{"689412":{"#nid":"689412","#data":{"type":"event","title":"PhD Defense by Maks Sorokin","body":[{"value":"\u003Cp\u003E\u003Cstrong\u003ETitle:\u003C\/strong\u003E\u0026nbsp;\u0022Levers of Robot Learning: From Privileged Training to Vision-Based Deployment\u0022\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EDate:\u003C\/strong\u003E\u0026nbsp;Monday, April 13, 2026\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003ETime:\u003C\/strong\u003E\u0026nbsp;1:00 - 3:00 PM ET\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003ELocation:\u0026nbsp;\u003C\/strong\u003ERemote (\u003Ca href=\u0022https:\/\/gatech.zoom.us\/j\/99520988331\u0022\u003Ehttps:\/\/gatech.zoom.us\/j\/99520988331\u003C\/a\u003E)\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EMaks Sorokin\u003C\/strong\u003E\u003C\/p\u003E\u003Cp\u003ERobotics Ph.D. Candidate\u003C\/p\u003E\u003Cp\u003ESchool of Interactive Computing\u003C\/p\u003E\u003Cp\u003EGeorgia Institute of Technology\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\u0022https:\/\/itsmaks.com\/\u0022\u003Ehttps:\/\/itsmaks.com\/\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003ECommittee\u003C\/strong\u003E\u003C\/p\u003E\u003Cp\u003EDr. Sehoon Ha (Advisor) - School of Interactive Computing, Georgia Institute of Technology\u003C\/p\u003E\u003Cp\u003EDr. Danfei Xu - School of Interactive Computing, Georgia Institute of Technology\u003C\/p\u003E\u003Cp\u003EDr. Sonia Chernova - School of Interactive Computing, Georgia Institute of Technology\u003C\/p\u003E\u003Cp\u003EDr. C. Karen Liu - Department of Computer Science, Stanford University\u003C\/p\u003E\u003Cp\u003EDr. Jie Tan - Director, Google DeepMind\u003C\/p\u003E\u003Cp\u003EDr. Simon Le Cleac\u0027H - Research Scientist, RAI Institute\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EAbstract\u003C\/strong\u003E\u003C\/p\u003E\u003Cp\u003ERobot learning systems typically train with privileged information that is unavailable when the robot deploys with onboard cameras: bird\u0027s-eye-view maps, ground-truth object positions, full environment state. This thesis develops four systems spanning navigation, robot design, and whole-body manipulation, and identifies in each case the design choice in representation, evaluation, or distillation that enabled deployment with onboard vision.\u003C\/p\u003E\u003Cp\u003EA quadruped navigated 3.2 km of urban sidewalks using penultimate features from a pre-trained segmentation network as its visual input, achieving 83% real-world success where raw images achieved 25% and semantic labels 7%. A mobile manipulator\u0027s morphology was optimized by evaluating candidates with onboard cameras rather than privileged state, producing designs that achieved 80% success and required 25x less training data than a human-expert baseline. A navigation policy trained in abstract colored-tile worlds transferred zero-shot to photorealistic simulation and real hardware using sparse boundary points as its only perception input (87-100% vs. 0-48% for dense representations). A Spot quadruped robot with an arm learned to push, roll, and upright a 15 kg car tire using hierarchical RL, and cascaded distillation transferred the resulting policies from privileged state to onboard perception.\u003C\/p\u003E","summary":"","format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003ELevers of Robot Learning: From Privileged Training to Vision-Based Deployment\u003C\/p\u003E","format":"limited_html"}],"field_summary_sentence":[{"value":"Levers of Robot Learning: From Privileged Training to Vision-Based Deployment"}],"uid":"27707","created_gmt":"2026-04-02 18:21:29","changed_gmt":"2026-04-02 18:21:58","author":"Tatianna Richardson","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2026-04-13T13:00:00-04:00","event_time_end":"2026-04-13T15:00:00-04:00","event_time_end_last":"2026-04-13T15:00:00-04:00","gmt_time_start":"2026-04-13 17:00:00","gmt_time_end":"2026-04-13 19:00:00","gmt_time_end_last":"2026-04-13 19:00:00","rrule":null,"timezone":"America\/New_York"},"location":"Remote ","extras":[],"groups":[{"id":"221981","name":"Graduate Studies"}],"categories":[],"keywords":[{"id":"100811","name":"Phd Defense"}],"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":""}}}