Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Learning Graph-Structured Sum-Product Networks for Probabilistic Semantic Maps
Univ Washington, Paul G Allen Sch Comp Sci & Engn, Seattle, WA 98195 USA..
KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL. Univ Washington, Paul G Allen Sch Comp Sci & Engn, Seattle, WA 98195 USA..ORCID-id: 0000-0002-1396-0102
Univ Washington, Paul G Allen Sch Comp Sci & Engn, Seattle, WA 98195 USA..
2018 (engelsk)Konferansepaper, Publicerat paper (Fagfellevurdert)
Abstract [en]

We introduce Graph-Structured Sum-Product Networks (GraphSPNs), a probabilistic approach to structured prediction for problems where dependencies between latent variables are expressed in terms of arbitrary, dynamic graphs. While many approaches to structured prediction place strict constraints on the interactions between inferred variables, many real-world problems can be only characterized using complex graph structures of varying size, often contaminated with noise when obtained from real data. Here, we focus on one such problem in the domain of robotics. We demonstrate how GraphSPNs can be used to bolster inference about semantic, conceptual place descriptions using noisy topological relations discovered by a robot exploring large-scale office spaces. Through experiments, we show that GraphSPNs consistently outperform the traditional approach based on undirected graphical models, successfully disambiguating information in global semantic maps built from uncertain, noisy local evidence. We further exploit the probabilistic nature of the model to infer marginal distributions over semantic descriptions of as yet unexplored places and detect spatial environment configurations that are novel and incongruent with the known evidence.

sted, utgiver, år, opplag, sider
ASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE , 2018. s. 4547-4555
HSV kategori
Identifikatorer
URN: urn:nbn:se:kth:diva-261987ISI: 000485488904078Scopus ID: 2-s2.0-85050353523OAI: oai:DiVA.org:kth-261987DiVA, id: diva2:1360144
Konferanse
32nd AAAI Conference on Artificial Intelligence / 30th Innovative Applications of Artificial Intelligence Conference / 8th AAAI Symposium on Educational Advances in Artificial Intelligence, New Orleans, LA, FEB 02-07,2018
Merknad

QC 20191011

Tilgjengelig fra: 2019-10-11 Laget: 2019-10-11 Sist oppdatert: 2019-10-11bibliografisk kontrollert

Open Access i DiVA

Fulltekst mangler i DiVA

Andre lenker

ScopusAAAI-18 ConferenceEAAI-18 Conference

Personposter BETA

Pronobis, Andrzej

Søk i DiVA

Av forfatter/redaktør
Pronobis, Andrzej
Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric

urn-nbn
Totalt: 2 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf