Header logo is

Learning view graphs for robot navigation


Conference Paper


We present a purely vision-based scheme for learning a parsimonious representation of an open environment. Using simple exploration behaviours, our system constructs a graph of appropriately chosen views. To navigate between views connected in the graph, we employ a homing strategy inspired by findings of insect ethology. Simulations and robot experiments demonstrate the feasibility of the proposed approach.

Author(s): Franz, MO. and Schölkopf, B. and Georg, P. and Mallot, HA. and Bülthoff, HH.
Journal: Proceedings of the 1st Intl. Conf. on Autonomous Agents
Pages: 138-147
Year: 1997
Month: Febuary
Day: 0
Editors: Johnson, W.L.
Publisher: ACM Press

Department(s): Empirical Inference
Bibtex Type: Conference Paper (inproceedings)

DOI: 10.1145/267658.267687
Event Name: First International Conference on Autonomous Agents (AGENTS ’97)
Event Place: Marina del Rey, CA, USA

Address: New York, NY, USA
ISBN: 0-89791-877-0
Organization: Max-Planck-Gesellschaft
School: Biologische Kybernetik

Links: PDF


  title = {Learning view graphs for robot navigation},
  author = {Franz, MO. and Sch{\"o}lkopf, B. and Georg, P. and Mallot, HA. and B{\"u}lthoff, HH.},
  journal = {Proceedings of the 1st Intl. Conf. on Autonomous Agents},
  pages = {138-147},
  editors = {Johnson, W.L.},
  publisher = {ACM Press},
  organization = {Max-Planck-Gesellschaft},
  school = {Biologische Kybernetik},
  address = {New York, NY, USA},
  month = feb,
  year = {1997},
  month_numeric = {2}