Advanced search
1 file | 1.42 MB Add to list

Neuro-inspired navigation strategies shifting for robots: integration of a multiple landmark taxon strategy

Author
Organization
Abstract
Rodents have been widely studied for their adaptive navigation capabilities. They are able to exhibit multiple navigation strategies; some based on simple sensory-motor associations, while others rely on the construction of cognitive maps. We previously proposed a computational model of parallel learning processes during navigation which could reproduce in simulation a wide set of rat behavioral data and which could adaptively control a robot in a changing environment. In this previous robotic implementation the visual approach (or taxon) strategy was how-ever paying attention to the intra-maze landmark only and learned to approach it. Here we replaced this mechanism by a more realistic one where the robot autonomously learns to select relevant landmarks. We show experimentally that the new taxon strategy is efficient, and that it combines robustly with the planning strategy, so as to choose the most efficient strategy given the available sensory information
Keywords
gating network, navigation strategies, hippocampus, rodent navigation, psikharpax

Downloads

  • Caluwaerts paperLM2012.pdf
    • full text
    • |
    • open access
    • |
    • PDF
    • |
    • 1.42 MB

Citation

Please use this url to cite or link to this publication:

MLA
Caluwaerts, Ken et al. “Neuro-inspired Navigation Strategies Shifting for Robots: Integration of a Multiple Landmark Taxon Strategy.” Lecture Notes in Artificial Intelligence. Ed. Tony T Prescott et al. Vol. 7375. Springer, 2012. 62–73. Print.
APA
Caluwaerts, K., Favre-Félix, A., Staffa, M., N’Guyen, S., Grand, C., Girard, B., & Khamassi, M. (2012). Neuro-inspired navigation strategies shifting for robots: integration of a multiple landmark taxon strategy. In T. T. Prescott, N. F. Lepora, A. Mura, & P. F. Verschure (Eds.), Lecture Notes in Artificial Intelligence (Vol. 7375, pp. 62–73). Presented at the Living Machine 2012 : The International Conference on Biomimetic and Biohybrid Systems, Springer.
Chicago author-date
Caluwaerts, Ken, Antoine Favre-Félix, Mariacarla Staffa, Steve N’Guyen, Christophe Grand, Benoît Girard, and Mehdi Khamassi. 2012. “Neuro-inspired Navigation Strategies Shifting for Robots: Integration of a Multiple Landmark Taxon Strategy.” In Lecture Notes in Artificial Intelligence, ed. Tony T Prescott, Nathan F Lepora, Anna Mura, and Paul FMJ Verschure, 7375:62–73. Springer.
Chicago author-date (all authors)
Caluwaerts, Ken, Antoine Favre-Félix, Mariacarla Staffa, Steve N’Guyen, Christophe Grand, Benoît Girard, and Mehdi Khamassi. 2012. “Neuro-inspired Navigation Strategies Shifting for Robots: Integration of a Multiple Landmark Taxon Strategy.” In Lecture Notes in Artificial Intelligence, ed. Tony T Prescott, Nathan F Lepora, Anna Mura, and Paul FMJ Verschure, 7375:62–73. Springer.
Vancouver
1.
Caluwaerts K, Favre-Félix A, Staffa M, N’Guyen S, Grand C, Girard B, et al. Neuro-inspired navigation strategies shifting for robots: integration of a multiple landmark taxon strategy. In: Prescott TT, Lepora NF, Mura A, Verschure PF, editors. Lecture Notes in Artificial Intelligence. Springer; 2012. p. 62–73.
IEEE
[1]
K. Caluwaerts et al., “Neuro-inspired navigation strategies shifting for robots: integration of a multiple landmark taxon strategy,” in Lecture Notes in Artificial Intelligence, Barcelona, Spain, 2012, vol. 7375, pp. 62–73.
@inproceedings{2917080,
  abstract     = {Rodents have been widely studied for their adaptive navigation capabilities. They are able to exhibit multiple navigation strategies; some based on simple sensory-motor associations, while others rely on the construction of cognitive maps. We previously proposed a computational model of parallel learning processes during navigation which could reproduce in simulation a wide set of rat behavioral data and which could adaptively control a robot in a changing environment. In this previous robotic implementation the visual approach (or taxon) strategy was how-ever paying attention to the intra-maze landmark only and learned to approach it. Here we replaced this mechanism by a more realistic one where the robot autonomously learns to select relevant landmarks. We show experimentally that the new taxon strategy is efficient, and that it combines robustly with the planning strategy, so as to choose the most efficient strategy given the available sensory information},
  author       = {Caluwaerts, Ken and Favre-Félix, Antoine and Staffa, Mariacarla and N'Guyen, Steve and Grand, Christophe and Girard, Benoît and Khamassi, Mehdi},
  booktitle    = {Lecture Notes in Artificial Intelligence},
  editor       = {Prescott, Tony T and Lepora, Nathan F and Mura, Anna and Verschure, Paul FMJ},
  isbn         = {9783642315244},
  issn         = {0302-9743},
  keywords     = {gating network,navigation strategies,hippocampus,rodent navigation,psikharpax},
  language     = {eng},
  location     = {Barcelona, Spain},
  pages        = {62--73},
  publisher    = {Springer},
  title        = {Neuro-inspired navigation strategies shifting for robots: integration of a multiple landmark taxon strategy},
  url          = {http://dx.doi.org/10.1007/978-3-642-31525-1_6},
  volume       = {7375},
  year         = {2012},
}

Altmetric
View in Altmetric