An Optimal Sensor Morphology Improves Adaptability of Neural Network Controllers

Abstract

Animals show an abundance of different sensor morphologies, for example in insect compound eyes. However, the advantages of having highly specific sensor morphologies still remain unclear. In this paper we show that an appropriate sensor morphology can improve the learning performance of an agent’s neural controller significantly. Using a sensor morphology… (More)
DOI: 10.1007/3-540-46084-5_138

Topics

3 Figures and Tables

Cite this paper

@inproceedings{Lichtensteiger2002AnOS, title={An Optimal Sensor Morphology Improves Adaptability of Neural Network Controllers}, author={Lukas Lichtensteiger and Rolf Pfeifer}, booktitle={ICANN}, year={2002} }