An ASSOM neural network to represent actions performed by an autonomous agent
An ASSOM neural network to describe the action performed by an autonomous reactive agent is proposed. The neural network receives in input the sequences of data acquired by the agent internal sensors and it classifies them by generating the corresponding symbolic assertions. Experimental results performed on a RWI B12 autonomous robot are reported.
Unable to display preview. Download preview PDF.
- 1.P.E. Agre and D. Chapman. What are plans for? Robotics and Autonom. Systems, 6:17–34, 1990.Google Scholar
- 2.C. Balkenius. Natural Intelligence in Artificial Creatures. PhD thesis, Lund University Cognitive Studies, Lund, Sweden, 1995.Google Scholar
- 3.R.A. Brooks. A robust layered control system for a mobile robot. IEEE J. Robotics and Automation, 2:14–23, 1986.Google Scholar
- 4.A. Chella, M. Frixione, and S. Gaglio. A cognitive architecture for artificial vision. Artif. Intell., 89:73–111, 1997.Google Scholar
- 5.A. Chella, Di Gesù V., Gaglio S., and Gerardi G. DAISY: a Distributed Architecture for Intelligent SYstem. In Proc. of CAMP '97. IEEE/CS, 1997. (in press).Google Scholar
- 6.T. Kohonen. The adaptive-subspace SOM (ASSOM) and its use for the implementation of invariant feature detection. In Proc. ICANN'95, Int. Conf. on Artificial Neur. Networks, volume 1, pages 3–10. EC2&Cie, 1995.Google Scholar
- 7.T. Kohonen. Self-Organizing Maps. Springer-Verlag, Berlin, 1995.Google Scholar
- 8.P. Maes. Designing autonomous agents. Robotics and Autonom. Systems, 6:1–2, 1990.Google Scholar