BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:AI Center x Sony AI Impact Talk Mireille El Gheche - Learning to P
 lay at Human Speed: From Simulation to Expert-Level Robot Table Tennis
DTSTART:20261015T101500
DTEND:20261015T111500
DTSTAMP:20260928T162019Z
UID:5894caa31ae89c5e126448609a0d74d2425cbb098ed581aec62ab582
CATEGORIES:Conferences - Seminars
DESCRIPTION:Dr. Mireille El Gheche\nRegistration with an EPFL email is re
 quired: HERE.\n\n! This event is restricted to the EPFL community !\n\nTit
 le\nLearning to Play at Human Speed: From Simulation to Expert-Level Robot
  Table Tennis\n\nAbstract\nWhat does it take for a robot to compete with a
  human in one of the fastest and most dynamic sports?\nTable tennis compre
 sses many of the fundamental challenges of physical AI into just a few hun
 dred milliseconds. The robot must perceive a ball travelling at high speed
 \, estimate its position and spin\, predict its trajectory\, decide how to
  respond\, and execute a precise motion\, all while interacting with an in
 telligent and unpredictable opponent.\nIn this talk\, I will present Proje
 ct ACE\, an autonomous table tennis robot developed at Sony AI that progre
 ssed from learning basic racket skills to competing with elite human playe
 rs. I will discuss the complete system behind this progression: high-speed
  visual perception\, reinforcement learning\, simulation\, robot control\,
  and the iterative sim-to-real process that enabled policies trained in si
 mulation to perform on a real robot. Beyond table tennis\, ACE provides a 
 case study in what it takes to move from impressive robotic demonstrations
  to robust physical intelligence. I will share some of the lessons we lear
 ned about combining learning with control\, using real-world failures to i
 mprove simulation\, and designing AI systems that can adapt and act under 
 the speed\, uncertainty\, and constraints of the physical world.\n\nBio\nM
 ireille El Gheche is a Lead Research Scientist at SoftBank Robotics\, work
 ing at the intersection of artificial intelligence and robotics. Her exper
 tise spans reinforcement learning\, computer vision and perception\, simul
 ation\, optimization\, and real-world robotic systems\, with a strong focu
 s on translating research advances into robust physical systems.\nPrior to
  joining SoftBank Robotics\, Mireille was a Staff Research Scientist at So
 ny AI in Zurich\, where she led research on Project ACE\, an autonomous t
 able tennis robot developed to compete with elite and professional human p
 layers. Before joining Sony AI\, Mireille conducted academic research at 
 EPFL and the University of Bordeaux\, working across computer vision\, a
 nd applied AI\, including applications in medical AI. Her broader research
  interests lie in physical AI and intelligent robotic systems that can pe
 rceive\, learn\, adapt\, and act in complex real-world environments.\n 
LOCATION:SG 0213 https://plan.epfl.ch/?room==SG%200213
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR