BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
X-WR-CALNAME:Won Kyung Do PhD Defense: "Improving Robotic Dexterity with Op
 tical Tactile Sensor DenseTact"
X-WR-TIMEZONE:Pacific Time (US & Canada)
BEGIN:VEVENT
DTSTAMP:20260722T233026Z
UID:tag:localist.com\,2008:EventInstance_49418849691493
DTSTART:20250529T170000Z
DTEND:20250529T180000Z
DESCRIPTION:Dexterous manipulation - especially when objects are small\, cl
 uttered\, or partially occluded - remains a complex challenge in robotics.
  In this talk\, I present three approaches to tackling this problem using 
 DenseTact\, a family of soft\, vision‑based tactile sensors. First\, I s
 how how end‑effector design\, particularly the fingertip\, can provide r
 ich information during contact with the environment. The design of DenseTa
 ct and its successive improvements demonstrate how to sense and enhance ma
 nipulation through high‑resolution measurements of surface deformation a
 nd force. Next\, I describe a physics‑aware calibration pipeline for the
  optical tactile sensor that reconstructs the full stress field across the
  gel information crucial for manipulating diverse objects and environments
 . With these components in place\, I show how the calibrated sensors broad
 en the range of manipulation behaviors. Integrated into various types of g
 rippers\, such as the Leap Hand and an 8‑DOF rolling gripper\, DenseTact
 ’s tactile information improve the grasping of small objects and enable 
 complex\, contact‑rich behaviors via behavior cloning.
GEO:37.425884;-122.170436
LOCATION:Building 520\, 131
SUMMARY:Won Kyung Do PhD Defense: "Improving Robotic Dexterity with Optical
  Tactile Sensor DenseTact"
URL;VALUE=URI:https://events.stanford.edu/event/won-kyung-do-phd-defense-im
 proving-robotic-dexterity-with-optical-tactile-sensor-densetact
CATEGORIES:PhD Defense
END:VEVENT
END:VCALENDAR