{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/80897"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/80897","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Hmm-Based Semantic Learning for a Mobile Robot","abstract":"We are developing a intelligent robot and attempting to teach it language. While there are many aspects of this research, for the purposes of this dissertation the most important are the following ideas. Language is primarily based on semantics, not syntax, which is the focus in speech recognition research these days. To truly learn meaning, a language engine cannot simply be a computer program running on a desktop computer analyzing speech. It must be part of a more general, embodied intelligent system, one capable of using associative learning to form concepts from the perception of experiences in the world, and further capable of manipulating those concepts symbolically. This dissertation explores the use of hidden Markov models (HMMs) in this capacity. HMMs are capable of automatically learning and extracting the underlying structure of continuous-valued inputs and representing that structure in the states of the model. These states can then be treated as symbolic representations of the inputs. We show how a model consisting of a cascade of HMMs can be embedded in a small mobile robot and used to learn correlations among sensory inputs to create symbolic concepts, which can eventually be manipulated linguistically and used for decision making.","abstract_html":"We are developing a intelligent robot and attempting to teach it language. While there are many aspects of this research, for the purposes of this dissertation the most important are the following ideas. Language is primarily based on semantics, not syntax, which is the focus in speech recognition research these days. To truly learn meaning, a language engine cannot simply be a computer program running on a desktop computer analyzing speech. It must be part of a more general, embodied intelligent system, one capable of using associative learning to form concepts from the perception of experiences in the world, and further capable of manipulating those concepts symbolically. This dissertation explores the use of hidden Markov models (HMMs) in this capacity. HMMs are capable of automatically learning and extracting the underlying structure of continuous-valued inputs and representing that structure in the states of the model. These states can then be treated as symbolic representations of the inputs. We show how a model consisting of a cascade of HMMs can be embedded in a small mobile robot and used to learn correlations among sensory inputs to create symbolic concepts, which can eventually be manipulated linguistically and used for decision making.","abstract_has_math":false,"creators":["Squire, Kevin Michael"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"Ph.D.","degree_level":"Dissertation","degree_discipline":"Electrical Engineering","degree_department":null,"school":null,"contributors":["Levinson, Stephen E."],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2015,"date_issued":"2015-09-25T20:08:42Z","date_published":"2015-09-25T20:08:42Z","updated_at":"2026-07-22T22:26:15Z","subjects":["Artificial Intelligence"],"languages":["eng"],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["(MiAaPQ)AAI3160956"],"render_values":[{"text":"(MiAaPQ)AAI3160956","href":null,"code":true}]}]},"links":{"outbound_url":"http://hdl.handle.net/2142/80897","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Levinson, Stephen E."]},{"key":"dc:creator","label":"Author","values":["Squire, Kevin Michael"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2015-09-25T20:08:42Z","10000-01-01","2004"]},{"key":"dc:type","label":"Dc Type","values":["text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Dissertation"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Ph.D."]},{"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"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["eng"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/80897","(MiAaPQ)AAI3160956"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["We are developing a intelligent robot and attempting to teach it language. While there are many aspects of this research, for the purposes of this dissertation the most important are the following ideas. Language is primarily based on semantics, not syntax, which is the focus in speech recognition research these days. To truly learn meaning, a language engine cannot simply be a computer program running on a desktop computer analyzing speech. It must be part of a more general, embodied intelligent system, one capable of using associative learning to form concepts from the perception of experiences in the world, and further capable of manipulating those concepts symbolically. This dissertation explores the use of hidden Markov models (HMMs) in this capacity. HMMs are capable of automatically learning and extracting the underlying structure of continuous-valued inputs and representing that structure in the states of the model. These states can then be treated as symbolic representations of the inputs. We show how a model consisting of a cascade of HMMs can be embedded in a small mobile robot and used to learn correlations among sensory inputs to create symbolic concepts, which can eventually be manipulated linguistically and used for decision making.","Made available in DSpace on 2015-09-25T20:08:42Z (GMT). No. of bitstreams: 2 license.txt: 4848 bytes, checksum: 96035ab3f5e1c23cc7138a224ce498bd (MD5) 3160956.pdf: 8331014 bytes, checksum: e4f253185ccee21bf9e886d9392cda63 (MD5) Previous issue date: 2004","Embargo set by: Seth Robbins for item 82179 Lift date: Forever Reason: Restricted to the U of I community idenfinitely during batch ingest of legacy ETDs","Restricted to the U of I community idenfinitely during batch ingest of legacy ETDs","U of I Only","155 p.","Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 2004."]},{"key":"dc:title","label":"Title","values":["Hmm-Based Semantic Learning for a Mobile Robot"]}]}],"canonical_facts":{"dc:contributor":["Levinson, Stephen E."],"dc:creator":["Squire, Kevin Michael"],"dc:date":["2015-09-25T20:08:42Z","10000-01-01","2004"],"dc:description":["We are developing a intelligent robot and attempting to teach it language. While there are many aspects of this research, for the purposes of this dissertation the most important are the following ideas. Language is primarily based on semantics, not syntax, which is the focus in speech recognition research these days. To truly learn meaning, a language engine cannot simply be a computer program running on a desktop computer analyzing speech. It must be part of a more general, embodied intelligent system, one capable of using associative learning to form concepts from the perception of experiences in the world, and further capable of manipulating those concepts symbolically. This dissertation explores the use of hidden Markov models (HMMs) in this capacity. HMMs are capable of automatically learning and extracting the underlying structure of continuous-valued inputs and representing that structure in the states of the model. These states can then be treated as symbolic representations of the inputs. We show how a model consisting of a cascade of HMMs can be embedded in a small mobile robot and used to learn correlations among sensory inputs to create symbolic concepts, which can eventually be manipulated linguistically and used for decision making.","Made available in DSpace on 2015-09-25T20:08:42Z (GMT). No. of bitstreams: 2 license.txt: 4848 bytes, checksum: 96035ab3f5e1c23cc7138a224ce498bd (MD5) 3160956.pdf: 8331014 bytes, checksum: e4f253185ccee21bf9e886d9392cda63 (MD5) Previous issue date: 2004","Embargo set by: Seth Robbins for item 82179 Lift date: Forever Reason: Restricted to the U of I community idenfinitely during batch ingest of legacy ETDs","Restricted to the U of I community idenfinitely during batch ingest of legacy ETDs","U of I Only","155 p.","Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 2004."],"dc:identifier":["http://hdl.handle.net/2142/80897","(MiAaPQ)AAI3160956"],"dc:language":["eng"],"dc:subject":["Artificial Intelligence"],"dc:title":["Hmm-Based Semantic Learning for a Mobile Robot"],"dc:type":["text"],"thesis:degree_discipline":["Electrical Engineering"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Ph.D."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:26:15Z"}