{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/113161"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/113161","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Vision-based dynamical systems and learning","abstract":"Nowadays, it is widely recognized that autonomous robots are “intelligent” machines, capable of performing complex tasks in a dynamical environment without explicit human intervention. Moreover, these tasks are performed while ensuring safe interactions between human and robots. Hence, ensuring Collision Avoidance is critical in designing any autonomous system. Concretely, most collision avoidance systems in mobile robots rely heavily on a computer vision machinery that provides the necessary feedback to the decision making and control units. In recent years, the advances in both machine learning algorithms and computer hardware have led to more wide application of deep neural networks in computer vision. The first part of this thesis focuses on providing methodologies for designing control strategies that guarantee collision avoidance for multi-agent systems without any information about the relative distances among the agents. The controllers are designed such that guarantee optimality of the designed activation function are provided. Finally, some examples are provided to illustrate the methodology, where some state-of-the-art activation functions are derived analytically they rely solely on the visual information, that is, times-to-collision and line-of-sight angle. These methods are particularly suitable to low-cost and/or small robotic systems that are not equipped with range measurement devices like radars and LIDARs. Furthermore, the collision avoidance is guaranteed using Lyapunov analysis type of technical arguments and illustrated using simulations. In the second part of this dissertation, a formal methodology for describing and designing activation functions in deep neural networks, is provided. The methodology is based on a precise characterization of the desired activation functions that satisfy particular criteria like circumventing vanishing or exploding gradient during training. The problem of finding desired activation functions is formulated as an infinite dimensional optimization problem, which is later relaxed to solving a partial differential equation. Furthermore, bounds that guarantee optimality of the designed activation function are provided. Finally, some examples are provided to illustrate the methodology, where some state-of-the-art activation functions are derived analytically.","abstract_html":"Nowadays, it is widely recognized that autonomous robots are “intelligent” machines, capable of performing complex tasks in a dynamical environment without explicit human intervention. Moreover, these tasks are performed while ensuring safe interactions between human and robots. Hence, ensuring Collision Avoidance is critical in designing any autonomous system. Concretely, most collision avoidance systems in mobile robots rely heavily on a computer vision machinery that provides the necessary feedback to the decision making and control units. In recent years, the advances in both machine learning algorithms and computer hardware have led to more wide application of deep neural networks in computer vision. The first part of this thesis focuses on providing methodologies for designing control strategies that guarantee collision avoidance for multi-agent systems without any information about the relative distances among the agents. The controllers are designed such that guarantee optimality of the designed activation function are provided. Finally, some examples are provided to illustrate the methodology, where some state-of-the-art activation functions are derived analytically they rely solely on the visual information, that is, times-to-collision and line-of-sight angle. These methods are particularly suitable to low-cost and/or small robotic systems that are not equipped with range measurement devices like radars and LIDARs. Furthermore, the collision avoidance is guaranteed using Lyapunov analysis type of technical arguments and illustrated using simulations. In the second part of this dissertation, a formal methodology for describing and designing activation functions in deep neural networks, is provided. The methodology is based on a precise characterization of the desired activation functions that satisfy particular criteria like circumventing vanishing or exploding gradient during training. The problem of finding desired activation functions is formulated as an infinite dimensional optimization problem, which is later relaxed to solving a partial differential equation. Furthermore, bounds that guarantee optimality of the designed activation function are provided. Finally, some examples are provided to illustrate the methodology, where some state-of-the-art activation functions are derived analytically.","abstract_has_math":false,"creators":["Amrouche, Massinissa"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"Ph.D.","degree_level":"Dissertation","degree_discipline":"Systems & Entrepreneurial Engr","degree_department":null,"school":null,"contributors":["Stipanovic, Dusan","Hovakimyan, Naira","Sreenivas, Ramavarapu","Beck, Carolyn"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2022,"date_issued":"2022-01-12T22:35:06Z","date_published":"2022-01-12T22:35:06Z","updated_at":"2026-07-22T22:24:53Z","subjects":["Control Theory, Vision Collision Avoidance, Dynamical Systems, Machine Learning, Deep neural networks"],"languages":["en"],"rights":["Copyright 2021 Massinissa Amrouche"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/113161","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Stipanovic, Dusan","Hovakimyan, Naira","Sreenivas, Ramavarapu","Beck, Carolyn"]},{"key":"dc:creator","label":"Author","values":["Amrouche, Massinissa"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2022-01-12T22:35:06Z","2024-01-12T22:35:30Z","2021-07-12","2021-08"]},{"key":"dc:type","label":"Dc Type","values":["text","Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Systems & Entrepreneurial Engr"]},{"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":["Control Theory, Vision Collision Avoidance, Dynamical Systems, Machine Learning, Deep neural networks"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2021 Massinissa Amrouche"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/113161"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Nowadays, it is widely recognized that autonomous robots are “intelligent” machines, capable of performing complex tasks in a dynamical environment without explicit human intervention. Moreover, these tasks are performed while ensuring safe interactions between human and robots. Hence, ensuring Collision Avoidance is critical in designing any autonomous system. Concretely, most collision avoidance systems in mobile robots rely heavily on a computer vision machinery that provides the necessary feedback to the decision making and control units. In recent years, the advances in both machine learning algorithms and computer hardware have led to more wide application of deep neural networks in computer vision. The first part of this thesis focuses on providing methodologies for designing control strategies that guarantee collision avoidance for multi-agent systems without any information about the relative distances among the agents. The controllers are designed such that guarantee optimality of the designed activation function are provided. Finally, some examples are provided to illustrate the methodology, where some state-of-the-art activation functions are derived analytically they rely solely on the visual information, that is, times-to-collision and line-of-sight angle. These methods are particularly suitable to low-cost and/or small robotic systems that are not equipped with range measurement devices like radars and LIDARs. Furthermore, the collision avoidance is guaranteed using Lyapunov analysis type of technical arguments and illustrated using simulations. In the second part of this dissertation, a formal methodology for describing and designing activation functions in deep neural networks, is provided. The methodology is based on a precise characterization of the desired activation functions that satisfy particular criteria like circumventing vanishing or exploding gradient during training. The problem of finding desired activation functions is formulated as an infinite dimensional optimization problem, which is later relaxed to solving a partial differential equation. Furthermore, bounds that guarantee optimality of the designed activation function are provided. Finally, some examples are provided to illustrate the methodology, where some state-of-the-art activation functions are derived analytically.","Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2023-08-01","The student, Massinissa Amrouche, accepted the attached license on 2021-07-08 at 22:14.","The student, Massinissa Amrouche, submitted this Dissertation for approval on 2021-07-08 at 22:22.","This Dissertation was approved for publication on 2021-07-12 at 15:51.","DSpace SAF Submission Ingestion Package generated from Vireo submission #16815 on 2022-01-12 at 12:54:03","Made available in DSpace on 2022-01-12T22:35:06Z (GMT). No. of bitstreams: 3 AMROUCHE-DISSERTATION-2021.pdf: 7213187 bytes, checksum: f24f04c946bc76f284cb9034a458fd22 (MD5) LICENSE.txt: 4211 bytes, checksum: a9a83369a4f495463a16386604f2acf4 (MD5) PROQUEST_LICENSE.txt: 4557 bytes, checksum: 03ba36c221662caec4e7b5266744afed (MD5) Previous issue date: 2021-07-12","Embargo set by: Seth Robbins for item 121087 Lift date: 2024-01-12T22:35:30Z Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system","Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system","U of I Only"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Vision-based dynamical systems and learning"]}]}],"canonical_facts":{"dc:contributor":["Stipanovic, Dusan","Hovakimyan, Naira","Sreenivas, Ramavarapu","Beck, Carolyn"],"dc:creator":["Amrouche, Massinissa"],"dc:date":["2022-01-12T22:35:06Z","2024-01-12T22:35:30Z","2021-07-12","2021-08"],"dc:description":["Nowadays, it is widely recognized that autonomous robots are “intelligent” machines, capable of performing complex tasks in a dynamical environment without explicit human intervention. Moreover, these tasks are performed while ensuring safe interactions between human and robots. Hence, ensuring Collision Avoidance is critical in designing any autonomous system. Concretely, most collision avoidance systems in mobile robots rely heavily on a computer vision machinery that provides the necessary feedback to the decision making and control units. In recent years, the advances in both machine learning algorithms and computer hardware have led to more wide application of deep neural networks in computer vision. The first part of this thesis focuses on providing methodologies for designing control strategies that guarantee collision avoidance for multi-agent systems without any information about the relative distances among the agents. The controllers are designed such that guarantee optimality of the designed activation function are provided. Finally, some examples are provided to illustrate the methodology, where some state-of-the-art activation functions are derived analytically they rely solely on the visual information, that is, times-to-collision and line-of-sight angle. These methods are particularly suitable to low-cost and/or small robotic systems that are not equipped with range measurement devices like radars and LIDARs. Furthermore, the collision avoidance is guaranteed using Lyapunov analysis type of technical arguments and illustrated using simulations. In the second part of this dissertation, a formal methodology for describing and designing activation functions in deep neural networks, is provided. The methodology is based on a precise characterization of the desired activation functions that satisfy particular criteria like circumventing vanishing or exploding gradient during training. The problem of finding desired activation functions is formulated as an infinite dimensional optimization problem, which is later relaxed to solving a partial differential equation. Furthermore, bounds that guarantee optimality of the designed activation function are provided. Finally, some examples are provided to illustrate the methodology, where some state-of-the-art activation functions are derived analytically.","Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2023-08-01","The student, Massinissa Amrouche, accepted the attached license on 2021-07-08 at 22:14.","The student, Massinissa Amrouche, submitted this Dissertation for approval on 2021-07-08 at 22:22.","This Dissertation was approved for publication on 2021-07-12 at 15:51.","DSpace SAF Submission Ingestion Package generated from Vireo submission #16815 on 2022-01-12 at 12:54:03","Made available in DSpace on 2022-01-12T22:35:06Z (GMT). No. of bitstreams: 3 AMROUCHE-DISSERTATION-2021.pdf: 7213187 bytes, checksum: f24f04c946bc76f284cb9034a458fd22 (MD5) LICENSE.txt: 4211 bytes, checksum: a9a83369a4f495463a16386604f2acf4 (MD5) PROQUEST_LICENSE.txt: 4557 bytes, checksum: 03ba36c221662caec4e7b5266744afed (MD5) Previous issue date: 2021-07-12","Embargo set by: Seth Robbins for item 121087 Lift date: 2024-01-12T22:35:30Z Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system","Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system","U of I Only"],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/2142/113161"],"dc:language":["en"],"dc:rights":["Copyright 2021 Massinissa Amrouche"],"dc:subject":["Control Theory, Vision Collision Avoidance, Dynamical Systems, Machine Learning, Deep neural networks"],"dc:title":["Vision-based dynamical systems and learning"],"dc:type":["text","Thesis"],"thesis:degree_discipline":["Systems & Entrepreneurial Engr"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Ph.D."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:24:53Z"}