{"id":{"repo_id":"msu","oai_identifier":"oai:d.lib.msu.edu:etd_53372"},"canonical_url":"https://search.ndltd.org/etd/msu/oai:d.lib.msu.edu:etd_53372","repository":{"repo_id":"msu","name":"Michigan State University","base_url":"https://d.lib.msu.edu/oai"},"display":{"title":"Data-driven Modeling, Control, and State Estimation : Advancements and Applications for Soft Robotic Systems","abstract":"Thesis (Ph.D.)--Michigan State University. Mechanical Engineering - Doctor of Philosophy, 2026","abstract_html":"Thesis (Ph.D.)--Michigan State University. Mechanical Engineering - Doctor of Philosophy, 2026","abstract_has_math":false,"creators":["Wang, Huanqing"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":["Li, Zhaojian","Zhu, Guoming","Modares, Hamidreza","Srivastava, Vaibhav"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2026,"date_issued":"2026","date_published":"2026","updated_at":"2026-11-18T18:59:47Z","subjects":["Mechanical engineering","Electrical engineering"],"languages":["eng"],"rights":["Attribution-NonCommercial-ShareAlike 4.0 International"],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["etd:53372","local:Wang_grad.msu_0128D_22428"],"render_values":[{"text":"etd:53372","href":null,"code":true},{"text":"local:Wang_grad.msu_0128D_22428","href":null,"code":true}]}],"person_identifier_entries":[]},"links":{"outbound_url":"https://doi.org/doi:10.25335/s0s9-5824","outbound_label":"DOI","outbound_source":"dc:identifier","record_url":"https://doi.org/doi:10.25335/s0s9-5824","record_label":"Repository record","record_kind":"doi","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://d.lib.msu.edu/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai%3Ad.lib.msu.edu%3Aetd_53372","prefix":"oai_dc"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Li, Zhaojian","Zhu, Guoming","Modares, Hamidreza","Srivastava, Vaibhav"]},{"key":"dc:creator","label":"Author","values":["Wang, Huanqing"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2026"]},{"key":"dc:relation","label":"Dc Relation","values":["Electronic Theses & Dissertations"]},{"key":"dc:type","label":"Dc Type","values":["text","Electronic dissertations"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Mechanical engineering","Electrical engineering"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["Attribution-NonCommercial-ShareAlike 4.0 International"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["etd:53372","local:Wang_grad.msu_0128D_22428","https://doi.org/doi:10.25335/s0s9-5824"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Thesis (Ph.D.)--Michigan State University. Mechanical Engineering - Doctor of Philosophy, 2026","Soft robots have attracted significant attention due to their flexibility, adaptability, and safety. However, their highly nonlinear dynamics present significant challenges for accurate modeling and control. Traditional model-based approaches often struggle to address these complexities, creating a growing need for advanced data-driven methodologies. In this dissertation, three innovative frameworks are proposed to advance data-driven control, modeling, and state estimation for soft robotic system applications.First, we present direct data-driven control of a planar soft robot using Data-Enabled Predictive Control (DeePC). This framework directly utilizes system input-output data without requiring an explicit parametric model. A dimension reduction technique based on singular value decomposition is incorporated to improve real-time computational efficiency. This work represents the first application of the DeePC framework to soft robots, with experimental results demonstrating superior performance over conventional model-based control strategies.Second, to address unknown payloads during soft robot manipulation tasks, we develop a novel velocity-form DeePC framework. By reformulating DeePC in an incremental input-output representation, the proposed method inherently compensates for constant disturbances and payload variations without relying on disturbance observers, weighted datasets, or explicit payload models. Experimental studies validate significant performance improvements over standard DeePC, particularly under unknown payload conditions.Third, we introduce a framework for data-driven modeling and proprioceptive state estimation of soft robots, addressing the limitations of relying on external motion capture systems in soft robotic applications. A bilinear Koopman modeling framework is developed to capture complex soft robot dynamics, while inertial measurement unit (IMU) data are fused through a time-varying Kalman filter for real-time state estimation. Experimental validation confirms that the proposed approach outperforms traditional methods in state estimation performance.Overall, this dissertation demonstrates effective data-driven modeling, control, and state estimation for soft robotic systems.","Description based on online resource. Title from PDF t.p. (Michigan State University Fedora Repository, viewed ).","Includes bibliographical references."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf","1 online resource (102 p.) : ill."]},{"key":"dc:title","label":"Title","values":["Data-driven Modeling, Control, and State Estimation : Advancements and Applications for Soft Robotic Systems"]}]}],"canonical_facts":{"dc:contributor":["Li, Zhaojian","Zhu, Guoming","Modares, Hamidreza","Srivastava, Vaibhav"],"dc:creator":["Wang, Huanqing"],"dc:date":["2026"],"dc:description":["Thesis (Ph.D.)--Michigan State University. Mechanical Engineering - Doctor of Philosophy, 2026","Soft robots have attracted significant attention due to their flexibility, adaptability, and safety. However, their highly nonlinear dynamics present significant challenges for accurate modeling and control. Traditional model-based approaches often struggle to address these complexities, creating a growing need for advanced data-driven methodologies. In this dissertation, three innovative frameworks are proposed to advance data-driven control, modeling, and state estimation for soft robotic system applications.First, we present direct data-driven control of a planar soft robot using Data-Enabled Predictive Control (DeePC). This framework directly utilizes system input-output data without requiring an explicit parametric model. A dimension reduction technique based on singular value decomposition is incorporated to improve real-time computational efficiency. This work represents the first application of the DeePC framework to soft robots, with experimental results demonstrating superior performance over conventional model-based control strategies.Second, to address unknown payloads during soft robot manipulation tasks, we develop a novel velocity-form DeePC framework. By reformulating DeePC in an incremental input-output representation, the proposed method inherently compensates for constant disturbances and payload variations without relying on disturbance observers, weighted datasets, or explicit payload models. Experimental studies validate significant performance improvements over standard DeePC, particularly under unknown payload conditions.Third, we introduce a framework for data-driven modeling and proprioceptive state estimation of soft robots, addressing the limitations of relying on external motion capture systems in soft robotic applications. A bilinear Koopman modeling framework is developed to capture complex soft robot dynamics, while inertial measurement unit (IMU) data are fused through a time-varying Kalman filter for real-time state estimation. Experimental validation confirms that the proposed approach outperforms traditional methods in state estimation performance.Overall, this dissertation demonstrates effective data-driven modeling, control, and state estimation for soft robotic systems.","Description based on online resource. Title from PDF t.p. (Michigan State University Fedora Repository, viewed ).","Includes bibliographical references."],"dc:format":["application/pdf","1 online resource (102 p.) : ill."],"dc:identifier":["etd:53372","local:Wang_grad.msu_0128D_22428","https://doi.org/doi:10.25335/s0s9-5824"],"dc:language":["eng"],"dc:relation":["Electronic Theses & Dissertations"],"dc:rights":["Attribution-NonCommercial-ShareAlike 4.0 International"],"dc:subject":["Mechanical engineering","Electrical engineering"],"dc:title":["Data-driven Modeling, Control, and State Estimation : Advancements and Applications for Soft Robotic Systems"],"dc:type":["text","Electronic dissertations"]},"updated_at":"2026-11-18T18:59:47Z"}