Evolutionary Robotics: A New Scientific Tool for Studying Cognition

By Inman R. Harvey, E. D. Di Paolo, Rachel Wood, M. Quinn, Elio Tuci. Artificial Life, 2005

301 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Cognitive Neuroscience

View Paper: https://www.semanticscholar.org/paper/b317b6488b5546aa525446977eae6cb0dd556ba8

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Cognitive Neuroscience

Citations in the corpus

Morphological change in machines accelerates the evolution of robust behavior (2011, methodology): “The method introduced here follows a biologically inspired approach to robotics in which populations of simulated robots undergo evolutionary pressure favoring some desired behavior (4, 5).”
The extended body: a case study in the neurophenomenology of social interaction (2012, unknown): “Given this general model setup, Froese and Di Paolo (2008) automatically configured the structure of the agents’ dynamical system by using an evolutionary algorithm, which is commonly employed in the fields of artificial life and evolutionary robotics (Beer 1995, 2003; Harvey et al. 2005).”
Influence of Plasticity and Learning on Evolution under Directional Selection (2007, background): “Finally, it can be applied to artificial intelligence and robotics, where combinations of simulated evolution (genetic algorithms) and plasticity (random noise and learning) are applied to solve complex problems (e.g., Nolfi 1999; Harvey et al. 2005).”
Enactive artificial intelligence: Investigating the systemic organization of life and mind (2009, background): “This category thus encompasses a variety of recent AI research programs including, for example, evolutionary robotics (e.g. Harvey et al. 2005; Nolfi & Floreano 2000), epigenetic and developmental robotics (e.g. Berthouze & Ziemke 2003; Lungarella et al. 2003), and the dynamical approach to…”
Horizons for the Enactive Mind: Values, Social Interaction, and Play (2010, background): “A proper extension of the enactive approach into a solid and mainstream framework for understanding cognition in all its manifestations will be a job of many and lasting for many years.”