BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:IC Colloquium: Learning to interact with the world: when generalit
 y meets precision
DTSTART:20220328T100000
DTEND:20220328T110000
DTSTAMP:20260415T183650Z
UID:3b4f20f198b39b5d9222cd822d5a89ceb0aa5d5f3996dab9a9d048b6
CATEGORIES:Conferences - Seminars
DESCRIPTION:By: Maria Bauza Villalonga - MIT\n\nIC Faculty candidate\n\nAb
 stract\nRobotics stands as one of the most impactful and promising endeavo
 rs of our times. Learning to interact with the world is fundamental for so
 lving some of our most pressing societal challenges:from taking care of ou
 r aging population and aiding with labor-intensive jobs to assisting in cl
 imate-related disasters and rescue emergencies. In this talk\, I will argu
 e that such a level of autonomy and performance requires robots that can e
 xcel across diverse settings while\nremaining accurate and reliable.\n\nMy
  talk will focus on how we can develop learning algorithms that foster rob
 otic generalization while ensuring the desired task performance. First\, I
  will present a learning approach to pose estimation for novel objects bas
 ed on visuo-tactile sensing that doesn’t rely on real data and results i
 n accurate pose distributions. Then\, I will demonstrate how this approach
  enables precise robotic pick-and-place using task-aware grasping. The rob
 otic system reasons over the models for grasping\, planning\, and percepti
 on in order to optimize its actions based only on simulated data. In real 
 experiments\, we demonstrate that our approach learned purely in simulatio
 n\, allows robots to successfully manipulate new objects and perform highl
 y accurate placements.\n\nBio\nMaria Bauza Villalonga is a PhD student in 
 Robotics at the Massachusetts Institute of Technology\, working with Profe
 ssor Alberto Rodriguez. Before that\, she received Bachelor’s degrees in
  Mathematics and Physics from CFIS\, an excellence center at the Polytechn
 ic University of Catalonia. Her research focuses on achieving precise robo
 tic generalization by learning probabilistic models of the world that allo
 w robots to reuse their skills across multiple\ntasks and environments. Ma
 ria has received several fellowships\, including Facebook\, NVIDIA\, and L
 aCaixa fellowships. Her research has obtained awards such as Best Paper Fi
 nalist in Service Robotics at ICRA 2021\, Best Cognitive Paper award at IR
 OS 2018\, and Best Paper award finalist at IROS 2016.\nShe was also part o
 f the MIT-Princeton Team participating in the Amazon Robotics Challenge\, 
 winning the stowing task in 2017 and receiving the 2018 Amazon Best System
 s Paper Award in Manipulation.\n\nMore information
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420 https://epfl.zoom.us/
 j/62020514487?pwd=bU9SU2xpL2VXRk1hOXRUYlJnVWdIdz09
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR