{"472781":{"#nid":"472781","#data":{"type":"event","title":"Ph.D. Dissertation Defense - Rowland O\u0027Flaherty","body":[{"value":"\u003Cstrong\u003ETitle:\u0026nbsp;\u003C\/strong\u003EA Control Theoretic Perspective on Learning in Robotics\u003Cbr \/\u003E\u003Cbr \/\u003E\u003Cstrong\u003ECommittee:\u003C\/strong\u003EDr. Magnus Egerstedt (Advisor), School of Electrical and Computer Engineering, Georgia Tech\u003Cbr \/\u003EDr. Ayanna Howard, School of Electrical and Computer Engineering, Georgia Tech\u003Cbr \/\u003EDr. Patricio Vela, School of Electrical and Computer Engineering, Georgia Tech\u003Cbr \/\u003EDr. Jonathan Rogers, School of Mechanical Engineering, Georgia Tech\u003Cbr \/\u003EDr. Charles Isbell, School of Interactive Computing, Georgia Tech\u003Cbr \/\u003E\u003Cstrong\u003EAbstract:\u003C\/strong\u003E\u003Cstrong\u003E\u003Cbr \/\u003E\u003C\/strong\u003E\u003Cstrong\u003E\u003C\/strong\u003EFor robotic systems to continue to move towards ubiquity, robots need to be more autonomous. More autonomy dictates that robots need to be able to make better decisions. Control theory and machine learning are fields of robotics that focus on the decision making process. However, each of these fields implements decision making at different levels of abstraction and at different time scales. Control theory defines low-level decisions at high rates, while machine learning defines high-level decision at low rates. The objective of this research is to integrate tools from both machine leaning and control theory to solve higher dimensional, complex problems, and to optimize the decision making process.\u003Cbr \/\u003EThroughout this research, multiple algorithms were created that use concepts from both control theory and machine learning, which provide new tools for robots to make better decisions. One algorithm enables a robot to learn how to optimally explore an unknown space, and autonomously decide when to explore for new information or exploit its current information. Another algorithm enables a robot to learn how to locomote with complex dynamics. These algorithms are evaluated both in simulation and on real robots. The results and analysis of these experiments are presented, which demonstrate the utility of the algorithms introduced in this work. Additionally, a new notion of \u0022learnability\u0027\u0027 is introduced to define and determine when a given dynamical system has the ability to gain knowledge to optimize a given objective function.","summary":null,"format":"limited_html"}],"field_subtitle":"","field_summary":"","field_summary_sentence":[{"value":"ROBOTICS PhD Dissertation Defense"}],"uid":"28475","created_gmt":"2015-11-23 20:14:53","changed_gmt":"2016-10-08 02:14:58","author":"Daniela Staiculescu","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2015-12-07T19:00:00-05:00","event_time_end":"2015-12-07T19:00:00-05:00","event_time_end_last":"2015-12-07T19:00:00-05:00","gmt_time_start":"2015-12-08 00:00:00","gmt_time_end":"2015-12-08 00:00:00","gmt_time_end_last":"2015-12-08 00:00:00","rrule":null,"timezone":"America\/New_York"},"extras":[],"groups":[{"id":"434381","name":"ECE Ph.D. Dissertation Defenses"}],"categories":[],"keywords":[{"id":"1808","name":"graduate students"},{"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":""}}}