000063911 001__ 63911
000063911 005__ 20180317094905.0
000063911 037__ $$aARTICLE
000063911 245__ $$aArtificial Evolution of Adaptive Software: An Application to Autonomous Robots
000063911 269__ $$a2000
000063911 260__ $$c2000
000063911 336__ $$aJournal Articles
000063911 520__ $$aArtificial evolution of computer software (evolutionary neural networks, genetic programming, evolutionary fuzzy systems, etc.) has been shown to generate software that in many cases is more performant than that designed by engineers. Evolved software performs well under the same conditions used during evolutionary training. However, in situations where unpredictable change may affect normal operation, evolved systems often fail. In this paper we describe a new approach for evolving software that remains adaptive and is therefore very robust to unpredictable change after evolution. To illustrate the idea, we present the case of evolutionary robots that quickly and reliably adapt online to several types of new situations, including sensory, environmental, and mechanical change, while still performing their task. The core of the methodology consists of evolving the mechanisms of parameter adaptation instead of the parameters themselves. We shall conclude by showing how this methodology can be applied to a variety of other situations beyond robotics.
000063911 6531_ $$aEvolutionary Robotics
000063911 6531_ $$aEvolution and Learning
000063911 6531_ $$aAdaptative Software
000063911 6531_ $$aHebbian Learning
000063911 6531_ $$aArtificial Life
000063911 700__ $$0240742$$aFloreano, D.$$g111729
000063911 700__ $$0241893$$aUrzelai, J.$$g100001
000063911 773__ $$j14$$k4$$q64-69$$t3D The Journal of Three dimensional images (in japanese)
000063911 8564_ $$s2381451$$uhttps://infoscience.epfl.ch/record/63911/files/hc2000.pdf$$zn/a
000063911 909CO $$ooai:infoscience.tind.io:63911$$particle$$pSTI
000063911 909C0 $$0252161$$pLIS$$xU10370
000063911 937__ $$aLIS-ARTICLE-2000-004
000063911 970__ $$a39/LIS
000063911 973__ $$aEPFL$$sPUBLISHED
000063911 980__ $$aARTICLE