BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
X-WR-CALNAME:Seminar @ Cornell Tech: Maria Bauza Villalonga
X-WR-TIMEZONE:Eastern Time (US & Canada)
BEGIN:VEVENT
DTSTAMP:20261018T005440Z
UID:tag:localist.com\,2008:EventInstance_39059594895900
DTSTART:20220207T153000Z
DTEND:20220207T163000Z
DESCRIPTION:Learning to Interact with the World\n\nWhen generality meets pr
 ecision Abstract Robotics stands as one of the most impactful and promisin
 g endeavors of our times. Learning to interact with the world is fundament
 al for solving some of our most pressing societal challenges: from taking 
 care of our aging population and aiding with labor-intensive jobs to assis
 ting in climate-related disasters and rescue emergencies. In this talk\, I
  will argue that such a level of autonomy and performance requires robots 
 that can excel across diverse settings while remaining accurate and reliab
 le. My talk will focus on how we can develop learning algorithms that fost
 er robotic generalization while ensuring the desired task performance. Fir
 st\, I will present a learning approach to pose estimation for novel objec
 ts based on visuo-tactile sensing that doesn’t rely on real data and res
 ults in accurate pose distributions. Then\, I will demonstrate how this ap
 proach enables precise robotic pick-and-place using task-aware grasping. T
 he robotic system reasons over the models for grasping\, planning\, and pe
 rception in order to optimize its actions based only on simulated data. In
  real experiments\, we demonstrate that our approach learned purely in sim
 ulation\, allows robots to successfully manipulate new objects and perform
  highly accurate placements.\n\n \n\nSpeaker Bio\n\nWorking with Professor
  Alberto Rodriguez. Before that\, she received Bachelor’s degrees in Mat
 hematics and Physics from CFIS\, an excellence center at the Polytechnic U
 niversity of Catalonia. Her research focuses on achieving precise robotic 
 generalization by learning probabilistic models of the world that allow ro
 bots to reuse their skills across multiple tasks and environments. Maria h
 as received several fellowships\, including Facebook\, NVIDIA\, and LaCaix
 a fellowships. Her research has obtained awards such as Best Paper Finalis
 t in Service Robotics at ICRA 2021\, Best Cognitive Paper award at IROS 20
 18\, and Best Paper award finalist at IROS 2016. She was also part of the 
 MIT-Princeton Team participating in the Amazon Robotics Challenge\, winnin
 g the stowing task in 2017 and receiving the 2018 Amazon Best Systems Pape
 r Award in Manipulation.
LOCATION:Cornell Tech\, Bloomberg Center\, Room 401
SUMMARY:Seminar @ Cornell Tech: Maria Bauza Villalonga
URL;VALUE=URI:https://events.cornell.edu/event/seminar_cornell_tech_maria_b
 auza_villalonga
CATEGORIES:Seminar
END:VEVENT
END:VCALENDAR