Stage-oe-small.jpg

Inproceedings3145: Unterschied zwischen den Versionen

Aus Aifbportal
Wechseln zu:Navigation, Suche
 
Zeile 21: Zeile 21:
 
|Organization=Machine Intelligence Research Labs
 
|Organization=Machine Intelligence Research Labs
 
|Publisher=IEEE Computer Society
 
|Publisher=IEEE Computer Society
 +
}}
 +
{{Publikation Tool
 +
|Tool=Organic Computing Learning Robots Arena
 
}}
 
}}
 
{{Publikation Details
 
{{Publikation Details

Aktuelle Version vom 15. Juli 2015, 13:53 Uhr


Age Based Controller Stabilization in Evolutionary Robotics


Age Based Controller Stabilization in Evolutionary Robotics



Published: 2010 Dezember

Buchtitel: 2nd World Congress on Nature and Biologically Inspired Computing (NaBIC)
Seiten: 84 -91
Verlag: IEEE Computer Society
Organisation: Machine Intelligence Research Labs

Referierte Veröffentlichung

BibTeX


Kurzfassung
Evolutionary Robotics is a collection of heuristics where robotic control systems are developed by following the example of natural evolution. An evolutionary run is performed by mutating the robots’ controllers randomly and selecting for some desired behavioral properties. Overall, these properties should be improved over time leading to a stable increase of fitness. However, random mutations on critical controller parts can lead to a rapid degradation lowering the performance of evolution. This paper presents an approach to reduce the loss of desirable behavior during an evolution process. A notion of age is introduced as a quality criterion to indicate the contribution of parts of a controller to the robot’s overall behavior. To preserve the behavior evolved so far, mutations are channeled to affect controller parts with a lower age more than those with a higher age. As a result, controller parts that contribute to a good behavior are stabilized and the evolved desirable behavior is maintained. Experiments have been performed in a decentralized online evolutionary scenario with controllers based on finite state machines (FSMs). The results show an improvement in the number of successful evolutions and the number of successfully evolved robots compared to previous studies.

Download: Media:PID1522079.pdf
Weitere Informationen unter: Link
DOI Link: 10.1109/NABIC.2010.5716366

Verknüpfte Tools

Organic Computing Learning Robots Arena


Forschungsgruppe

Effiziente Algorithmen


Forschungsgebiet

Evolutionäre Robotik


age based controller stabilization;behavioral properties;critical controller parts;decentralized online evolutionary scenario;desirable behavior;evolution performance;evolution process;evolutionary robotics;evolutionary run;finite state machines;natural evolution;quality criterion;rapid degradation lowering;robotic control systems;evolutionary computation;finite state machines;stability;