{"641677":{"#nid":"641677","#data":{"type":"event","title":"Ph.D. Proposal Oral Exam - Keuntaek Lee","body":[{"value":"\u003Cp\u003E\u003Cstrong\u003ETitle:\u0026nbsp; \u003C\/strong\u003E\u003Cem\u003ERobust Deep Vision-based Control Algorithms with Probabilistic Learning\u003C\/em\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003ECommittee:\u0026nbsp; \u003C\/strong\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003EDr. Theodorou, Advisor\u003C\/p\u003E\r\n\r\n\u003Cp\u003EDr. Vela, Co-Advisor\u0026nbsp;\u0026nbsp;\u0026nbsp;\u0026nbsp;\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003EDr. Coogan, Chair\u003C\/p\u003E\r\n\r\n\u003Cp\u003EDr. Rehg\u003C\/p\u003E\r\n\r\n\u003Cp\u003EDr. Al-Regib\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003EAbstract: \u003C\/strong\u003EThe object of the proposed research is to develop safe and robust vision-based control algorithms for autonomous vehicles.\u0026nbsp;In our robust vision-based imitation learning algorithms, we propose the use of Bayesian Neural Networks (BNNs), which provide both a mean value and an uncertainty estimate as output, to enhance the safety of learned control policies when a test-time input differs significantly from the training set. Furthermore, to quickly detect abnormal uncertain situations in vision-based control, we use Model Predictive Control (MPC) to learn how to focus on important areas of the visual input. This attention-based mechanism allows the system to more rapidly detect unsafe conditions when novel obstacles are present in the navigation environment.\u0026nbsp;Another vision-based control algorithm, the PixelMPC with the Deep Optical Flow dynamics, robustifies the vision-based state estimation of the robot. This novel MPC algorithm allows us to predict both robot\u0026#39;s optimal path and the path of a pixel-of-interest in the scene. By controlling a pixel with its learned optical flow dynamics, a robot can have better and stable visual information which results in a robust state estimation followed by robust path planning and control. The proposed algorithm is tested in a photorealistic simulation with a high-speed drone racing task.\u003C\/p\u003E\r\n","summary":null,"format":"limited_html"}],"field_subtitle":"","field_summary":"","field_summary_sentence":[{"value":"Robust Deep Vision-based Control Algorithms with Probabilistic Learning"}],"uid":"28475","created_gmt":"2020-11-29 23:45:21","changed_gmt":"2020-11-29 23:45:21","author":"Daniela Staiculescu","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2020-12-02T13:30:00-05:00","event_time_end":"2020-12-02T15:30:00-05:00","event_time_end_last":"2020-12-02T15:30:00-05:00","gmt_time_start":"2020-12-02 18:30:00","gmt_time_end":"2020-12-02 20:30:00","gmt_time_end_last":"2020-12-02 20:30:00","rrule":null,"timezone":"America\/New_York"},"extras":[],"groups":[{"id":"434371","name":"ECE Ph.D. Proposal Oral Exams"}],"categories":[],"keywords":[{"id":"102851","name":"Phd proposal"},{"id":"1808","name":"graduate students"}],"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":""}}}