Evolving cognitive scaffolding and environment adaptation: a new research direction for evolutionary robotics
Authors:
- 1 December 2004
- journal article
- research article
- Published by Taylor & Francis in Connection Science
- Vol. 16 (4) , 339-350
Abstract
Many researchers in embodied cognitive science and artificial intelligence, and evolutionary robotics in particular, emphasize the interaction of brain, body and environment as crucial to the emergence of intelligent, adaptive behaviour. Accordingly, the interaction between agent and environment, as well as the co-adaptation of artificial brains and bodies, has been the focus of much research in evolutionary robotics. Hence, there are plenty of studies of robotic agents/species adapting to a given environment. Many animals, on the other hand, in particular humans, to some extent can choose to adapt the environment to their own needs instead of adapting (only) themselves. That alternative has been studied relatively little in robot experiments. This paper, therefore, presents some simple initial simulation experiments, in a delayed response task setting, that illustrate how the evolution of environment adaptation can serve to provide cognitive scaffolding that reduces the requirements for individual agents. Furthermore, theoretical implications, open questions and future research directions for evolutionary robotics are discussed.Keywords
This publication has 16 references indexed in Scilit:
- Brains, Bodies, and Beyond: Competitive Co-Evolution of Robot Controllers, Morphologies and EnvironmentsGenetic Programming and Evolvable Machines, 2005
- Evolving internal memory for T-maze tasks in noisy environmentsConnection Science, 2004
- The Dynamics of Active Categorical Perception in an Evolved Model AgentAdaptive Behavior, 2003
- Three Generations of Automatically Designed RobotsArtificial Life, 2001
- Editor's Introduction: StigmergyArtificial Life, 1999
- Embedded neural networks: exploiting constraintsNeural Networks, 1998
- Evolutionary Robotics: Exploiting the Full Power of Self-organizationConnection Science, 1998
- Using Emergent Modularity to Develop Control Systems for Mobile RobotsAdaptive Behavior, 1997
- Adapting the Environment Instead of OneselfAdaptive Behavior, 1996
- Intelligence without representationArtificial Intelligence, 1991