Zur Kurzanzeige

Using enriched semantic event chains to model human action prediction based on (minimal) spatial information

dc.contributor.authorZiaeetabar, Fatemeh
dc.contributor.authorPomp, Jennifer
dc.contributor.authorPfeiffer, Stefan
dc.contributor.authorEl-Sourani, Nadiya
dc.contributor.authorSchubotz, Ricarda I.
dc.contributor.authorTamosiunaite, Minija
dc.contributor.authorWörgötter, Florentin
dc.date.accessioned2021-05-18T09:39:47Z
dc.date.available2021-05-18T09:39:47Z
dc.date.issued2020de
dc.identifier.urihttp://resolver.sub.uni-goettingen.de/purl?gs-1/17807
dc.description.abstractPredicting other people’s upcoming action is key to successful social interactions. Previous studies have started to disentangle the various sources of information that action observers exploit, including objects, movements, contextual cues and features regarding the acting person’s identity. We here focus on the role of static and dynamic inter-object spatial relations that change during an action. We designed a virtual reality setup and tested recognition speed for ten different manipulation actions. Importantly, all objects had been abstracted by emulating them with cubes such that participants could not infer an action using object information. Instead, participants had to rely only on the limited information that comes from the changes in the spatial relations between the cubes. In spite of these constraints, participants were able to predict actions in, on average, less than 64% of the action’s duration. Furthermore, we employed a computational model, the so-called enriched Semantic Event Chain (eSEC), which incorporates the information of different types of spatial relations: (a) objects’ touching/untouching, (b) static spatial relations between objects and (c) dynamic spatial relations between objects during an action. Assuming the eSEC as an underlying model, we show, using information theoretical analysis, that humans mostly rely on a mixed-cue strategy when predicting actions. Machine-based action prediction is able to produce faster decisions based on individual cues. We argue that human strategy, though slower, may be particularly beneficial for prediction of natural and more complex actions with more variable or partial sources of information. Our findings contribute to the understanding of how individuals afford inferring observed actions’ goals even before full goal accomplishment, and may open new avenues for building robots for conflict-free human-robot cooperation.de
dc.description.sponsorshipOpen-Access-Publikationsfonds 2020
dc.language.isoengde
dc.rightsopenAccess
dc.rightsNamensnennung 4.0 International*
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/*
dc.subject.ddc530
dc.titleUsing enriched semantic event chains to model human action prediction based on (minimal) spatial informationde
dc.typejournalArticlede
dc.identifier.doi10.1371/journal.pone.0243829
dc.identifier.doi10.1371/journal.pone.0243829.g001
dc.identifier.doi10.1371/journal.pone.0243829.g002
dc.identifier.doi10.1371/journal.pone.0243829.g003
dc.identifier.doi10.1371/journal.pone.0243829.g004
dc.identifier.doi10.1371/journal.pone.0243829.g005
dc.identifier.doi10.1371/journal.pone.0243829.g006
dc.identifier.doi10.1371/journal.pone.0243829.g007
dc.identifier.doi10.1371/journal.pone.0243829.g008
dc.identifier.doi10.1371/journal.pone.0243829.g009
dc.identifier.doi10.1371/journal.pone.0243829.g010
dc.identifier.doi10.1371/journal.pone.0243829.g011
dc.identifier.doi10.1371/journal.pone.0243829.t001
dc.identifier.doi10.1371/journal.pone.0243829.s001
dc.identifier.doi10.1371/journal.pone.0243829.s002
dc.identifier.doi10.1371/journal.pone.0243829.s003
dc.identifier.doi10.1371/journal.pone.0243829.s004
dc.identifier.doi10.1371/journal.pone.0243829.r001
dc.identifier.doi10.1371/journal.pone.0243829.r002
dc.identifier.doi10.1371/journal.pone.0243829.r003
dc.identifier.doi10.1371/journal.pone.0243829.r004
dc.identifier.doi10.1371/journal.pone.0243829.r005
dc.type.versionpublishedVersionde
dc.relation.eISSN1932-6203
dc.bibliographicCitation.volume15de
dc.bibliographicCitation.issue12de
dc.bibliographicCitation.firstPagee0243829de
dc.type.subtypejournalArticle
dc.description.statuspeerReviewedde
dc.bibliographicCitation.journalPLOS ONEde


Dateien zu dieser Ressource

Thumbnail
Thumbnail

Das Dokument erscheint in:

Zur Kurzanzeige

Nutzungslizenz für diese Dokumente:
openAccess