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
UID:239636
DTSTAMP:20260727T095335Z
DTSTART;TZID=America/New_York:20260803T110000
DTEND;TZID=America/New_York:20260803T120000
URL;TYPE=URI:https://www.wpi.edu/news/calendar/events/robotics-engineering-
 masters-thesis-presentation-nehal-sonawane
SUMMARY:Robotics Engineering Masters Thesis Presentation: Nehal Sonawane
DESCRIPTION:Model-Free Generative Sampling of Continuum-Robot Configuration
 s for Vision-Based Motion Planning\n\n\nImage\n  \n\n\n\n  Image base Moti
 on Planning needs either a dense roadmap of valid configurations or a way 
 to sample valid robot configuration in the image space. Analytical models 
 of soft robots exist, but they might not be accurate due to material prope
 rties, discrepancies through construction. They also usually do not take i
 nto account the dynamic forces on the robot and might not be available for
  novel robots. The set of valid configurations needed for motion planning 
 can be acquired by moving the robot to collect data or learned efficiently
  through observations. Data efficiency is a central concern here as it tra
 nslates to long data collection hours.  This thesis attempt to understand 
 if the compositional structure of a multi-module origami robot can be used
  to make this problem tractable. We compare three families of generative m
 odels- flat (which treat the configuration as a single vector), graph stru
 ctured decoders (which attempt to learn the relationship between key point
 s) and a compositional network which trains a generative model on only 1 m
 odule and chains modules together using SE(2) transformations, building th
 e structure rather than learning it. The models are compared in simulation
 , where curve-fitting projection errors serve as a measure of sample valid
 ity, and performance is tracked as training set shrinks. Preliminary resul
 ts suggest that graph-structured decoders do not learn about the structure
  efficiently which motivates a closer look at the compositional model. The
  best model is then deployed on a multi-module origami arm to build a road
 map. The paths generated are then executed using visual servoing.\nAdvisor
 : Professor Berk CalliCommittee: Professor Vincent Aloi, Professor Griffn 
 Tabor\nZoom link: https://wpi.zoom.us/j/91655971603\n
END:VEVENT
END:VCALENDAR