BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/New_York
X-LIC-LOCATION:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20221109T183714Z
LOCATION:A706
DTSTART;TZID=America/New_York:20221013T140600
DTEND;TZID=America/New_York:20221013T142400
UID:HFESAM_HFES 66th International Annual Meeting_sess176_LECT294@linkling
 s.com
SUMMARY:Deep Learning-based human activity recognition using RGB images in
  Human-robot collaboration
DESCRIPTION:Lecture\n\nDeep Learning-based human activity recognition usin
 g RGB images in Human-robot collaboration\n\nKeshinro, Seong, Yi\n\nIn hum
 an-robot interaction, to ensure safety and effectiveness, robots need to b
 e able to accurately predict human intentions. Hidden Markov Model, Bayesi
 an Filtering, and deep learning methods have been used to predict human in
 tentions. However, few studies have explored deep learning methods to pred
 ict variant human intention. Our study aims to evaluate the performance of
  the human intent recognition inference algorithm, and its impact on the h
 uman-robot team for collaborative tasks. Two deep learning algorithms Conv
 LSTM and LRCN were used to predict human intention. A dataset of 10 partic
 ipants performing Pick, Throw, Wave, and Carry actions was used. The ConvL
 STM method had a prediction accuracy of 74%. The LRCN method had a lower p
 rediction accuracy of 25% compared to ConvLSTM. This result shows that dee
 p learning methods using RGB images can predict human intent with high acc
 uracy. The proposed method is successful in predicting human intents under
 lying human behavior.\n\nTrack: Human AI Robot Teaming (HART), Human Perfo
 rmance Modeling
END:VEVENT
END:VCALENDAR