About: Controlling three agents in a quarrel: Lessons learnt     Goto   Sponge   NotDistinct   Permalink

An Entity of Type : http://linked.opendata.cz/ontology/domain/vavai/Vysledek, within Data Space : linked.opendata.cz associated with source document(s)

AttributesValues
rdf:type
rdfs:seeAlso
Description
  • Steering behaviours can be used to position 3D embodied agents in small groups engaged in relatively simple social interactions such as in group conversation or walking while talking. Less is known about scaling these mechanisms for situations with complex dynamics requiring agents to perform actions beyond walking, turning, talking and gesturing. Here, we present a model for controlling three agents in an example of such a situation: a vigorous quarrel. The model combines a general steering behaviour for keeping the three agents in a triangular formation with a probabilistic two-level hierarchical state machine (hFSM) for unfolding the quarrel by means of changing parameters of the steering behaviour and issuing actions to the agents. The model has been implemented using UnrealEngine2Runtime on the example of a boy dating two girls at the same time who do not know about each other. The user can influence the course of the quarrel by changing attitudes among the agents. To create a list of the agents' actions and the hFSM, we video-taped about 40 episodes in which three actors improvised on the topic of the quarrel, and we manually annotated the videos. The evaluation with 67 human participants indicates that the model produces outcomes comprehensible and believable even for persons with limited previous experience with 3D graphics. On a more general level, this paper suggests that augmenting steering behaviours by a nontrivial higher-level controller is a feasible approach to modelling behaviour of 3D agents interacting in small groups in a complex way and presents a possible workflow for developing scenes featuring such agents.
  • Steering behaviours can be used to position 3D embodied agents in small groups engaged in relatively simple social interactions such as in group conversation or walking while talking. Less is known about scaling these mechanisms for situations with complex dynamics requiring agents to perform actions beyond walking, turning, talking and gesturing. Here, we present a model for controlling three agents in an example of such a situation: a vigorous quarrel. The model combines a general steering behaviour for keeping the three agents in a triangular formation with a probabilistic two-level hierarchical state machine (hFSM) for unfolding the quarrel by means of changing parameters of the steering behaviour and issuing actions to the agents. The model has been implemented using UnrealEngine2Runtime on the example of a boy dating two girls at the same time who do not know about each other. The user can influence the course of the quarrel by changing attitudes among the agents. To create a list of the agents' actions and the hFSM, we video-taped about 40 episodes in which three actors improvised on the topic of the quarrel, and we manually annotated the videos. The evaluation with 67 human participants indicates that the model produces outcomes comprehensible and believable even for persons with limited previous experience with 3D graphics. On a more general level, this paper suggests that augmenting steering behaviours by a nontrivial higher-level controller is a feasible approach to modelling behaviour of 3D agents interacting in small groups in a complex way and presents a possible workflow for developing scenes featuring such agents. (en)
Title
  • Controlling three agents in a quarrel: Lessons learnt
  • Controlling three agents in a quarrel: Lessons learnt (en)
skos:prefLabel
  • Controlling three agents in a quarrel: Lessons learnt
  • Controlling three agents in a quarrel: Lessons learnt (en)
skos:notation
  • RIV/00216208:11320/12:10126376!RIV13-GA0-11320___
http://linked.open...avai/riv/aktivita
http://linked.open...avai/riv/aktivity
  • P(GAP103/10/1287), S
http://linked.open...iv/cisloPeriodika
  • 7660
http://linked.open...vai/riv/dodaniDat
http://linked.open...aciTvurceVysledku
http://linked.open.../riv/druhVysledku
http://linked.open...iv/duvernostUdaju
http://linked.open...titaPredkladatele
http://linked.open...dnocenehoVysledku
  • 128740
http://linked.open...ai/riv/idVysledku
  • RIV/00216208:11320/12:10126376
http://linked.open...riv/jazykVysledku
http://linked.open.../riv/klicovaSlova
  • quarrel simulation; steerings; artificial intelligence; virtual agents (en)
http://linked.open.../riv/klicoveSlovo
http://linked.open...odStatuVydavatele
  • DE - Spolková republika Německo
http://linked.open...ontrolniKodProRIV
  • [484F879A8A5D]
http://linked.open...i/riv/nazevZdroje
  • Lecture Notes in Computer Science
http://linked.open...in/vavai/riv/obor
http://linked.open...ichTvurcuVysledku
http://linked.open...cetTvurcuVysledku
http://linked.open...vavai/riv/projekt
http://linked.open...UplatneniVysledku
http://linked.open...v/svazekPeriodika
  • 7660
http://linked.open...iv/tvurceVysledku
  • Brom, Cyril
  • Gemrot, Jakub
  • Bída, Michal
  • Popelová, Markéta
  • Tomek, Jakub
  • Babor, Petr
issn
  • 0302-9743
number of pages
http://bibframe.org/vocab/doi
  • 10.1007/978-3-642-34710-8_15
http://localhost/t...ganizacniJednotka
  • 11320
Faceted Search & Find service v1.16.118 as of Jun 21 2024


Alternative Linked Data Documents: ODE     Content Formats:   [cxml] [csv]     RDF   [text] [turtle] [ld+json] [rdf+json] [rdf+xml]     ODATA   [atom+xml] [odata+json]     Microdata   [microdata+json] [html]    About   
This material is Open Knowledge   W3C Semantic Web Technology [RDF Data] Valid XHTML + RDFa
OpenLink Virtuoso version 07.20.3240 as of Jun 21 2024, on Linux (x86_64-pc-linux-gnu), Single-Server Edition (126 GB total memory, 48 GB memory in use)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software