{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/129334"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/129334","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Neural dynamics augmented diffusion policy","abstract":"Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-10-19 without embargo terms","abstract_html":"Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-10-19 without embargo terms","abstract_has_math":false,"creators":["Chen, Haozhe"],"institution":"University of Illinois Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Electrical & Computer Engr","degree_department":null,"school":null,"contributors":["Wang, Shenlong"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-05-07","date_published":"2025-05-07","updated_at":"2026-07-22T22:25:05Z","subjects":["Robotics","Imitation Learning","Diffusion Policy","Neural Dynamics","Robotic Manipulation"],"languages":["en","eng"],"rights":["Copyright 2025 Haozhe Chen"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2142/129334","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Wang, Shenlong"]},{"key":"dc:creator","label":"Author","values":["Chen, Haozhe"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2025-05-07","2025-05"]},{"key":"dc:type","label":"Dc Type","values":["text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical & Computer Engr"]},{"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 Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Robotics","Imitation Learning","Diffusion Policy","Neural Dynamics","Robotic Manipulation"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en","eng"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2025 Haozhe Chen"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://hdl.handle.net/2142/129334"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-10-19 without embargo terms","The student, Haozhe Chen, accepted the attached license on 2025-05-06 at 14:46.","The student, Haozhe Chen, submitted this Thesis for approval on 2025-05-06 at 14:57.","This Thesis was approved for publication on 2025-05-07 at 09:47.","DSpace SAF Submission Ingestion Package generated from Vireo submission #22235 on 2025-10-19 at 18:13:12","Imitation learning has been proven effective in mimicking demonstrations across various robotic manipulation tasks. However, to develop robust policies, current imitation methods, such as diffusion policy, require training on extensive demonstrations, making data collection labor-intensive. In contrast, model-based planning with dynamics models can effectively cover a sufficient range of configurations using only off-policy data. Yet, without the guidance of expert demonstrations, many tasks are difficult and time-consuming to plan using the dynamics models. Therefore, we take the best of both model learning and imitation learning, and propose neural dynamics augmented imitation learning that covers large-scene configurations with few-shot demonstrations. This method trains a robust diffusion policy in a local support region using few-shot demonstrations and rearranges objects outside this region into it using offline-trained neural dynamics models. Extensive experiments across various tasks in both simulations and real-world scenarios, including granular manipulation, contact-rich tasks, and multi-object interaction tasks, have demonstrated that trained with only 1 to 30 demonstrations, our proposed method can robustly cover a significantly larger area than the policy trained purely from the demonstrations."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Neural dynamics augmented diffusion policy"]}]}],"canonical_facts":{"dc:contributor":["Wang, Shenlong"],"dc:creator":["Chen, Haozhe"],"dc:date":["2025-05-07","2025-05"],"dc:description":["Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-10-19 without embargo terms","The student, Haozhe Chen, accepted the attached license on 2025-05-06 at 14:46.","The student, Haozhe Chen, submitted this Thesis for approval on 2025-05-06 at 14:57.","This Thesis was approved for publication on 2025-05-07 at 09:47.","DSpace SAF Submission Ingestion Package generated from Vireo submission #22235 on 2025-10-19 at 18:13:12","Imitation learning has been proven effective in mimicking demonstrations across various robotic manipulation tasks. However, to develop robust policies, current imitation methods, such as diffusion policy, require training on extensive demonstrations, making data collection labor-intensive. In contrast, model-based planning with dynamics models can effectively cover a sufficient range of configurations using only off-policy data. Yet, without the guidance of expert demonstrations, many tasks are difficult and time-consuming to plan using the dynamics models. Therefore, we take the best of both model learning and imitation learning, and propose neural dynamics augmented imitation learning that covers large-scene configurations with few-shot demonstrations. This method trains a robust diffusion policy in a local support region using few-shot demonstrations and rearranges objects outside this region into it using offline-trained neural dynamics models. Extensive experiments across various tasks in both simulations and real-world scenarios, including granular manipulation, contact-rich tasks, and multi-object interaction tasks, have demonstrated that trained with only 1 to 30 demonstrations, our proposed method can robustly cover a significantly larger area than the policy trained purely from the demonstrations."],"dc:format":["application/pdf"],"dc:identifier":["https://hdl.handle.net/2142/129334"],"dc:language":["en","eng"],"dc:rights":["Copyright 2025 Haozhe Chen"],"dc:subject":["Robotics","Imitation Learning","Diffusion Policy","Neural Dynamics","Robotic Manipulation"],"dc:title":["Neural dynamics augmented diffusion policy"],"dc:type":["text"],"thesis:degree_discipline":["Electrical & Computer Engr"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois Urbana-Champaign"]},"updated_at":"2026-07-22T22:25:05Z"}