MIT Press Journals - Artificial Life

Evolutionary Robotics: A New Scientific Tool for Studying Cognition

Inman Harvey
Centre for Computational, Neuroscience and Robotics (CCNR), Evolutionary and Adaptive Systems Group (EASy), COGS/Informatics, University of Sussex, Brighton BN1 9QH UK inmanh@susx.ac.uk
Ezequiel Di Paolo
Centre for Computational, Neuroscience and Robotics (CCNR), Evolutionary and Adaptive Systems Group (EASy), COGS/Informatics, University of Sussex, Brighton BN1 9QH UK ezequiel@susx.ac.uk
Rachel Wood
Centre for Computational, Neuroscience and Robotics (CCNR), Evolutionary and Adaptive Systems Group (EASy), COGS/Informatics, University of Sussex, Brighton BN1 9QH UK rachelwo@susx.ac.uk
Matt Quinn
Centre for Computational, Neuroscience and Robotics (CCNR), Evolutionary and Adaptive Systems Group (EASy), COGS/Informatics, University of Sussex, Brighton BN1 9QH UK matthewq@susx.ac.uk
Elio Tuci
Centre for Computational Neuroscience and Robotics (CCNR), Evolutionary and Adaptive Systems Group (EASy), COGS/Informatics, University of Sussex, Brighton BN1 9QH UK and IRIDIA Université Libre de Bruxelles Avenue, Franklin Roosevelt 50, CP 194/6, B-1050 Brussels, Belgium etuci@ulb.ac.be

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.

Cited by

Pierre Loor, Kristen Manac’h, Jacques Tisseau. (2009) Enaction-Based Artificial Intelligence: Toward Co-evolution with Humans in the Loop. Minds and Machines 19:3, 319-343
Online publication date: 1-Sep-2009.
CrossRef

Vito Trianni, Stefano Nolfi. (2009) Self-Organizing Sync in a Robotic Swarm: A Dynamical System View. IEEE Transactions on Evolutionary Computation 13:4, 722-741
Online publication date: 1-Sep-2009.
CrossRef

Michail Maniadakis, Panos Trahanias. (2009) Agent-Based Brain Modeling by Means of Hierarchical Cooperative Coevolution. Artificial Life 15:3, 293-336
Online publication date: 1-Jul-2009.
Abstract | PDF (1428 KB) | PDF Plus (1424 KB)

Z. V. Nagoev. (2008) Genomic control of agent morphogenesis in a physically correct virtual environment. Cybernetics and Systems Analysis 44:2, 185-195
Online publication date: 1-Apr-2008.
CrossRef

Ingo Paenke, Bernhard Sendhoff, Tadeusz J. Kawecki. (2007) Influence of Plasticity and Learning on Evolution under Directional Selection. The American Naturalist 170:2, E47-E58
Online publication date: 1-Sep-2007.
CrossRef

Vito Trianni, Marco Dorigo. (2006) Self-organisation and communication in groups of simulated and physical robots. Biological Cybernetics 95:3, 213-231
Online publication date: 1-Oct-2006.
CrossRef