BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.4.5//EN
TZID:America/New_York
X-WR-TIMEZONE:America/New_York
BEGIN:VEVENT
UID:0-8727@eng.ufl.edu
DTSTART;TZID=America/New_York:20260910T124000
DTEND;TZID=America/New_York:20260910T134000
DTSTAMP:20260902T131133Z
URL:https://www.eng.ufl.edu/news-events/events/mae-seminar-learning-optimi
 zation-and-control-for-assured-data-driven-autonomy/
SUMMARY:MAE Seminar: Learning\, optimization\, and control for assured data
 -driven autonomy
DESCRIPTION:MAE Seminar: Learning\, optimization\, and control for assured 
 data-driven autonomy\nDate: September 10\, 2026\nTime: 12:50 PM Location: 
 MAE-A 303\n\nDr. Rushikesh Kamalapurkar\nAssociate Professor\nDepartment o
 f Mechanical and Aerospace Engineering\nUniversity of Florida\n\nAbstract\
 nIn an effort to automate increasingly complex cyber-physical systems\, wh
 ere first-principles models of the underlying physical processes are eithe
 r poorly understood or computationally taxing\, practitioners of autonomy 
 have gravitated towards data-driven modeling and control techniques. Howev
 er\, many data-driven methods still lack the theoretical guarantees requir
 ed for safety-critical autonomy. My research program develops the mathemat
 ical foundations needed to integrate data-driven models into autonomous ar
 chitectures while preserving system-theoretic guarantees of stability\, pe
 rformance\, and safety.\n\nIn this talk\, I will highlight the adaptive op
 timal control (AOC) techniques developed by my lab. AOC techniques have be
 en studied in detail over the past decade and have proven effective in add
 ressing a variety of autonomy challenges. Originally developed for traditi
 onal control tasks such as set-point regulation and trajectory tracking\, 
 these techniques have since been applied to complex objectives including s
 afe learning\, imitation learning\, missions specified via temporal logic\
 , herding control\, and game-theoretic deception. In this talk\, I will di
 scuss the foundations of adaptive optimal control\, highlight the technica
 l challenges in the application of adaptive optimal control to partially o
 bserved systems with safety constraints\, and illustrate various technique
 s developed by my students to solve the safe adaptive optimal control prob
 lem.\n\nBiography\nRushikesh Kamalapurkar received his M.S. and his Ph.D. 
 degree in 2011 and 2014\, respectively\, from the Department of Mechanical
  and Aerospace Engineering at the University of Florida. In 2016\, he join
 ed the School of Mechanical and Aerospace Engineering at the Oklahoma Stat
 e University as an Assistant professor. Since 2024\, he has served as an a
 ssociate professor in the Department of Mechanical and Aerospace Engineeri
 ng at the University of Florida. His primary research interest is intellig
 ent\, learning-based optimal control of uncertain nonlinear dynamical syst
 ems. He has published a book\, multiple book chapters\, over 50 peer-revie
 wed journal papers and over 50 peer-reviewed conference papers. His work h
 as been recognized by a 2026 ASHRAE Science and Technology for the Built E
 nvironment Best Paper Award and a 2022 Oklahoma State University School of
  Mechanical and Aerospace Engineering Researcher of the Year award.\n\nFac
 ulty Host: Dr. John Schueller
CATEGORIES:Seminars
END:VEVENT
BEGIN:VTIMEZONE
TZID:America/New_York
X-LIC-LOCATION:America/New_York
BEGIN:DAYLIGHT
DTSTART:20260308T030000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
END:DAYLIGHT
END:VTIMEZONE
END:VCALENDAR