Empirical Inference

View-based cognitive mapping and path planning

1994

Technical Report

ei


We present a scheme for learning a cognitive map of a maze from a sequence of views and movement decisions. The scheme is based on an intermediate representation called the view graph. We show that this representation carries sufficient information to reconstruct the topological and directional structure of the maze. Moreover, we present a neural network that learns the view graph during a random exploration of the maze. We use a unsupervised competitive learning rule which translates temporal sequence (rather than similarity) of views into connectedness in the network. The network uses its knowledge of the topological and directional structure of the maze to generate expectations about which views are likely to be perceived next, improving the view recognition performance. We provide an additional mechanism which uses the map to find paths between arbitrary points of the previously explored environment. The results are compared to findings of behavioural neuroscience.

Author(s): Schölkopf, B. and Mallot, HA.
Number (issue): 7
Year: 1994
Month: November
Day: 0

Department(s): Empirical Inference
Bibtex Type: Technical Report (techreport)

Institution: Max Planck Institute for Biological Cybernetics Tübingen

Digital: 0
Note: This technical report has also been <a href="/main/publication.php?machwas=view_e&edit_lfnr=947">published elsewhere</a>
Organization: Max-Planck-Gesellschaft
School: Biologische Kybernetik

BibTex

@techreport{1462,
  title = {View-based cognitive mapping and path planning},
  author = {Sch{\"o}lkopf, B. and Mallot, HA.},
  number = {7},
  organization = {Max-Planck-Gesellschaft},
  institution = {Max Planck Institute for Biological Cybernetics Tübingen},
  school = {Biologische Kybernetik},
  month = nov,
  year = {1994},
  note = {This technical report has also been <a href="/main/publication.php?machwas=view_e&edit_lfnr=947">published elsewhere</a>},
  doi = {},
  month_numeric = {11}
}