Canavan, Ph.D.","Paul A. Rosen, Ph.D."],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2022,"date_issued":"2022-03-18T07:00:00Z","date_published":"2022-03-18T07:00:00Z","updated_at":"2026-11-19T08:47:18Z","subjects":["Multi-Object Grasping","Prediction","Robotic Grasping","Tactile Sensing","Computer Sciences"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://digitalcommons.usf.edu/etd/9474","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://digitalcommons.usf.edu/etd/9474","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-10671","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Yu Sun, Ph.D.","Shaun Canavan, Ph.D.","Paul A. Rosen, Ph.D."]},{"key":"dc:creator","label":"Author","values":["Tamrakar, Utkarsh"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2022-03-18T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science and Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis","M.S.C.S."]},{"key":"thesis:degree_name","label":"Degree Name","values":["MS in Computer Science (M.S.C.S.)"]},{"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":["Multi-Object Grasping","Prediction","Robotic Grasping","Tactile Sensing","Computer Sciences"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.usf.edu/etd/9474"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Picking up the desired number of objects at once from a pile is still very difficult to dofor a robot. The main challenge is predicting the number of objects in the grasp. This thesis describes several deep-learning-based prediction models that predict the number of objects in the grasp of a Barrett hand using the tactile sensors on its fingers and palm and its joint angles and torque (strain gauge) readings. The deep learning models include various architectures using autoencoders and vision transformers. We evaluated the models with a dataset of grasping 0, 1, 2, 3, and 4 spheres. Then, we train the model using the dataset generated from the simulation system and use it on real-system data through transfer learning. Finally, we predict the number of objects a robot might have grasped before lifting the hand. We achieved an overall accuracy of 79% on the simulation and 60% on the real system dataset."]},{"key":"dc:title","label":"Title","values":["Predicting the Number of Objects in a Robotic Grasp"]}]}],"canonical_facts":{"dc:contributor":["Yu Sun, Ph.D.","Shaun Canavan, Ph.D.","Paul A. Rosen, Ph.D."],"dc:creator":["Tamrakar, Utkarsh"],"dc:date":["2022-03-18T07:00:00Z"],"dc:description":["Picking up the desired number of objects at once from a pile is still very difficult to dofor a robot. The main challenge is predicting the number of objects in the grasp. This thesis describes several deep-learning-based prediction models that predict the number of objects in the grasp of a Barrett hand using the tactile sensors on its fingers and palm and its joint angles and torque (strain gauge) readings. The deep learning models include various architectures using autoencoders and vision transformers. We evaluated the models with a dataset of grasping 0, 1, 2, 3, and 4 spheres. Then, we train the model using the dataset generated from the simulation system and use it on real-system data through transfer learning. Finally, we predict the number of objects a robot might have grasped before lifting the hand. We achieved an overall accuracy of 79% on the simulation and 60% on the real system dataset."],"dc:identifier":["https://digitalcommons.usf.edu/etd/9474"],"dc:subject":["Multi-Object Grasping","Prediction","Robotic Grasping","Tactile Sensing","Computer Sciences"],"dc:title":["Predicting the Number of Objects in a Robotic Grasp"],"thesis:degree_discipline":["Computer Science and Engineering"],"thesis:degree_level":["Thesis","M.S.C.S."],"thesis:degree_name":["MS in Computer Science (M.S.C.S.)"],"thesis:institution_name":["University of South Florida"]},"updated_at":"2026-11-19T08:47:18Z"}