Evolution of adaptive behaviour in robots by means of Darwinian selection

• Published in: PLoS biology Vol. 8; no. 1; p. e1000292
• Main Authors: Floreano, Dario, Keller, Laurent
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 01.01.2010; Public Library of Science (PLoS)
• Subjects: Artificial Intelligence; Biological Evolution; Computer Science/Systems and Control Theory; Ecology/Behavioral Ecology; Ecology/Evolutionary Ecology; Evolutionary Biology; Evolutionary Biology/Animal Behavior; Evolutionary Biology/Evolutionary Ecology; Models, Theoretical; Mutation; Neural networks; Neural Networks (Computer); Robots; Selection, Genetic; Studies; Biological Evolution; Models, Theoretical; Artificial Intelligence; Selection, Genetic; Neural Networks (Computer)
• ISSN: 1545-7885; 1544-9173; 1545-7885
• DOI: 10.1371/journal.pbio.1000292

  [...]the robot's neural networks had a simple architecture with no synaptic plasticity, no ontogenetic development, and no detailed modelling of ion channels and spike transmission. [...]the genomes were directly mapped into the neural network (i.e., no gene-to-gene interaction, time-dependent dynamics, or ontogenetic plasticity). [...]simulations allow one to conduct selection with a large number of individuals over many generations.\n The use of real robot features are particularly useful in an evolutionary perspective where behaviour and ensuing complex physical interactions can significantly affect the interaction with the environment and performance. [...]evolutionary robotics also offers new opportunities to address issues such as sexual selection, division of labour, speciation, and, in general, the open-ended evolution of diversity and complexity in behavioural systems.