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:20230103T035307Z
LOCATION:Auditorium\, Level 5\, West Wing
DTSTART;TZID=Asia/Seoul:20221206T100000
DTEND;TZID=Asia/Seoul:20221206T120000
UID:siggraphasia_SIGGRAPH Asia 2022_sess153_papers_262@linklings.com
SUMMARY:PADL: Language-Directed Physics-Based Character Control
DESCRIPTION:Technical Papers\n\nPADL: Language-Directed Physics-Based Char
 acter Control\n\nJuravsky, Guo, Fidler, Peng\n\nDeveloping systems that ca
 n synthesize natural and life-like motions for simulated characters has lo
 ng been a focus for computer animation. But in order for these systems to 
 be useful for downstream applications, they need not only produce high-qua
 lity motions, but must also provide an accessible and versatile interface 
 through which users can direct a character's behaviors. Natural language p
 rovides a simple-to-use and expressive medium for specifying a user's inte
 nt. Recent breakthroughs in natural language processing (NLP) have demonst
 rated effective use of language-based interfaces for applications such as 
 image generation and program synthesis. In this work, we present PADL, whi
 ch leverages recent innovations in NLP in order to take steps towards deve
 loping language-directed controllers for physics-based character animation
 . PADL allows users to issue natural language commands for specifying both
  high-level tasks and low-level skills that a character should perform. We
  present an adversarial imitation learning approach for training policies 
 to map high-level language commands to low-level controls that enable a ch
 aracter to perform the desired task and skill specified by a user's comman
 ds. Furthermore, we propose a multi-task aggregation method that leverages
  a language-based multiple-choice question-answering approach to determine
  high-level task objectives from a language command. We show that our fram
 ework can be applied to effectively direct a simulated humanoid character 
 to perform a diverse array of complex motor skills.\n\nRegistration Catego
 ry: FULL ACCESS, EXPERIENCE PLUS ACCESS, EXPERIENCE ACCESS, TRADE EXHIBITO
 R\n\nLanguage: ENGLISH\n\nFormat: IN-PERSON
URL:https://sa2022.siggraph.org/en/full-program/?id=papers_262&sess=sess15
 3
END:VEVENT
END:VCALENDAR