BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
X-WR-CALNAME:Physics-Informed Learning and Control for Intelligent Transpor
 tation: Theory\, Algorithms\, and Experimental Validations
X-WR-TIMEZONE:Eastern Time (US & Canada)
BEGIN:VEVENT
DTSTAMP:20260817T043356Z
UID:tag:localist.com\,2008:EventInstance_49426245639405
DTSTART:20250423T150000Z
DTEND:20250423T160000Z
DESCRIPTION:Wednesday\, April 23\nSEC LL2.221\n11:00am\n\n \n\nPhysics-Info
 rmed Learning and Control for Intelligent Transportation: Theory\, Algorit
 hms\, and Experimental Validations\nZhe Fu\, Ph.D. Candidate\, University 
 of California Berkeley\n\n\nAbstract: The rapid growth of data science is 
 reshaping how we model and control physical infrastructure systems. Tradit
 ional PDE-based methods provide structured interpretability\, whereas pure
 ly data-driven neural networks offer flexibility but often lack adherence 
 to physical principles. In this talk\, I will present a physics-informed l
 earning and control framework that combines PDE-based modeling with neural
  networks\, enabling improved understanding and predictive accuracy of tra
 nsportation system dynamics. Specifically\, I will introduce a Neural Fini
 te Volume Method (NFVM) that preserves crucial physical properties\, effec
 tively bridging physics and data-driven approaches. Motivated by the poten
 tial of leveraging this improved understanding to influence real transport
 ation systems\, I developed control strategies using a small number of "le
 ader" vehicles to guide traffic flow toward greater efficiency and lower e
 nergy consumption\, with minimal system-wide intervention. These approache
 s include a kernel-based control method and an imitation learning strategy
 \, with variations validated in a large-scale operational field experiment
  involving 100 autonomous vehicles. I will conclude by highlighting ongoin
 g comparative studies to quantify how incorporating physics-informed model
 ing further enhances control performance in terms of efficiency\, safety\,
  and robustness.\n\n \n\nBio: Zhe Fu is a Ph.D. candidate in Transportatio
 n Engineering and an M.S. candidate in Electrical Engineering and Computer
  Sciences (EECS) at the University of California\, Berkeley. Her research 
 lies at the intersection of transportation systems\, control theory\, and 
 machine learning\, with the goal of enabling intelligent and energy-effici
 ent mobility in mixed autonomy environments. She has been recognized as a 
 2025 Eno Fellow and has received several national honors\, including the R
 ising Stars in NSF CPS Award (2025)\, Rising Stars in Mechanical Engineeri
 ng Award (2024)\, First Place Winner in the INFORMS Best Poster Competitio
 n (2023) and Second Place Winner in Berkeley Grad Slam (2025). Her leaders
 hip\, mentorship\, and teaching efforts have been recognized by UC Berkele
 y and external organizations such as ITS/CTF\, EDGE in Tech\, H2H8 and AAa
 /e.\n\n \n\nHost: Professor Heng Yang
GEO:42.363197;-71.127278
LOCATION:Science and Engineering Complex (SEC)\, SEC LL2.221
SUMMARY:Physics-Informed Learning and Control for Intelligent Transportatio
 n: Theory\, Algorithms\, and Experimental Validations
URL;VALUE=URI:https://events.seas.harvard.edu/event/physics-informed-learni
 ng-and-control-for-intelligent-transportation-theory-algorithms-and-experi
 mental-validations
CATEGORIES:Colloquia / Seminar / Lecture
END:VEVENT
END:VCALENDAR