Abstract
We present the hypothesis that an important factor for the choice of a particular embodiment for a natural or artificial agent is the effect of the embodiment on the agent’s ability to adapt to changes in the environment. To support this hypothesis, we discuss recent empirical results where sensor morphology was found to significantly affect the time needed for learning a given task. Also, we discuss other recent experiments where a unique optimal sensor morphology could be evolved simply by requiring that the agent had to learn its task as quickly as possible. Both these findings are explained by the recently discovered ”Principle of Unique Local Gain Factors for Optimal Adaptation” which provides a first step towards a general mathematical setting for understanding the interdependence between an agent’s embodiment and its learning performance.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Brooks, R.: Intelligence without reason. In: Mylopoulos, J., Reiter, R. (eds.) Proceedings of the 12th International Conference on Artificial Intelligence (IJCAI 1991), pp. 569–595. Morgan Kaufmann, San Mateo (1991)
Brooks, R.A.: Intelligence without representation. Artificial Intelligence 47, 139–159 (1991)
Land, M.: Variations in the structure and design of compound eyes. In: Stavenga, D., Hardie, R. (eds.) Facets of Vision, pp. 90–111. Springer, Berlin (1989)
Pfeifer, R.: Building fungus eaters: Design principles of autonomous agents. In: Maes, P., Mataric, M.J., Meyer, J.A., Pollack, J., Wilson, S.W. (eds.) From animals to animats 4: Proceedings of the fourth international conference on simulation of adaptive behavior, pp. 3–12. MIT Press, Cambridge (1996)
Pfeifer, R., Scheier, C.: Understanding Intelligence. MIT Press, Cambridge (1999)
Pfeifer, R.: On the role of morphology and materials in adaptive behavior. In: Berthoz, A., Floreano, D., Meyer, J.A., Roitblat, H., Wilson, S. (eds.) From Animals to Animats 6: Proceedings of the Sixth International Conference on the Simulation of Adaptive Behaviour, pp. 23–32. MIT Press, Cambridge (2000)
McGeer, T.: Passive dynamic walking. Int. J. Robotics Research 9(2), 62–82 (1990)
Hara, F., Pfeifer, R. (eds.): Morpho-functional machines: the new species; designing embodied intelligence. Springer, Tokyo (2003)
Wisse, M., van Frankenhuyzen, J.: Design and construction of mike: a 2d autonomous biped based on passive dynamic walking. In: Proceedings of the 2nd International Symposium on Adaptive Motion of Animals and Machines AMAM 2003, Kyoto, Japan (2003)
Lichtensteiger, L., Eggenberger, P.: Evolving the morphology of a compound eye on a robot. In: Proceedings of the 3rd European Workshop on Advanced Mobile Robots Eurobot 1999, pp. 127–134. IEEE Press, Piscataway (1999)
Lichtensteiger, L.: Towards optimal sensor morphology for specific tasks: Evolution of an artificial compound eye for estimating time to contact. In: McKee, G.T., Schenker, P.S. (eds.) Sensor Fusion and Decentralized Control in Robotic Systems III, Proceedings of SPIE,Society of Photo-Optical Instrumentation Engineers (SPIE), Bellingham, WA, vol. 4196, pp. 138–146 (2000)
Lichtensteiger, L., Salomon, R.: The evolution of an artificial compound eye by using adaptive hardware. In: Proceedings of the 2000 Congress on Evolutionary Computation (CEC 2000), pp. 1144–1151. IEEE Computer Society Press, San Diego (2000)
Lichtensteiger, L.: Evolving task specific optimal morphologies for an artificial insect eye. In: Hara, F., Pfeifer, R. (eds.) Morpho-functional machines: the new species; designing embodied intelligence, pp. 41–57. Springer, Tokyo (2003)
Lichtensteiger, L., Pfeifer, R.: An optimal sensor morphology improves adaptability of neural network controllers. In: Dorronsoro, J.R. (ed.) ICANN 2002. LNCS, vol. 2415, pp. 850–855. Springer, Heidelberg (2002)
Lichtensteiger, L.: How the need to learn fast can shape bodies (2004) (submitted)
Lichtensteiger, L.: Existence and uniqueness of optimal local gain factors for gradient descent learning (2004) (submitted)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Lichtensteiger, L. (2004). The Need to Adapt and Its Implications for Embodiment. In: Iida, F., Pfeifer, R., Steels, L., Kuniyoshi, Y. (eds) Embodied Artificial Intelligence. Lecture Notes in Computer Science(), vol 3139. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-27833-7_7
Download citation
DOI: https://doi.org/10.1007/978-3-540-27833-7_7
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-22484-6
Online ISBN: 978-3-540-27833-7
eBook Packages: Springer Book Archive