{"622864":{"#nid":"622864","#data":{"type":"news","title":"IC Researchers Earn 2018 IJRR Paper of the Year for Impactful Robotics Research","body":[{"value":"\u003Cp\u003EA paper published in the \u003Cem\u003EI\u003Ca href=\u0022http:\/\/www.ijrr.org\/\u0022\u003Enternational Journal of Robotics Research\u003C\/a\u003E\u003C\/em\u003E (IJRR) by researchers in the \u003Ca href=\u0022http:\/\/ic.gatech.edu\u0022\u003ESchool of Interactive Computing\u003C\/a\u003E (IC) was selected as the 2018 IJRR Paper of the Year.\u003C\/p\u003E\r\n\r\n\u003Cp\u003EChosen from a shortlist considered by the IJRR Executive Committee, the paper, \u003Ca href=\u0022https:\/\/arxiv.org\/abs\/1707.07383\u0022\u003E\u003Cem\u003EContinuous-time Gaussian Process Motion Planning via Probabilistic Inference\u003C\/em\u003E\u003C\/a\u003E, was recognized for its technical rigor, relevance, and potential for impact in the robotics research community. The research comes from IC Ph.D. students \u003Cstrong\u003EMustafa Mukadam\u003C\/strong\u003E and \u003Cstrong\u003EJing Dong\u003C\/strong\u003E, master\u0026rsquo;s student \u003Cstrong\u003EXinyan Yan\u003C\/strong\u003E, and advisors Professor \u003Cstrong\u003EFrank Dellaert\u003C\/strong\u003E and Assistant Professor \u003Cstrong\u003EByron Boots\u003C\/strong\u003E.\u003C\/p\u003E\r\n\r\n\u003Cp\u003EThis paper introduces a novel formulation of motion planning that treats the problem of finding an efficient, feasible path between two points as probabilistic inference with Gaussian Processes. Motion planning is a hard problem, and state-of-the art sampling-based and trajectory optimization algorithms have well-known drawbacks. The former can effectively find feasible trajectories but often exhibits jerky and redundant motion, and the latter requires a fine approximation of the trajectory to reason about thin obstacles or tight constraints.\u003C\/p\u003E\r\n\r\n\u003Cp\u003EIn their paper, the team of researchers adopts a continuous-time representation of trajectories, viewing them as functions that map time to robot state. Combing this representation with fast approaches to probabilistic inference, they developed a computationally-efficient gradient-based optimization algorithm called a Gaussian Process Motion Planner that can overcome large computational costs associated with fine discretization, while still maintaining smoothness of motion in the result.\u003C\/p\u003E\r\n\r\n\u003Cp\u003EWith the award comes a $1,000 prize. Boots attended the \u003Ca href=\u0022http:\/\/www.roboticsconference.org\/\u0022\u003ERobotics: Science and Systems\u003C\/a\u003E (RSS) conference in the Freiburg, Germany, this week, where he accepted the award on behalf of his team.\u003C\/p\u003E\r\n\r\n\u003Cp\u003EAnother paper involving Boots was also awarded a Best Student Paper Award at RSS. Titled \u003Ca href=\u0022https:\/\/arxiv.org\/abs\/1902.08967\u0022\u003E\u003Cem\u003EAn Online Learning Approach to Model Predictive Control\u003C\/em\u003E\u003C\/a\u003E, the paper was written by Robotics Ph.D. students \u003Cstrong\u003ENolan Wagener\u003C\/strong\u003E, \u003Cstrong\u003EChing-An Cheng\u003C\/strong\u003E, and \u003Cstrong\u003EJacob Sacks\u003C\/strong\u003E, along with Boots.\u003C\/p\u003E\r\n\r\n\u003Cp\u003EIt shows that there exists a close connection between model predictive control (MPC), a popular technique for solving dynamic control tasks, and online learning, an abstract theoretical framework for analyzing online decision making. This new perspective provides a foundation for leveraging powerful online learning algorithms to design MPC algorithms. Toward this end, the researchers propose a generic framework for synthesizing new MPC algorithms called Dynamic Mirror Decent Model Predictive Control.\u003C\/p\u003E\r\n\r\n\u003Cp\u003EThe framework exposes key design choices that can help practitioners easily develop new control algorithms tailored to the challenges of their specific task. The approach is validated by developing new MPC algorithms that consistently match or outperform the state-of-the-art on several tasks including an aggressive driving problem with the goal of racing an autonomous car around a dirt track under computational resource constraints.\u003C\/p\u003E\r\n","summary":null,"format":"limited_html"}],"field_subtitle":"","field_summary":"","field_summary_sentence":[{"value":"With the award comes a $1,000 prize. Boots attended the Robotics: Science and Systems (RSS) conference in the Freiburg, Germany, this week, where he accepted the award on behalf of his team."}],"uid":"33939","created_gmt":"2019-06-28 21:45:13","changed_gmt":"2019-06-28 21:45:13","author":"David Mitchell","boilerplate_text":"","field_publication":"","field_article_url":"","dateline":{"date":"2019-06-28T00:00:00-04:00","iso_date":"2019-06-28T00:00:00-04:00","tz":"America\/New_York"},"extras":[],"hg_media":{"622863":{"id":"622863","type":"image","title":"IJRR Paper of the Year","body":null,"created":"1561757769","gmt_created":"2019-06-28 21:36:09","changed":"1561757769","gmt_changed":"2019-06-28 21:36:09","alt":"Byron Boots accepts the IJRR Paper of the Year Award at RSS 2019","file":{"fid":"237211","name":"IJRR Paper of the Year.jpeg","image_path":"\/sites\/default\/files\/images\/IJRR%20Paper%20of%20the%20Year.jpeg","image_full_path":"http:\/\/www.tlwarc.hg.gatech.edu\/\/sites\/default\/files\/images\/IJRR%20Paper%20of%20the%20Year.jpeg","mime":"image\/jpeg","size":214672,"path_740":"http:\/\/www.tlwarc.hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/images\/IJRR%20Paper%20of%20the%20Year.jpeg?itok=SXUz75L5"}},"622862":{"id":"622862","type":"image","title":"RSS Best Student Paper","body":null,"created":"1561757679","gmt_created":"2019-06-28 21:34:39","changed":"1561757679","gmt_changed":"2019-06-28 21:34:39","alt":"A team of researchers accepts the Best Student Paper award at RSS 2019","file":{"fid":"237210","name":"RSS Best Student Paper.jpeg","image_path":"\/sites\/default\/files\/images\/RSS%20Best%20Student%20Paper.jpeg","image_full_path":"http:\/\/www.tlwarc.hg.gatech.edu\/\/sites\/default\/files\/images\/RSS%20Best%20Student%20Paper.jpeg","mime":"image\/jpeg","size":181785,"path_740":"http:\/\/www.tlwarc.hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/images\/RSS%20Best%20Student%20Paper.jpeg?itok=25hWiAB-"}}},"media_ids":["622863","622862"],"related_links":[{"url":"https:\/\/www.ic.gatech.edu\/content\/robotics-computational-perception","title":"Robotics and Computational Perception Research at Georgia Tech"}],"groups":[{"id":"1299","name":"GVU Center"},{"id":"576481","name":"ML@GT"},{"id":"431631","name":"OMS"},{"id":"50876","name":"School of Interactive Computing"}],"categories":[],"keywords":[{"id":"181602","name":"ic-robotics"},{"id":"181216","name":"cc-research"}],"core_research_areas":[{"id":"39501","name":"People and Technology"},{"id":"39521","name":"Robotics"}],"news_room_topics":[],"event_categories":[],"invited_audience":[],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[{"value":"\u003Cp\u003EDavid Mitchell\u003C\/p\u003E\r\n\r\n\u003Cp\u003ECommunications Officer\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Ca href=\u0022mailto:david.mitchell@cc.gatech.edu\u0022\u003Edavid.mitchell@cc.gatech.edu\u003C\/a\u003E\u003C\/p\u003E\r\n","format":"limited_html"}],"email":[],"slides":[],"orientation":[],"userdata":""}}}