Tè
Darwiniano
Tè
Darwiniano
In occasione del sedicesimo incontro del Tè Darwiniano (presenti: Raffaele Calabretta, Andrea Di Ferdinando, Louis Foucart, Davide Marocco, Stefano Nolfi, Anne Spallanzani, Richard Walker), Dario Floreano (Institute of Robotic Systems, Swiss Federal Institute of Technology, Losanna) ci ha parlato di:
Evolutionary
Robotics:
Coping with Unpredictable Change
Abstract
I suggest a way to make evolved robots capable of dealing with sources change that were not included in the evolutionary training. The method consists of evolving mechanisms of parameter adaptation instead of conventional evolution of the parameters themselves. I provide a series of experimental results on physical robots indicating that: a) The method can develop more complex abilities than evolution alone;
b) The dynamics of evolved learning
system are qualitatively different from conventional evolved systems;
c) The approach scales up to large control architectures;
d) Evolved robots remain adaptive after evolution to several sources of changes
(sensors, environment layout, transfer from simulation to hardware and across
different robotic platforms)
e) When evolving genetic expression, evolution selects expression of parameter
adaptation rather than expression of the parameters.
Floreano, D. and Urzelai, J. Evolutionary Robotics: The Next Generation. In T. Gomi (Ed.), Evolutionary Robotics, Boston: Kluwer Academic Publishers, 2000.
Floreano, D. and Urzelai, J. Evolutionary Robots with Online
Self-Organization and Behavioral Fitness. Neural Networks, 2000. Forthcoming.