BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Australia/Melbourne
X-LIC-LOCATION:Australia/Melbourne
BEGIN:DAYLIGHT
TZOFFSETFROM:+1000
TZOFFSETTO:+1100
TZNAME:AEDT
DTSTART:19721003T020000
RRULE:FREQ=YEARLY;BYMONTH=4;BYDAY=1SU
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:19721003T020000
TZOFFSETFROM:+1100
TZOFFSETTO:+1000
TZNAME:AEST
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20240214T070240Z
LOCATION:Darling Harbour Theatre\, Level 2 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231212T093000
DTEND;TZID=Australia/Melbourne:20231212T124500
UID:siggraphasia_SIGGRAPH Asia 2023_sess209_papers_443@linklings.com
SUMMARY:Discovering Fatigued Movements for Virtual Character Animation
DESCRIPTION:Technical Papers\n\nNoshaba Cheema (German Research Center for
  Artificial Intelligence, Max-Planck Institute for Informatics); Rui Xu (G
 erman Research Center for Artificial Intelligence, Saarland University); N
 am Hee Kim and Perttu Hämäläinen (Aalto University); Vladislav Golyanik an
 d Marc Habermann (Max-Planck-Institut für Informatik); Christian Theobalt 
 (Max-Planck-Institut für Informatik, Saarland University); and Philipp Slu
 sallek (Saarland University, German Research Center for Artificial Intelli
 gence)\n\nVirtual character animation and movement synthesis have advanced
  rapidly during recent years, especially through a combination of extensiv
 e motion capture datasets and machine learning. A remaining challenge is i
 nteractively simulating characters that fatigue when performing extended m
 otions, which is indispensable for the realism of generated animations. Ho
 wever, capturing such movements is problematic, as performing movements li
 ke backflips with fatigued variations up to exhaustion raises capture cost
  and risk of injury. Surprisingly, little research has been done on faithf
 ul fatigue modeling. To address this, we propose a deep reinforcement lear
 ning-based approach, which---for the first time in literature---generates 
 control policies for full-body physically simulated agents aware of cumula
 tive fatigue. For this, we first leverage Generative Adversarial Imitation
  Learning (GAIL) to learn an expert policy for the skill; Second, we learn
  a fatigue policy by limiting the generated constant torque bounds based o
 n endurance time to non-linear, state- and time-dependent limits in the jo
 int-actuation space using a Three-Compartment Controller (3CC) model. Our 
 results demonstrate that agents can adapt to different fatigue and rest ra
 tes interactively, and discover realistic recovery strategies without the 
 need for any captured data of fatigued movement.\n\nRegistration Category:
  Full Access, Enhanced Access, Trade Exhibitor, Experience Hall Exhibitor
URL:https://asia.siggraph.org/2023/full-program?id=papers_443&sess=sess209
END:VEVENT
END:VCALENDAR