Back
Full-text
Journal article

Evolutionary robots with on-line self-organization and behavioral fitness.

  • Floreano D Institute of Robotic Systems (ISR), Swiss Federal Institute of Technology (EPFL), Lausanne, Switzerland. dario.floreano@epfl.ch
  • Urzelai J
  • 2000-08-18
Published in:
  • Neural networks : the official journal of the International Neural Network Society. - 2000
Evolution, Molecular
Genetic Code
Infrared Rays
Lighting
Neural Networks, Computer
Robotics
Synapses
English We address two issues in Evolutionary Robotics, namely the genetic encoding and the performance criterion, also known as the fitness function. For the first aspect, we suggest to encode mechanisms for parameter self-organization, instead of the parameters themselves as in conventional approaches. We argue that the suggested encoding generates systems that can solve more complex tasks and are more robust to unpredictable sources of change. We support our arguments with a set of experiments on evolutionary neural controllers for physical robots and compare them to conventional encoding. In addition, we show that when also the genetic encoding is left free to evolve, artificial evolution will select to exploit mechanisms of self-organization. For the second aspect, we shall discuss the role of the performance criterion, als known as fitness function, and suggest Fitness Space as a framework to conceive fitness functions in Evolutionary Robotics. Fitness Space can be used as a guide to design fitness functions as well as to compare different experiments in Evolutionary Robotics.
Language
  • English
Open access status
green
Identifiers
Persistent URL
https://folia.unifr.ch/global/documents/127300
Statistics
Document views: 3 File downloads:
  • fulltext.pdf: 0