{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/162413"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/162413","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Simulation-Based Reinforcement Learning Policy Optimization for Tactile Manipulation: A Case Study on the Eyesight Hand","abstract":"Robotic manipulation remains a complex and unsolved challenge due to the need for adaptability across diverse objects and tasks. In this work, we explore how to train effective manipulation policies using reinforcement learning in simulation for the Eyesight Hand: a novel, low-cost, tactile-enabled robotic hand. We implement a range of experiments in MuJoCo to evaluate the impact of controller types, observation spaces, reward formulations, and curriculum strategies on policy performance. Our findings highlight the benefits of delta position control, a carefully selected observation space including joint states, control vectors, object pose, and contact forces, and success-driven curriculum learning. Our study establishes baseline strategies for training robust, tactile-based policies on this in-house hardware.","abstract_html":"Robotic manipulation remains a complex and unsolved challenge due to the need for adaptability across diverse objects and tasks. In this work, we explore how to train effective manipulation policies using reinforcement learning in simulation for the Eyesight Hand: a novel, low-cost, tactile-enabled robotic hand. We implement a range of experiments in MuJoCo to evaluate the impact of controller types, observation spaces, reward formulations, and curriculum strategies on policy performance. Our findings highlight the benefits of delta position control, a carefully selected observation space including joint states, control vectors, object pose, and contact forces, and success-driven curriculum learning. Our study establishes baseline strategies for training robust, tactile-based policies on this in-house hardware.","abstract_has_math":false,"creators":["Chang, Ethan"],"institution":"Massachusetts Institute of Technology","degree_name":"Bachelor","degree_level":null,"degree_discipline":null,"degree_department":"Massachusetts Institute of Technology. Department of Mechanical Engineering","school":null,"contributors":[],"advisors":["Agrawal, Pulkit"],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-05","date_published":"2025-05","updated_at":"2026-07-22T22:22:10Z","subjects":[],"languages":[],"rights":["In Copyright - Educational Use Permitted","Copyright retained by author(s)"],"rights_urls":["https://rightsstatements.org/page/InC-EDU/1.0/"],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1721.1/162413","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Agrawal, Pulkit"]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Department of Mechanical Engineering"]},{"key":"dc:creator","label":"Author","values":["Chang, Ethan"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2025-08-21T17:00:22Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2025-08-21T17:00:22Z"]},{"key":"dc:date.issued","label":"Date","values":["2025-05"]},{"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":["Bachelor","Bachelor of Science in Mechanical Engineering"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["In Copyright - Educational Use Permitted","Copyright retained by author(s)"]},{"key":"dc:rights.uri","label":"Rights URI","values":["https://rightsstatements.org/page/InC-EDU/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1721.1/162413"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Robotic manipulation remains a complex and unsolved challenge due to the need for adaptability across diverse objects and tasks. In this work, we explore how to train effective manipulation policies using reinforcement learning in simulation for the Eyesight Hand: a novel, low-cost, tactile-enabled robotic hand. We implement a range of experiments in MuJoCo to evaluate the impact of controller types, observation spaces, reward formulations, and curriculum strategies on policy performance. Our findings highlight the benefits of delta position control, a carefully selected observation space including joint states, control vectors, object pose, and contact forces, and success-driven curriculum learning. Our study establishes baseline strategies for training robust, tactile-based policies on this in-house hardware."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["S.B."]},{"key":"dc:title","label":"Title","values":["Simulation-Based Reinforcement Learning Policy Optimization for Tactile Manipulation: A Case Study on the Eyesight Hand"]}]}],"canonical_facts":{"dc:contributor.advisor":["Agrawal, Pulkit"],"dc:contributor.department":["Massachusetts Institute of Technology. Department of Mechanical Engineering"],"dc:creator":["Chang, Ethan"],"dc:date.accessioned":["2025-08-21T17:00:22Z"],"dc:date.available":["2025-08-21T17:00:22Z"],"dc:date.issued":["2025-05"],"dc:description.abstract":["Robotic manipulation remains a complex and unsolved challenge due to the need for adaptability across diverse objects and tasks. In this work, we explore how to train effective manipulation policies using reinforcement learning in simulation for the Eyesight Hand: a novel, low-cost, tactile-enabled robotic hand. We implement a range of experiments in MuJoCo to evaluate the impact of controller types, observation spaces, reward formulations, and curriculum strategies on policy performance. Our findings highlight the benefits of delta position control, a carefully selected observation space including joint states, control vectors, object pose, and contact forces, and success-driven curriculum learning. Our study establishes baseline strategies for training robust, tactile-based policies on this in-house hardware."],"dc:description.degree":["S.B."],"dc:identifier.uri":["https://hdl.handle.net/1721.1/162413"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["In Copyright - Educational Use Permitted","Copyright retained by author(s)"],"dc:rights.uri":["https://rightsstatements.org/page/InC-EDU/1.0/"],"dc:title":["Simulation-Based Reinforcement Learning Policy Optimization for Tactile Manipulation: A Case Study on the Eyesight Hand"],"dc:type":["Thesis"],"thesis:degree_name":["Bachelor","Bachelor of Science in Mechanical Engineering"]},"updated_at":"2026-07-22T22:22:10Z"}