{"686276":{"#nid":"686276","#data":{"type":"event","title":"PhD Proposal by Shuo Cheng","body":[{"value":"\u003Cp\u003E\u003Cstrong\u003ETitle: Robot Skill Representations for Long-Horizon Task Learning and Deployment\u003C\/strong\u003E\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EShuo Cheng\u003C\/p\u003E\u003Cp\u003EPh.D. Student in Computer Science\u003C\/p\u003E\u003Cp\u003ESchool of Interactive Computing\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EGeorgia Institute of Technology\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\u0022https:\/\/sites.google.com\/view\/shuocheng\u0022\u003Ehttps:\/\/sites.google.com\/view\/shuocheng\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EDate:\u003C\/strong\u003E\u0026nbsp;Monday, Nov 17th, 2025\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003ETime:\u003C\/strong\u003E\u0026nbsp;11:00 AM - \u0026nbsp;12:30 PM EST\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003ELocation:\u003C\/strong\u003E\u0026nbsp;Klaus 1212,\u0026nbsp;\u003Ca href=\u0022https:\/\/gatech.zoom.us\/j\/2301796303?pwd=QjFYTE5sTzhCeVJRNXdpbXViSjFMUT09\u0026amp;omn=99157421529\u0022\u003EZoom Link\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003ECommittee:\u0026nbsp;\u003C\/strong\u003E\u003C\/p\u003E\u003Cp\u003EDr. Danfei Xu (Advisor) \u2013 School of Interactive Computing, Georgia Institute of Technology\u003C\/p\u003E\u003Cp\u003EDr. Sehoon Ha \u2013 School of Interactive Computing, Georgia Institute of Technology\u003C\/p\u003E\u003Cp\u003EDr. Harish Ravichandar \u2013 School of Interactive Computing, Georgia Institute of Technology\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EAbstract\u003C\/strong\u003E\u003C\/p\u003E\u003Cp\u003ERobots must acquire versatile and generalizable skills to operate effectively in complex, unstructured environments. This thesis investigates how to enable such capabilities through two complementary directions: (1) structural skill representations for scalable and generalizable learning, and (2) data generation and co-training frameworks for learning reactive, deployable policies. The first part develops representations that embed structural inductive biases to support efficient skill acquisition and reuse. LEAGUE, which progressively learns neuro-symbolic reinforcement learning policies within task and motion planning systems, facilitates compositional skill learning over long horizons and earned a Best Paper Honorable Mention at IEEE RA-L. NOD-TAMP enables one-shot skill adaptation across novel geometries and configurations through learned neural object descriptors. The second part introduces robotic data generation and policy distillation frameworks for large-scale, cross-domain learning. OT-Sim2Real leverages the learned skill representations to synthesize diverse simulation demonstrations and employs a co-training strategy that improves policy generalization beyond real-world data coverage\u2014bridging the gap between simulation and deployment.\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EProposed Work\u003C\/strong\u003E: Building on these foundations, future research will investigate how large-scale human videos can be leveraged to learn composable motion priors that enable scalable learning of robot manipulation systems that generalize across diverse tasks and embodiments. A factor graph representation is proposed to decompose the manipulation process into structured subcomponents, facilitating efficient learning of motion samplers from human videos. In addition, a diffusion-based steering strategy will be explored to guide the sampling process toward trajectories that satisfy task-specific constraints effectively and efficiently.\u003C\/p\u003E","summary":"","format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003E\u003Cstrong\u003ERobot Skill Representations for Long-Horizon Task Learning and Deployment\u003C\/strong\u003E\u003C\/p\u003E","format":"limited_html"}],"field_summary_sentence":[{"value":"Robot Skill Representations for Long-Horizon Task Learning and Deployment"}],"uid":"27707","created_gmt":"2025-11-06 20:10:08","changed_gmt":"2025-11-06 20:11:03","author":"Tatianna Richardson","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2025-11-17T11:00:00-05:00","event_time_end":"2025-11-17T12:30:42-05:00","event_time_end_last":"2025-11-17T12:30:42-05:00","gmt_time_start":"2025-11-17 16:00:00","gmt_time_end":"2025-11-17 17:30:42","gmt_time_end_last":"2025-11-17 17:30:42","rrule":null,"timezone":"America\/New_York"},"location":"Klaus 1212","extras":[],"groups":[{"id":"221981","name":"Graduate Studies"}],"categories":[],"keywords":[{"id":"102851","name":"Phd proposal"}],"core_research_areas":[],"news_room_topics":[],"event_categories":[{"id":"1788","name":"Other\/Miscellaneous"}],"invited_audience":[{"id":"78771","name":"Public"}],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[],"email":[],"slides":[],"orientation":[],"userdata":""}}}