A Perceptual Memory System for Affordance Learning in Humanoid Robots

Kammer M, Tscherepanow M, Schack T, Nagai Y (2011)
In: Proceedings of the International Conference on Artificial Neural Networks (ICANN). Honkela T, Duch W, Girolami M, Kaski S (Eds); Lecture Notes in Computer Science, 6792, . Berlin: Springer: 349-356.

Download
OA
Conference Paper | Published | English
Editor
Honkela, Timo ; Duch, Wlodzislaw ; Girolami, Mark ; Kaski, Samuel
Abstract
Memory constitutes an essential cognitive capability of humans and animals. It allows them to act in very complex, non-stationary environments. In this paper, we propose a perceptual memory system, which is intended to be applied on a humanoid robot learning affordances. According to the properties of biological memory systems, it has been designed in such a way as to enable life-long learning without catastrophic forgetting. Based on clustering sensory information, a symbolic representation is derived automatically. In contrast to alternative approaches, our memory system does not rely on pre-trained models and works completely unsupervised.
Publishing Year
Conference
Artificial Neural Networks and Machine Learning – ICANN 2011 : 21st International Conference on Artificial Neural Networks, Proceedings, Part II
Location
Espoo, Finland
Conference Date
2011-06-14 – 2011-06-17
PUB-ID

Cite this

Kammer M, Tscherepanow M, Schack T, Nagai Y. A Perceptual Memory System for Affordance Learning in Humanoid Robots. In: Honkela T, Duch W, Girolami M, Kaski S, eds. Proceedings of the International Conference on Artificial Neural Networks (ICANN). Lecture Notes in Computer Science, 6792. Berlin: Springer; 2011: 349-356.
Kammer, M., Tscherepanow, M., Schack, T., & Nagai, Y. (2011). A Perceptual Memory System for Affordance Learning in Humanoid Robots. In T. Honkela, W. Duch, M. Girolami, & S. Kaski (Eds.), Lecture Notes in Computer Science, 6792. Proceedings of the International Conference on Artificial Neural Networks (ICANN) (pp. 349-356). Berlin: Springer.
Kammer, M., Tscherepanow, M., Schack, T., and Nagai, Y. (2011). “A Perceptual Memory System for Affordance Learning in Humanoid Robots” in Proceedings of the International Conference on Artificial Neural Networks (ICANN), ed. T. Honkela, W. Duch, M. Girolami, and S. Kaski Lecture Notes in Computer Science, 6792 (Berlin: Springer), 349-356.
Kammer, M., et al., 2011. A Perceptual Memory System for Affordance Learning in Humanoid Robots. In T. Honkela, et al., eds. Proceedings of the International Conference on Artificial Neural Networks (ICANN). Lecture Notes in Computer Science, 6792. Berlin: Springer, pp. 349-356.
M. Kammer, et al., “A Perceptual Memory System for Affordance Learning in Humanoid Robots”, Proceedings of the International Conference on Artificial Neural Networks (ICANN), T. Honkela, et al., eds., Lecture Notes in Computer Science, 6792, Berlin: Springer, 2011, pp.349-356.
Kammer, M., Tscherepanow, M., Schack, T., Nagai, Y.: A Perceptual Memory System for Affordance Learning in Humanoid Robots. In: Honkela, T., Duch, W., Girolami, M., and Kaski, S. (eds.) Proceedings of the International Conference on Artificial Neural Networks (ICANN). Lecture Notes in Computer Science, 6792. p. 349-356. Springer, Berlin (2011).
Kammer, Marc, Tscherepanow, Marko, Schack, Thomas, and Nagai, Yukie. “A Perceptual Memory System for Affordance Learning in Humanoid Robots”. Proceedings of the International Conference on Artificial Neural Networks (ICANN). Ed. Timo Honkela, Wlodzislaw Duch, Mark Girolami, and Samuel Kaski. Berlin: Springer, 2011. Lecture Notes in Computer Science, 6792. 349-356.
Main File(s)
Access Level
OA Open Access
Last Uploaded
2012-06-18 11:13:27

This data publication is cited in the following publications:
This publication cites the following data publications:

Export

0 Marked Publications

Open Data PUB

Search this title in

Google Scholar
ISBN Search