Evolving in Real Time a Neural Net Controller of Robot-Arm: Track and Evolve

Created by W.Langdon from gp-bibliography.bib Revision:1.8129

@Article{DBLP:journals/informaticaLT/LehirecheR04,

• author = "Ahmed Lehireche and Abdellatif Rahmoun",
• title = "Evolving in Real Time a Neural Net Controller of Robot-Arm: Track and Evolve",
• journal = "Informatica, Lith. Acad. Sci.",
• year = "2004",
• volume = "15",
• number = "1",
• pages = "63--76",
• keywords = "genetic algorithms, genetic programming, evolutionary engineering, tracking, real time, neighbourhood hypothesis, artificial intelligence",
• bibsource = "OAI-PMH server at citeseerx.ist.psu.edu",
• language = "en",
• oai = "oai:CiteSeerX.psu:10.1.1.532.6397",
• URL = "http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.532.6397",
• URL = "http://www.mii.lt/Informatica/pdf/INFO539.pdf",
• URL = "http://content.iospress.com/download/informatica/inf15-1-05?id=informatica%2Finf15-1-05",
• URL = "http://content.iospress.com/articles/informatica/inf15-1-05",
• timestamp = "Mon, 18 May 2015 17:23:14 +0200",
• biburl = "http://dblp.uni-trier.de/rec/bib/journals/informaticaLT/LehirecheR04",
• bibsource = "dblp computer science bibliography, http://dblp.org",
• size = "14 pages",
• abstract = "Evolutionary Engineering (EE) is defined to be the art of using evolutionary algorithms approach such as genetic algorithms to build complex systems. This paper deals with a neural net based system. It analyses ability of genetically trained neural nets to control Simulated robot arm, witch tries to track a moving object. In difference from classical Approaches neural network learning is performed on line, i.e., in real time. Usually systems are built/evolved, i.e., genetically trained separately of their use. That is how it is commonly done. It is a fact that evolution process is heavy on time; that is why Real-Time approach is rarely taken into consideration. The results presented in this paper show that such approach (Real-Time EE) is possible. These successful results are essentially due to the continuity of the target's trajectory. In EE terms, we express this by the Neighbourhood Hypothesis (NH) concept.",
• notes = "Institute of Mathematics and Informatics, Vilnius",

}

Genetic Programming entries for Ahmed Lehireche Abdellatif Rahmoun

Citations