Multimodal active exploration using a Bayesian approach

João Filipe Ferreira, José Augusto Prado, Jorge Lobo, Jorge Dias

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Scopus citations

Abstract

In this text, we use a Bayesian framework for active multimodal perception of 3D structure and motion-which, while not strictly neuromimetic, finds its roots in the role of the dorsal perceptual pathway of the human brain-to implement a strategy of active exploration based on entropy. The computational models described in this text support a robotic implementation of multimodal active perception to be used in real-world applications, such as human-machine interaction or mobile robot navigation.

Original languageBritish English
Title of host publicationProceedings of the 14th IASTED International Conference on Robotics and Applications, RA 2009
Pages319-326
Number of pages8
StatePublished - 2009
Event14th IASTED International Conference on Robotics and Applications, RA 2009 - Cambridge, MA, United States
Duration: 2 Nov 20094 Nov 2009

Publication series

NameProceedings of the IASTED International Conference on Robotics and Applications
ISSN (Print)1027-264X

Conference

Conference14th IASTED International Conference on Robotics and Applications, RA 2009
Country/TerritoryUnited States
CityCambridge, MA
Period2/11/094/11/09

Keywords

  • Active perception
  • Bayesian
  • Bioinspired
  • Exploration
  • Multisensory
  • Realtime

Fingerprint

Dive into the research topics of 'Multimodal active exploration using a Bayesian approach'. Together they form a unique fingerprint.

Cite this