BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Hong_Kong
X-LIC-LOCATION:Asia/Hong_Kong
BEGIN:STANDARD
TZOFFSETFROM:+0800
TZOFFSETTO:+0800
TZNAME:HKT
DTSTART:19911015T033000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20251218T030657Z
LOCATION:Meeting Room S221\, Level 2
DTSTART;TZID=Asia/Hong_Kong:20251218T113400
DTEND;TZID=Asia/Hong_Kong:20251218T114500
UID:siggraphasia_SIGGRAPH Asia 2025_sess153_tog_105@linklings.com
SUMMARY:CHOICE: Coordinated Human-Object Interaction in Cluttered Environm
 ents for Pick-and-Place Actions
DESCRIPTION:Jintao Lu (The University of Hong Kong); He Zhang (Tencent Rob
 otics X); Yuting Ye, Takaaki Shiratori, and Sebastian Starke (Meta Reality
  Labs); and Taku Komura (The University of Hong Kong)\n\nAnimating human-s
 cene interactions, such as picking and placing a wide range of objects wit
 h different geometries, is a challenging task, especially in a cluttered e
 nvironment where interactions with complex articulated containers are invo
 lved. The main difficulty lies in the sparsity of the motion data compared
  to the wide variation of the objects and environments, as well as the poo
 r availability of transition motions between different actions, increasing
  the complexity of the generalization to arbitrary conditions. To cope wit
 h this issue, we develop a system that tackles the interaction synthesis p
 roblem as a hierarchical goal-driven task. Firstly, we develop a bimanual 
 scheduler that plans a set of keyframes for simultaneously controlling the
  two hands to efficiently achieve the pick-and-place task from an abstract
  goal signal, such as the target object selected by the user.  Next, we de
 velop a neural implicit planner that generates hand trajectories to guide 
 reaching and leaving motions across diverse object shapes/types and obstac
 le layouts. Finally, we propose a linear dynamic model for our DeepPhase c
 ontroller that incorporates a Kalman filter to enable smooth transitions i
 n the frequency domain, resulting in a more realistic and effective multi-
 objective control of the character. Our system can synthesize a rich varie
 ty of natural pick-and-place movements that adapt to different object geom
 etries, container articulations, and scene layouts.\n\nRegistration Catego
 ry: Full Access, Full Access Supporter\n\nSession Chair: Kai Wang (Simon F
 raser University)\n\n
END:VEVENT
END:VCALENDAR