2005 Special Issue: The contribution of active body movement to visual development in evolutionary robots

Authors:
Mototaka Suzuki;Dario Floreano;Ezequiel A. Di Paolo
Affiliations:
Laboratory of Intelligent Systems, Swiss Federal Institute of Technology (EPFL) CH-1015 Lausanne, Switzerland;Laboratory of Intelligent Systems, Swiss Federal Institute of Technology (EPFL) CH-1015 Lausanne, Switzerland;Centre for Computational Neuroscience and Robotics, University of Sussex, Brighton, BN19QH, UK
Venue:
Neural Networks - 2005 Special issue: IJCNN 2005
Year:
2005

Citing 5
Cited 4

Animate vision

Artificial Intelligence
What is the goal of sensory coding?

Neural Computation
The world from a cat’s perspective – statistics of natural videos

Biological Cybernetics
Coevolution of active vision and feature selection

Biological Cybernetics
Active Vision and Receptive Field Development in Evolutionary Robots

Evolutionary Computation

Enactive Robot Vision

Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
Active Vision for Goal-Oriented Humanoid Robot Walking

Creating Brain-Like Intelligence
2009 Special Issue: Explorations on artificial time perception

Neural Networks
Dynamical systems in the sensorimotor loop: on the interrelation between internal and external mechanisms of evolved robot behavior

50 years of artificial intelligence

Quantified Score

Hi-index	0.01

Visualization

Abstract

Inspired by the pioneering work by Held and Hein (1963) on the development of kitten visuo-motor systems, we explore the role of active body movement in the developmental process of the visual system by using robots. The receptive fields in an evolved mobile robot are developed during active or passive movement with a Hebbian learning rule. In accordance to experimental observations in kittens, we show that the receptive fields and behavior of the robot developed under active condition significantly differ from those developed under passive condition. A possible explanation of this difference is derived by correlating receptive field formation and behavioral performance in the two conditions.