de.mpg.escidoc.pubman.appbase.FacesBean
English
 
Help Guide Disclaimer Contact us Login
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Conference Paper

Using evolutionary algorithms for the optimization of the sensorimotor control in an autonomous agent

MPS-Authors
http://pubman.mpdl.mpg.de/cone/persons/resource/persons83985

Huber,  S
Department Human Perception, Cognition and Action, Max Planck Institute for Biological Cybernetics, Max Planck Society;

http://pubman.mpdl.mpg.de/cone/persons/resource/persons84072

Mallot,  HA
Department Human Perception, Cognition and Action, Max Planck Institute for Biological Cybernetics, Max Planck Society;

http://pubman.mpdl.mpg.de/cone/persons/resource/persons83839

Bülthoff,  HH
Department Human Perception, Cognition and Action, Max Planck Institute for Biological Cybernetics, Max Planck Society;

Locator
There are no locators available
Fulltext (public)
There are no public fulltexts available
Supplementary Material (public)
There is no public supplementary material available
Citation

Huber, S., Mallot, H., & Bülthoff, H. (1996). Using evolutionary algorithms for the optimization of the sensorimotor control in an autonomous agent. In 6th International Conference Information Processing and Management of Uncertainty in Knowledge-Based Systems (IPMU 1996) (pp. 1241-1246). Granada, Spain: Universidad de Granada.


Cite as: http://hdl.handle.net/11858/00-001M-0000-0013-EB54-2
Abstract
Autonomous agents that evolve visually-guided control mechanisms using genetic algorithms (GA) and evolutionary strategies (ES) are introduced. These agents are situated in simulated environments and are designed based on the neurobiological principles of various aspects of insect navigation. They generate behavioral modules for obstacle avoidance and the compensation for rotations caused by external disturbances. The sensor positions and the visuomotor coupling evolve with the sensors and motors acting in a closed loop of perception and action. The probabilities for the genetic operations mutation and crossover are optimized and the results of the two optimization techniques genetic algorithms and evolutionary strategies are compared.