{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/144618"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/144618","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Model-based Control for Robot Manipulation Tasks with High-dimensional State Spaces","abstract":"Long horizon manipulation tasks are typically composed of sub-tasks with varying complexity. One phase of the task, for example, may require a continuous action space and another may be more efficiently solved using a discrete action space. Similarly, complexity in the state space may require analogous abstractions in order to apply classical planning and control methods; e.g., viewing a symbolic representation versus pixel-based representation. A common approach to addressing long horizon tasks is to develop a hierarchical system with a fixed state representation and a set of discrete and continuous action spaces to solve components of the task. However, tasks with high-dimensional state spaces present a problem for this approach where the fixed representation is ill-fit for solving certain phases of the task. This work motivates an alternative where learnt abstractions of the state space allow a hierarchical system to do coarse-to-fine reasoning of representation information to solve a task more effectively. We demonstrate a prototype of such an adaptive system and compare its performance with a system that has fixed representations. The prototype was tested in simulated table-top experiments as well as physical experiments with the Franka Emika Panda arm. The prototype outperformed the baselines in all long horizon cloth manipulation tasks by a margin of up to 20% and matched baseline performance in the rope domain.","abstract_html":"Long horizon manipulation tasks are typically composed of sub-tasks with varying complexity. One phase of the task, for example, may require a continuous action space and another may be more efficiently solved using a discrete action space. Similarly, complexity in the state space may require analogous abstractions in order to apply classical planning and control methods; e.g., viewing a symbolic representation versus pixel-based representation. A common approach to addressing long horizon tasks is to develop a hierarchical system with a fixed state representation and a set of discrete and continuous action spaces to solve components of the task. However, tasks with high-dimensional state spaces present a problem for this approach where the fixed representation is ill-fit for solving certain phases of the task. This work motivates an alternative where learnt abstractions of the state space allow a hierarchical system to do coarse-to-fine reasoning of representation information to solve a task more effectively. We demonstrate a prototype of such an adaptive system and compare its performance with a system that has fixed representations. The prototype was tested in simulated table-top experiments as well as physical experiments with the Franka Emika Panda arm. The prototype outperformed the baselines in all long horizon cloth manipulation tasks by a margin of up to 20% and matched baseline performance in the rope domain.","abstract_has_math":false,"creators":["Githinji, Bilha-Catherine \"Bilkit\" W."],"institution":"Massachusetts Institute of Technology","degree_name":"Master","degree_level":null,"degree_discipline":null,"degree_department":"Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science","school":null,"contributors":[],"advisors":["Shah, Julie A."],"committee_chairs":[],"committee_members":[],"year":2022,"date_issued":"2022-05","date_published":"2022-05","updated_at":"2026-07-22T22:22:13Z","subjects":[],"languages":[],"rights":["In Copyright - Educational Use Permitted","Copyright MIT"],"rights_urls":["http://rightsstatements.org/page/InC-EDU/1.0/"],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1721.1/144618","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Shah, Julie A."]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"]},{"key":"dc:creator","label":"Author","values":["Githinji, Bilha-Catherine \"Bilkit\" W."]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2022-08-29T15:59:57Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2022-08-29T15:59:57Z"]},{"key":"dc:date.issued","label":"Date","values":["2022-05"]},{"key":"dc:publisher","label":"Institution","values":["Massachusetts Institute of Technology"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master","Master of Science in Electrical Engineering and Computer Science"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["In Copyright - Educational Use Permitted","Copyright MIT"]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://rightsstatements.org/page/InC-EDU/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1721.1/144618"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Long horizon manipulation tasks are typically composed of sub-tasks with varying complexity. One phase of the task, for example, may require a continuous action space and another may be more efficiently solved using a discrete action space. Similarly, complexity in the state space may require analogous abstractions in order to apply classical planning and control methods; e.g., viewing a symbolic representation versus pixel-based representation. A common approach to addressing long horizon tasks is to develop a hierarchical system with a fixed state representation and a set of discrete and continuous action spaces to solve components of the task. However, tasks with high-dimensional state spaces present a problem for this approach where the fixed representation is ill-fit for solving certain phases of the task. This work motivates an alternative where learnt abstractions of the state space allow a hierarchical system to do coarse-to-fine reasoning of representation information to solve a task more effectively. We demonstrate a prototype of such an adaptive system and compare its performance with a system that has fixed representations. The prototype was tested in simulated table-top experiments as well as physical experiments with the Franka Emika Panda arm. The prototype outperformed the baselines in all long horizon cloth manipulation tasks by a margin of up to 20% and matched baseline performance in the rope domain."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["S.M."]},{"key":"dc:title","label":"Title","values":["Model-based Control for Robot Manipulation Tasks with High-dimensional State Spaces"]}]}],"canonical_facts":{"dc:contributor.advisor":["Shah, Julie A."],"dc:contributor.department":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"],"dc:creator":["Githinji, Bilha-Catherine \"Bilkit\" W."],"dc:date.accessioned":["2022-08-29T15:59:57Z"],"dc:date.available":["2022-08-29T15:59:57Z"],"dc:date.issued":["2022-05"],"dc:description.abstract":["Long horizon manipulation tasks are typically composed of sub-tasks with varying complexity. One phase of the task, for example, may require a continuous action space and another may be more efficiently solved using a discrete action space. Similarly, complexity in the state space may require analogous abstractions in order to apply classical planning and control methods; e.g., viewing a symbolic representation versus pixel-based representation. A common approach to addressing long horizon tasks is to develop a hierarchical system with a fixed state representation and a set of discrete and continuous action spaces to solve components of the task. However, tasks with high-dimensional state spaces present a problem for this approach where the fixed representation is ill-fit for solving certain phases of the task. This work motivates an alternative where learnt abstractions of the state space allow a hierarchical system to do coarse-to-fine reasoning of representation information to solve a task more effectively. We demonstrate a prototype of such an adaptive system and compare its performance with a system that has fixed representations. The prototype was tested in simulated table-top experiments as well as physical experiments with the Franka Emika Panda arm. The prototype outperformed the baselines in all long horizon cloth manipulation tasks by a margin of up to 20% and matched baseline performance in the rope domain."],"dc:description.degree":["S.M."],"dc:identifier.uri":["https://hdl.handle.net/1721.1/144618"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["In Copyright - Educational Use Permitted","Copyright MIT"],"dc:rights.uri":["http://rightsstatements.org/page/InC-EDU/1.0/"],"dc:title":["Model-based Control for Robot Manipulation Tasks with High-dimensional State Spaces"],"dc:type":["Thesis"],"thesis:degree_name":["Master","Master of Science in Electrical Engineering and Computer Science"]},"updated_at":"2026-07-22T22:22:13Z"}