BEGIN:VCALENDAR
CALSCALE:GREGORIAN
VERSION:2.0
METHOD:PUBLISH
PRODID:-//Drupal iCal API//EN
X-WR-TIMEZONE:America/New_York
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
DTSTART:20070311T020000
TZNAME:EDT
TZOFFSETTO:-0400
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
DTSTART:20071104T020000
TZNAME:EST
TZOFFSETTO:-0500
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
SEQUENCE:1
X-APPLE-TRAVEL-ADVISORY-BEHAVIOR:AUTOMATIC
198531
20250131T112952Z
DTSTART;TZID=America/New_York:20250205T130000
DTEND;TZID=America/New_York:2
 0250205T140000
URL;TYPE=URI:/news/calendar/events/rbe-c
 olloquium-speaker-dr-yifan-zhu
RBE Colloquium Speaker - Dr. Yifan Zhu
Data-Efficient Visual-Tactile World Models for Robot Deployment in the Open World\n\n\n\n      \n      \n\n\n\nAbstract:
 \nDespite recent advances in robotics, the robust deployment of robots in 
 the open world for practical tasks remains a formidable challenge. A signi
 ficant roadblock is that robots lack a fundamental understanding of their 
 interaction with the physical world, especially in new scenarios. Traditio
 nal model-based approaches utilize geometry primitives and physics models,
  which require significant prior knowledge and fail in the unknown. On the
  other hand, deep-learning-based approaches are extremely data-hungry and 
 brittle against distribution shifts. In this talk, I will talk about how I
  developed robot world model representations that tightly integrate physic
 s modeling and machine learning to allow data-efficient and accurate world
  models for contact-rich tasks involving rigid bodies, granular media, and
  deformable objects. Next, I will discuss how I tailor the world model rep
 resentations to downstream active perception to allow fast adaptation of t
 he world models with sparse online visual-tactile data. Following this, I 
 will briefly talk about how I leveraged the learned world models for plann
 ing locomotion and manipulation tasks, and designed low-cost robot hardwar
 e with multi-sensory capabilities, which is a prerequisite towards buildin
 g predictive world models from multi-modal sensing. Finally, I will conclu
 de with my future research directions in representing, acquiring, and usin
 g robot world models for contact-rich tasks in the open world.\nBio:\nYifa
 n Zhu is currently a postdoctoral research associate in the Mechanical Eng
 ineering and Materials Science Department at Yale University. Prior to thi
 s, he obtained a Ph.D. degree in the Computer Science Department at the Un
 iversity of Illinois Urbana-Champaign and a B.E. degree in the Mechanical 
 Engineering Department at Vanderbilt University. His research centers arou
 nd developing representations for robots that facilitate tight integration
  of physics modeling and machine learning for predictive world modeling fr
 om visual-tactile perceptions, especially in the low-data regime. His rese
 arch has been featured in top-tier robotics venues such as R:SS, ICRA, IRO
 S, RA-L, and IJSR. He also co-led the UIUC team in placing 4-th in the $10
 M ANA Avatar XPRIZE competition.\nZoom link: https://wpi.zoom.us/j/9341334
 9160\n
END:VEVENT
END:VCALENDAR