BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//UM//UM*Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/Detroit
TZURL:http://tzurl.org/zoneinfo/America/Detroit
X-LIC-LOCATION:America/Detroit
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20070311T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20071104T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260220T143001
DTSTART;TZID=America/Detroit:20260223T140000
DTEND;TZID=America/Detroit:20260223T160000
SUMMARY:Presentation:Multi-modal Representation Learning for Contact-rich and Dexterous Manipulation
DESCRIPTION:Co-Chairs: Dmitry Berenson and Nima Fazeli\n\nAbstract:\nMy PhD research focuses on representation learning with force and touch for contact rich\, dexterous robot manipulation. Recent robot learning has made major progress in vision and language\, but those modalities alone cannot fully capture physical interaction in robot manipulation tasks. Tasks like cleaning\, assembly\, and assistive care require robots to reason about contact and force\, especially in the presence of sensor noise and visual occlusion. My work develops learning based methods that integrate force and tactile sensing into robot learning and control. I build object centric multi-modal (vision and touch) representations to infer object state and contact under noise and occlusion\, design contact aware planning and control frameworks with learned dynamics to regulate interaction that effectively integrated with language modality\, and develop shared tactile representations that align human and robot touch signals for cross embodiment policy transfer. Overall\, this dissertation studies how force\, touch\, and contact can improve robotic dexterity in contact rich manipulation.\n\nZoom:\nhttps://umich.zoom.us/j/95094568449\nMeeting ID: 950 9456 8449\nPasscode: 837399
UID:145782-21897810@events.umich.edu
URL:https://events.umich.edu/event/145782
CLASS:PUBLIC
STATUS:CONFIRMED
CATEGORIES:Michigan Robotics,Robotics
LOCATION:Ford Robotics Building - 2300
CONTACT:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260223T142051
DTSTART;TZID=America/Detroit:20260223T150000
DTEND;TZID=America/Detroit:20260223T160000
SUMMARY:Workshop / Seminar:ACUM CES: Findings from a Survey Characterizing Advisors' and Coaches' Experiences and Perceptions with Validating Approaches
DESCRIPTION:The Student Success Initiative (SSI) coming out of the Office for the Vice Provost of Undergraduate Education seeks to create data-informed change that promotes the holistic success of students at the University of Michigan. Recognizing the importance that advising and coaching play in students’ academic journeys\, one focus of the SSI is to enhance advising and coaching at U-M for both students and advisors and coaches\, such as through the implementation of training on a validation approach to advising and coaching (with training planned to begin in Sp/Su 2026). To support these efforts\, we—Dr. Solaire Finkenstaedt-Quinn (Assessment and Evaluation Specialist for the SSI) and Natalie Drobny and Gray Strain (Evaluation Advising Fellows)—are working to understand the current advising landscape at U-M and how it shifts over time as validation training is implemented. During this CES\, we will begin by presenting our findings from a survey that characterizes U-M advisors’ and coaches’ knowledge and use of approaches that align with validation theory and the mission and framework developed by the Academic Advising & Coaching Team. To close off the session\, we hope to engage advisors and coaches in a conversation about how our findings can be used to inform changes in advising and coaching at U-M.
UID:144758-21895820@events.umich.edu
URL:https://events.umich.edu/event/144758
CLASS:PUBLIC
STATUS:CONFIRMED
CATEGORIES:Sessions
LOCATION:R1220 Ross School of Business
CONTACT:
END:VEVENT
END:VCALENDAR