Harvey, Inman, Paolo, Ezequiel Di, Wood, Rachel, Quinn, Matt and Tuci, Elio (2005) Evolutionary Robotics: A New Scientific Tool for Studying Cognition. Artificial Life, 11 (1-2). pp. 79-98. ISSN 1064-5462

Preview

PDF Download (981kB) | Preview

Abstract

We survey developments in artificial neural networks, in behavior-based robotics, and in evolutionary algorithms that set the stage for evolutionary robotics (ER) in the 1990s. We examine the motivations for using ER as a scientific tool for studying minimal models of cognition, with the advantage of being capable of generating integrated sensorimotor systems with minimal (or controllable) prejudices. These systems must act as a whole in close coupling with their environments, which is an essential aspect of real cognition that is often either bypassed or modeled poorly in other disciplines. We demonstrate with three example studies: homeostasis under visual inversion, the origins of learning, and the ontogenetic acquisition of entrainment.

Item Type:	Article
Additional Information:	Publisher's version available at official url.
Schools and Departments:	School of Engineering and Informatics > Informatics
Subjects:	Q Science > QA Mathematics > QA0075 Electronic computers. Computer science
Depositing User:	Chris Keene
Date Deposited:	22 Feb 2008
Last Modified:	07 Mar 2017 05:54
URI:	http://srodev.sussex.ac.uk/id/eprint/1365
Google Scholar:	144 Citations

View download statistics for this item

📧 Request an update