Abstract.
We show that complex visual tasks, such as position- and size-invariant shape recognition and navigation in the environment, can be tackled with simple architectures generated by a coevolutionary process of active vision and feature selection. Behavioral machines equipped with primitive vision systems and direct pathways between visual and motor neurons are evolved while they freely interact with their environments. We describe the application of this methodology in three sets of experiments, namely, shape discrimination, car driving, and robot navigation. We show that these systems develop sensitivity to a number of oriented, retinotopic, visual-feature-oriented edges, corners, height, and a behavioral repertoire to locate, bring, and keep these features in sensitive regions of the vision system, resembling strategies observed in simple insects.
Similar content being viewed by others
Acknowledgments.
The authors thank Claudio Mattiussi, Jesper Blynel, and Shloke Hajela for help with technical preparation of the experiments and discussions. This work was carried out while the authors were at the Swiss Federal Institute of Technology Lausanne and was partially supported by the Swiss National Science Foundation, grant no. 620-58049. Video clips of the experiments and supplementary material can be found on the lab research pages (http://asl.epfl.ch).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Floreano, D., Kato, T., Marocco, D. et al. Coevolution of active vision and feature selection. Biol. Cybern. 90, 218–228 (2004). https://doi.org/10.1007/s00422-004-0467-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00422-004-0467-5