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:20260114T163633Z
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_523@linklings.com
SUMMARY:Adaptive Tracking of a Single-Rigid-Body Character in Various Envi
 ronments
DESCRIPTION:Taesoo Kwon, Taehong Gu, Jaewon Ahn, and Yoonsang Lee (Hanyang
  University)\n\nSince the introduction of DeepMimic [Peng et al. 2018], su
 bsequent research\nhas focused on expanding the repertoire of simulated mo
 tions across various\nscenarios. In this study, we propose an alternative 
 approach for this goal,\na deep reinforcement learning method based on the
  simulation of a single-\nrigid-body character. Using the centroidal dynam
 ics model (CDM) to express\nthe full-body character as a single rigid body
  (SRB) and training a policy to\ntrack a reference motion, we can obtain a
  policy that is capable of adapting\nto various unobserved environmental c
 hanges and controller transitions\nwithout requiring any additional learni
 ng. Due to the reduced dimension\nof state and action space, the learning 
 process is sample-efficient. The final\nfull-body motion is kinematically 
 generated in a physically plausible way,\nbased on the state of the simula
 ted SRB character. The SRB simulation is\nformulated as a quadratic progra
 mming (QP) problem, and the policy outputs\nan action that allows the SRB 
 character to follow the reference motion. We\ndemonstrate that our policy,
  efficiently trained within 30 minutes on an\nultraportable laptop, has th
 e ability to cope with environments that have\nnot been experienced during
  learning, such as running on uneven terrain\nor pushing a box, and transi
 tions between learned policies, without any\nadditional learning.\n\nRegis
 tration Category: Full Access, Enhanced Access, Trade Exhibitor, Experienc
 e Hall Exhibitor\n\n
URL:https://asia.siggraph.org/2023/full-program?id=papers_523&sess=sess209
END:VEVENT
END:VCALENDAR