Stage-oe-small.jpg

Inproceedings3063: Unterschied zwischen den Versionen

Aus Aifbportal
Wechseln zu:Navigation, Suche
Zeile 16: Zeile 16:
 
}}
 
}}
 
{{Publikation Details
 
{{Publikation Details
 +
|Abstract=Artificial evolution has successfully been utilized to train robotic controllers in various types of applications and scenarios. However, for different behaviors to be trained usually different evolutionary setups have to be designed which is a costly procedure. For many current real-world problems in robotics, the effort for finding a good evolutionary setup is still big and programming by hand is a more feasible approach. In this paper, a completely evolvable genotype-phenotype mapping (ceGPM) is studied with respect to its capability of improving the flexibility of artificial evolution. By letting mutation affect not only controller genotypes, but also the mapping from genotype to phenotype, the future effects of mutation can change over time. That makes the training process highly adaptable to the behavior being trained during the training itself. By this means, the need for prior parameter adaptation can be reduced. Experiments with the presented approach in a simulated swarm of mobile robots using controllers based on finite state machines indicate that the ceGPM is capable of robustly adapting to a benchmark behavior. A comparison to a related approach shows significant improvements in evolvability according to a proposed measure.
 
|Forschungsgruppe=Effiziente Algorithmen
 
|Forschungsgruppe=Effiziente Algorithmen
 
}}
 
}}

Version vom 11. Mai 2010, 07:27 Uhr


Evolvability in Evolutionary Robotics: Evolving the Genotype-Phenotype Mapping


Evolvability in Evolutionary Robotics: Evolving the Genotype-Phenotype Mapping



Published: 2010

Buchtitel: Under submission
Verlag: Under submission

Referierte Veröffentlichung
Note: Under submission

BibTeX

Kurzfassung
Artificial evolution has successfully been utilized to train robotic controllers in various types of applications and scenarios. However, for different behaviors to be trained usually different evolutionary setups have to be designed which is a costly procedure. For many current real-world problems in robotics, the effort for finding a good evolutionary setup is still big and programming by hand is a more feasible approach. In this paper, a completely evolvable genotype-phenotype mapping (ceGPM) is studied with respect to its capability of improving the flexibility of artificial evolution. By letting mutation affect not only controller genotypes, but also the mapping from genotype to phenotype, the future effects of mutation can change over time. That makes the training process highly adaptable to the behavior being trained during the training itself. By this means, the need for prior parameter adaptation can be reduced. Experiments with the presented approach in a simulated swarm of mobile robots using controllers based on finite state machines indicate that the ceGPM is capable of robustly adapting to a benchmark behavior. A comparison to a related approach shows significant improvements in evolvability according to a proposed measure.


Verknüpfte Tools

Organic Computing Learning Robots Arena


Forschungsgruppe

Effiziente Algorithmen


Forschungsgebiet

Organic Computing, Genetische Algorithmen, Naturanaloge Algorithmen, Evolutionäre Robotik


Die Veröffentlichung wird noch referiert, dies ist ein vorläufiger Eintrag, um auf ein im Beitrag referenziertes Bild zu verlinken: http://www.aifb.kit.edu/images/6/6b/Utrans.pdf