hh.sePublikasjoner
Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • 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
Modular Neural Network and Classical Reinforcement Learning for Autonomous Robot Navigation: Inhibiting Undesirable Behaviors
Electronics and Information Systems (ELIS) department, Ghent university, Belgium.
Högskolan i Halmstad, Sektionen för Informationsvetenskap, Data– och Elektroteknik (IDE), Halmstad Embedded and Intelligent Systems Research (EIS).
Högskolan i Halmstad, Sektionen för Informationsvetenskap, Data– och Elektroteknik (IDE), Halmstad Embedded and Intelligent Systems Research (EIS).ORCID-id: 0000-0001-5163-2997
State University of Maringá, Brazil.
2006 (engelsk)Inngår i: International Joint Conference on Neural Networks, 2006. IJCNN '06, Piscataway, N.J.: IEEE Press, 2006, s. 498-505Konferansepaper, Publicerat paper (Fagfellevurdert)
Abstract [en]

Classical reinforcement learning mechanisms and a modular neural network are unified for conceiving an intelligent autonomous system for mobile robot navigation. The conception aims at inhibiting two common navigation deficiencies: generation of unsuitable cyclic trajectories and ineffectiveness in risky configurations. Distinct design apparatuses are considered for tackling these navigation difficulties, for instance: 1) neuron parameter for memorizing neuron activities (also functioning as a learning factor), 2) reinforcement learning mechanisms for adjusting neuron parameters (not only synapse weights), and 3) a inner-triggered reinforcement. Simulation results show that the proposed system circumvents difficulties caused by specific environment configurations, improving the relation between collisions and captures.

sted, utgiver, år, opplag, sider
Piscataway, N.J.: IEEE Press, 2006. s. 498-505
Serie
IEEE International Joint Conference on Neural Networks (IJCNN), ISSN 1098-7576
Emneord [en]
mobile robots, neurocontrollers, path planning
HSV kategori
Identifikatorer
URN: urn:nbn:se:hh:diva-2112DOI: 10.1109/IJCNN.2006.246723ISI: 000245125900073Scopus ID: 2-s2.0-40649114292Lokal ID: 2082/2507ISBN: 0-7803-9490-9 OAI: oai:DiVA.org:hh-2112DiVA, id: diva2:239330
Konferanse
International Joint Conference on Neural Networks, 2006. IJCNN '06, Vancouver
Merknad

©2006 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

Tilgjengelig fra: 2008-11-07 Laget: 2008-11-07 Sist oppdatert: 2018-03-23bibliografisk kontrollert

Open Access i DiVA

fulltekst(546 kB)517 nedlastinger
Filinformasjon
Fil FULLTEXT01.pdfFilstørrelse 546 kBChecksum SHA-512
d6537885681977fc2b88b4ee91992959384510e9f07c856f8cbd2e4f2041a123e809d137bc7e785bcb91be811e369ecdd3e48a117e7da224b2f6b6bf856bc3a5
Type fulltextMimetype application/pdf

Andre lenker

Forlagets fulltekstScopus

Personposter BETA

Baerveldt, Albert-JanRögnvaldsson, Thorsteinn

Søk i DiVA

Av forfatter/redaktør
Baerveldt, Albert-JanRögnvaldsson, Thorsteinn
Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar
Totalt: 517 nedlastinger
Antall nedlastinger er summen av alle nedlastinger av alle fulltekster. Det kan for eksempel være tidligere versjoner som er ikke lenger tilgjengelige

doi
isbn
urn-nbn

Altmetric

doi
isbn
urn-nbn
Totalt: 497 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • 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