{"id":{"repo_id":"buffalo","oai_identifier":"oai:ubir.buffalo.edu:10477/78653"},"canonical_url":"https://search.dev.ndltd.org/etd/buffalo/oai:ubir.buffalo.edu:10477/78653","repository":{"repo_id":"buffalo","name":"Buffalo","base_url":"https://ubir.buffalo.edu/oai/request"},"display":{"title":"Neuroevolution in Control of Intelligent Systems: Benchmark Testing, Simulated and Physical Demonstrations","abstract":"M.S.","abstract_html":"M.S.","abstract_has_math":false,"creators":["Chidambaran, Sharat"],"institution":"State University of New York at Buffalo","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":["Chowdhury, Souma","Mechanical and Aerospace Engineering"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2018,"date_issued":"2018-10-26T02:57:35Z","date_published":"2018-10-26T02:57:35Z","updated_at":"2026-07-27T19:05:14Z","subjects":["mechanical engineering"],"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/10477/78653","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Chowdhury, Souma","Mechanical and Aerospace Engineering"]},{"key":"dc:creator","label":"Author","values":["Chidambaran, Sharat"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2018-10-26T02:57:35Z","2018","2018-08-16 15:15:22"]},{"key":"dc:publisher","label":"Institution","values":["State University of New York at Buffalo"]},{"key":"dc:type","label":"Dc Type","values":["Text","Thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["mechanical engineering"]}]},{"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/10477/78653"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["M.S.","A majority of Artificial Neural Network (ANN) implementations in autonomous systems use a fixed/user-prescribed network topology, leading to sub-optimal performance and low portability. The existing neuro-evolution of augmenting topology or NEAT paradigm offers a powerful alternative by allowing the network topology and the connection weights to be simultaneously optimized through an evolutionary process. In this thesis, we will discuss the use of a modified neuroevolution paradigm, inspired largely by NEAT.Most NEAT implementations allow the consideration of only a single objective. There also persists the question of how to tractably introduce topological diversification that mitigates overfitting to training scenarios. The modified neuroevolution algorithm seeks to address these shortcomings. While adopting the basic elements of NEAT, important modifications are made to the selection, speciation, and mutation processes. With the backdrop of small-robot path-planning applications, an experience-gain criterion is derived to encapsulate the amount of diverse local environment encountered by the system. This criterion facilitates the evolution of genes that support exploration, thereby seeking to generalize from a smaller set of mission scenarios than possible with performance maximization alone. The effectiveness of the single-objective (optimizing performance) and the multi-objective (optimizing performance and experience-gain) neuro-evolution approaches are evaluated on two different small-robot cases, with ANNs obtained by the multi-objective optimization observed to provide superior performance in unseen scenarios. Finally, we will also discuss and analyze the usage of this modified neuroevolution algorithm on two different, difficult benchmark problems as well as discuss its potential use in the design of a high level intelligence model of a one-of-a-kind energy autonomous robot."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Neuroevolution in Control of Intelligent Systems: Benchmark Testing, Simulated and Physical Demonstrations"]}]}],"canonical_facts":{"dc:contributor":["Chowdhury, Souma","Mechanical and Aerospace Engineering"],"dc:creator":["Chidambaran, Sharat"],"dc:date":["2018-10-26T02:57:35Z","2018","2018-08-16 15:15:22"],"dc:description":["M.S.","A majority of Artificial Neural Network (ANN) implementations in autonomous systems use a fixed/user-prescribed network topology, leading to sub-optimal performance and low portability. The existing neuro-evolution of augmenting topology or NEAT paradigm offers a powerful alternative by allowing the network topology and the connection weights to be simultaneously optimized through an evolutionary process. In this thesis, we will discuss the use of a modified neuroevolution paradigm, inspired largely by NEAT.Most NEAT implementations allow the consideration of only a single objective. There also persists the question of how to tractably introduce topological diversification that mitigates overfitting to training scenarios. The modified neuroevolution algorithm seeks to address these shortcomings. While adopting the basic elements of NEAT, important modifications are made to the selection, speciation, and mutation processes. With the backdrop of small-robot path-planning applications, an experience-gain criterion is derived to encapsulate the amount of diverse local environment encountered by the system. This criterion facilitates the evolution of genes that support exploration, thereby seeking to generalize from a smaller set of mission scenarios than possible with performance maximization alone. The effectiveness of the single-objective (optimizing performance) and the multi-objective (optimizing performance and experience-gain) neuro-evolution approaches are evaluated on two different small-robot cases, with ANNs obtained by the multi-objective optimization observed to provide superior performance in unseen scenarios. Finally, we will also discuss and analyze the usage of this modified neuroevolution algorithm on two different, difficult benchmark problems as well as discuss its potential use in the design of a high level intelligence model of a one-of-a-kind energy autonomous robot."],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/10477/78653"],"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":["mechanical engineering"],"dc:title":["Neuroevolution in Control of Intelligent Systems: Benchmark Testing, Simulated and Physical Demonstrations"],"dc:type":["Text","Thesis"]},"updated_at":"2026-07-27T19:05:14Z"}