![\"Ani](\"\/learningautonomy\/files\/2024\/09\/Ani-Hsieh-150x150.jpg\")
<\/p>\n<\/p>\n
From Data-Driven to Physics Guided: A Pathway to More Efficient, Generalizable, and Robust Autonomy<\/span><\/strong><\/p>\n Robots and autonomous systems revolutionize the way we explore and interact with the world around us!<\/span>\u00a0 <\/span>However, good dynamics modeling is foundational in the design, control, and planning of robust and safe robotic systems.<\/span>\u00a0 <\/span>However, as robotic systems and the environments where they are deployed in become more complex, it is increasingly difficult <\/span>to capture their behaviors by relying solely on foundational, first-principles, physics models.<\/span>\u00a0 <\/span>In this talk, I will describe my group\u2019s attempts at bridging the gap between physics-based and data-driven methods to improve model performance, increase sample efficiency, and enhance the generalizability of learned models.<\/span>\u00a0 <\/span>Specifically, I will discuss two approaches to knowledge embedding: through the use of<\/span>\u00a0 <\/span>Knowledge-Based Neural Ordinary Differential Equations (KNODE) and via Koopman operator theory.<\/span>\u00a0 <\/span>I will conclude with example robot applications ranging from tight formation flying with quadrotors to mapping complex spatiotemporal processes to highlight the advantages of physics-informed learning.<\/span><\/p>\n M. Ani Hsieh<\/strong> is an Associate Professor in the Department of Mechanical Engineering and Applied Mechanics at the University of Pennsylvania.<\/span>\u00a0 <\/span>She is also the Deputy Director of the General Robotics, Automation, Sensing, and Perception (GRASP) Laboratory and Program Chair for the Robotics MSE Program.<\/span>\u00a0 <\/span>Her research interests lie at the intersection of robotics, multi-agent systems, and dynamical systems theory.<\/span>\u00a0 <\/span>Hsieh and her team design algorithms for estimation, control, and planning for multi-agent robotic systems with applications in environmental monitoring, estimation and prediction of complex dynamics, and design of collective behaviors.<\/span>\u00a0 <\/span>She received her B.S. in Engineering and B.A. in Economics from Swarthmore College and her PhD in Mechanical Engineering from the University of Pennsylvania.<\/span>\u00a0 <\/span>Prior to Penn, she was an Associate Professor in the Department of Mechanical Engineering and Mechanics at Drexel University.<\/span>\u00a0 <\/span>Hsieh is the recipient of a 2012 Office of Naval Research (ONR) Young Investigator Award and a 2013 National Science Foundation (NSF) CAREER Award.<\/span>\u00a0<\/span><\/p>\n","protected":false},"excerpt":{"rendered":" University of Pennsylvania Deputy Director, GRASP Lab; Graduate Program Chair, ROBO; Associate Professor, MEAM Mechanical Engineering and Applied Mechanics From Data-Driven to Physics Guided: A Pathway to More Efficient, Generalizable, and Robust Autonomy Robots and autonomous systems revolutionize the way we explore and interact with the world around us!\u00a0 However, good dynamics modeling is foundational […]<\/p>\n","protected":false},"author":18553,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"page-templates\/no-sidebars.php","meta":[],"_links":{"self":[{"href":"https:\/\/sites.bu.edu\/learningautonomy\/wp-json\/wp\/v2\/pages\/395"}],"collection":[{"href":"https:\/\/sites.bu.edu\/learningautonomy\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/sites.bu.edu\/learningautonomy\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/sites.bu.edu\/learningautonomy\/wp-json\/wp\/v2\/users\/18553"}],"replies":[{"embeddable":true,"href":"https:\/\/sites.bu.edu\/learningautonomy\/wp-json\/wp\/v2\/comments?post=395"}],"version-history":[{"count":8,"href":"https:\/\/sites.bu.edu\/learningautonomy\/wp-json\/wp\/v2\/pages\/395\/revisions"}],"predecessor-version":[{"id":444,"href":"https:\/\/sites.bu.edu\/learningautonomy\/wp-json\/wp\/v2\/pages\/395\/revisions\/444"}],"wp:attachment":[{"href":"https:\/\/sites.bu.edu\/learningautonomy\/wp-json\/wp\/v2\/media?parent=395"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}
\nUniversity of Pennsylvania<\/span>
\nDeputy Director, GRASP Lab; <\/span>Graduate Program Chair, ROBO; <\/span>Associate Professor, MEAM<\/span>
\nMechanical Engineering and Applied Mechanics<\/span><\/p>\n