{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/45440"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/45440","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Usage of computer vision and machine learning to solve 3D mazes","abstract":"This thesis deals with incorporating artificial intelligence into a humanoid robot by making a cognitive model of the learning process. The goal is to “teach” a specialized humanoid robot, the iCub robot, to solve any puzzle, wherein a ball of a given color would be placed at the ‘start’ position of the maze, and the robot would navigate the ball through obstacles and get the ball to the ‘finish’ position. The robot would be able to move the ball through the maze by physically tilting the base of the puzzle with its hand. In the process, the robot would utilize the most efficient way possible. If no possible path exists, the robot would not begin to solve the maze. The first approach was to test the feasibility of the project and an open loop offline-learning algorithm was used to test if the robot could physically solve a given maze. Once this proved successful, the robot was then given multiple mazes that were labeled with the best path, so that it would be able to pick up on the ideal policy on its own, as a result of supervised learning. Once sufficient training was provided, the robot was tested on multiple patterns of mazes that were not seen beforehand by the robot. The robot correctly solved all test mazes that were given to it, giving it a final accuracy rate of 100%.","abstract_html":"This thesis deals with incorporating artificial intelligence into a humanoid robot by making a cognitive model of the learning process. The goal is to “teach” a specialized humanoid robot, the iCub robot, to solve any puzzle, wherein a ball of a given color would be placed at the ‘start’ position of the maze, and the robot would navigate the ball through obstacles and get the ball to the ‘finish’ position. The robot would be able to move the ball through the maze by physically tilting the base of the puzzle with its hand. In the process, the robot would utilize the most efficient way possible. If no possible path exists, the robot would not begin to solve the maze. The first approach was to test the feasibility of the project and an open loop offline-learning algorithm was used to test if the robot could physically solve a given maze. Once this proved successful, the robot was then given multiple mazes that were labeled with the best path, so that it would be able to pick up on the ideal policy on its own, as a result of supervised learning. Once sufficient training was provided, the robot was tested on multiple patterns of mazes that were not seen beforehand by the robot. The robot correctly solved all test mazes that were given to it, giving it a final accuracy rate of 100%.","abstract_has_math":false,"creators":["Kamalnath, Vishnu Nath"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Smaragdis, Paris","Levinson, Stephen E."],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2013,"date_issued":"2013-08-22T16:40:13Z","date_published":"2013-08-22T16:40:13Z","updated_at":"2026-07-22T22:25:34Z","subjects":["Artificial Intelligence","Machine Learning","Robotics","iCub","Computer Vision","Computer Science","Pattern Recognition","learning","q-learning"],"languages":["en"],"rights":["Copyright 2013 Vishnu Nath Kamalnath"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/45440","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Smaragdis, Paris","Levinson, Stephen E."]},{"key":"dc:creator","label":"Author","values":["Kamalnath, Vishnu Nath"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2013-08-22T16:40:13Z","2013-08"]},{"key":"dc:type","label":"Dc Type","values":["text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois at Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Artificial Intelligence","Machine Learning","Robotics","iCub","Computer Vision","Computer Science","Pattern Recognition","learning","q-learning"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2013 Vishnu Nath Kamalnath"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/45440"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["This thesis deals with incorporating artificial intelligence into a humanoid robot by making a cognitive model of the learning process. The goal is to “teach” a specialized humanoid robot, the iCub robot, to solve any puzzle, wherein a ball of a given color would be placed at the ‘start’ position of the maze, and the robot would navigate the ball through obstacles and get the ball to the ‘finish’ position. The robot would be able to move the ball through the maze by physically tilting the base of the puzzle with its hand. In the process, the robot would utilize the most efficient way possible. If no possible path exists, the robot would not begin to solve the maze. The first approach was to test the feasibility of the project and an open loop offline-learning algorithm was used to test if the robot could physically solve a given maze. Once this proved successful, the robot was then given multiple mazes that were labeled with the best path, so that it would be able to pick up on the ideal policy on its own, as a result of supervised learning. Once sufficient training was provided, the robot was tested on multiple patterns of mazes that were not seen beforehand by the robot. The robot correctly solved all test mazes that were given to it, giving it a final accuracy rate of 100%.","Item withdrawn by Mark Zulauf (zulauf@illinois.edu) on 2013-06-21T16:21:49Z Item was in collections: University of Illinois Theses & Dissertations (ID: 1) No. of bitstreams: 1 Kamalnath_VishnuNath.pdf: 2203539 bytes, checksum: e2561bb968981e986967406a8a15783f (MD5)","Made available in DSpace on 2013-08-22T16:40:13Z (GMT). No. of bitstreams: 2 Vishnu Nath_Kamalnath.pdf: 2203539 bytes, checksum: e2561bb968981e986967406a8a15783f (MD5) license.txt: 4071 bytes, checksum: 2aae603e475cfa50bac7461605df661b (MD5)"]},{"key":"dc:title","label":"Title","values":["Usage of computer vision and machine learning to solve 3D mazes"]}]}],"canonical_facts":{"dc:contributor":["Smaragdis, Paris","Levinson, Stephen E."],"dc:creator":["Kamalnath, Vishnu Nath"],"dc:date":["2013-08-22T16:40:13Z","2013-08"],"dc:description":["This thesis deals with incorporating artificial intelligence into a humanoid robot by making a cognitive model of the learning process. The goal is to “teach” a specialized humanoid robot, the iCub robot, to solve any puzzle, wherein a ball of a given color would be placed at the ‘start’ position of the maze, and the robot would navigate the ball through obstacles and get the ball to the ‘finish’ position. The robot would be able to move the ball through the maze by physically tilting the base of the puzzle with its hand. In the process, the robot would utilize the most efficient way possible. If no possible path exists, the robot would not begin to solve the maze. The first approach was to test the feasibility of the project and an open loop offline-learning algorithm was used to test if the robot could physically solve a given maze. Once this proved successful, the robot was then given multiple mazes that were labeled with the best path, so that it would be able to pick up on the ideal policy on its own, as a result of supervised learning. Once sufficient training was provided, the robot was tested on multiple patterns of mazes that were not seen beforehand by the robot. The robot correctly solved all test mazes that were given to it, giving it a final accuracy rate of 100%.","Item withdrawn by Mark Zulauf (zulauf@illinois.edu) on 2013-06-21T16:21:49Z Item was in collections: University of Illinois Theses & Dissertations (ID: 1) No. of bitstreams: 1 Kamalnath_VishnuNath.pdf: 2203539 bytes, checksum: e2561bb968981e986967406a8a15783f (MD5)","Made available in DSpace on 2013-08-22T16:40:13Z (GMT). No. of bitstreams: 2 Vishnu Nath_Kamalnath.pdf: 2203539 bytes, checksum: e2561bb968981e986967406a8a15783f (MD5) license.txt: 4071 bytes, checksum: 2aae603e475cfa50bac7461605df661b (MD5)"],"dc:identifier":["http://hdl.handle.net/2142/45440"],"dc:language":["en"],"dc:rights":["Copyright 2013 Vishnu Nath Kamalnath"],"dc:subject":["Artificial Intelligence","Machine Learning","Robotics","iCub","Computer Vision","Computer Science","Pattern Recognition","learning","q-learning"],"dc:title":["Usage of computer vision and machine learning to solve 3D mazes"],"dc:type":["text"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:25:34Z"}