BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Seoul
X-LIC-LOCATION:Asia/Seoul
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:KST
DTSTART:18871231T000000
DTSTART:19881009T020000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20230103T035312Z
LOCATION:Room 325-AB\, Level 3\, West Wing
DTSTART;TZID=Asia/Seoul:20221209T140000
DTEND;TZID=Asia/Seoul:20221209T153000
UID:siggraphasia_SIGGRAPH Asia 2022_sess178_papers_255@linklings.com
SUMMARY:Force-Aware Interface via Electromyography for Natural VR/AR Inter
 action
DESCRIPTION:Technical Communications, Technical Papers\n\nForce-Aware Inte
 rface via Electromyography for Natural VR/AR Interaction\n\nZhang, Liang, 
 Chen, Torrens, Atashzar...\n\nWhile tremendous advances in visual and audi
 tory realism have been made for virtual and augmented reality (VR/AR), int
 roducing a plausible sense of physicality into the virtual world remains c
 hallenging. Closing the gap between real-world physicality and immersive v
 irtual experience requires a closed interaction loop: applying user-exerte
 d physical forces to the virtual environment and generating haptic sensati
 ons back to the users. However, existing VR/AR solutions either completely
  ignore the force inputs from the users or rely on obtrusive sensing devic
 es that compromise user experience.\n\nBy identifying users' muscle activa
 tion patterns while engaging in VR/AR, we design a learning-based neural i
 nterface for natural and intuitive force inputs. Specifically, we show tha
 t lightweight electromyography sensors, resting non-invasively on users' f
 orearm skin, inform and establish a robust understanding of their complex 
 hand activities. Fuelled by a neural-network-based model, our interface ca
 n decode finger-wise forces in real-time with 3.3% mean error, and general
 ize to new users with little calibration. Through an interactive psychophy
 sical study, we show that human perception of virtual objects' physical pr
 operties, such as stiffness, can be significantly enhanced by our interfac
 e. We further demonstrate that our interface enables ubiquitous control vi
 a finger tapping. Ultimately, we envision our findings to push forward res
 earch towards more realistic physicality in future VR/AR.\n\nRegistration 
 Category: FULL ACCESS, ON-DEMAND ACCESS\n\nLanguage: ENGLISH\n\nFormat: IN
 -PERSON, ON-DEMAND
URL:https://sa2022.siggraph.org/en/full-program/?id=papers_255&sess=sess17
 8
END:VEVENT
END:VCALENDAR