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
220576
20250808T134630Z
DTSTART;TZID=America/New_York:20250811T120000
DTEND;TZID=America/New_York:2
 0250811T130000
URL;TYPE=URI:/news/calendar/events/compu
 ter-science-department-ms-thesis-presentation-isabella-feeney-visual-conta
 ct-detection-hand
Computer Science Department , MS Thesis Presentation, Isabella Feeney "Visual Contact Detection for In-Hand Manipulation"
Isabella Feeney\nMS student\nWPI 鈥?Computer Science Department\n\n\nMonday, August 11, 2025\nTime:
  12:00 pm 鈥?1:00 PM\nZoom Link:https://wpi.zoom.us/j/99058582614\n\nAdvi
 sor :Prof. Berk Calli, WPI 鈥?RBE Department\nReader :Prof. Joshua Cuneo 
 , WPI 鈥?Computer Science Department\n\nAbstract:\nIn-hand manipulation i
 nvolves changing the pose of an object within a hand without\nthe need to 
 put it down and regrasp it. While this is a common skill for humans,\nsuch
  as picking up a cell phone and shifting its position to view the screen, 
 in-\nhand manipulation remains a significant challenge for robots. This pr
 oject proposes\nusing visual pose-tracking tools to accurately estimate th
 e position of the object\nin hand, enabling closed-loop control of in-hand
  manipulation for robotic systems.\n\nWe develop an algorithm to account f
 or the physical constraints present during\nin-hand manipulation, increasi
 ng the accuracy of the estimation. Specifically, we\naccount for the knowl
 edge that the surface of the object must be in contact with the\nrobotic h
 and, but not intersecting it, while the object is grasped. We then conduct
 \nseveral experiments to determine optimal heuristics for our estimation a
 lgorithm,\nprioritizing solutions that are closest to the original predict
 ed pose of the object.\nUsing this baseline, we move on to testing our met
 hod on manipulation tasks using a\nreal robotic gripper. Finally, we evalu
 ate the performance of this algorithm against\nthe standard pose estimatio
 n method.\n\n\n\n\n
END:VEVENT
END:VCALENDAR