Avtor/Urednik		Filipič, Bogdan; Urbančič, Tanja; Križman, Viljem
Naslov		Optimiranje pravil za obvladovanje nihanja na modelni napravi
Prevedeni naslov		Optimizing rules for swing control on a model device
Tip		članek
Vir		In: Zajc B, editor. Zbornik 7. elektrotehniške in računalniške konference ERK'98. Zvezek B. Računalništvo in informatika, umetna inteligenca, robotika, razpoznavanje vzorcev, biomedicinska tehnika, močnostna elektrotehnika, didaktika, študentski članki; 1998 sep 24-26; Portorož. Ljubljana: Slovenska sekcija IEEE,
Leto izdaje		1998
Obseg		str. 133-6
Jezik		slo
Abstrakt		The paper illustrates the potential of genetic algorithms in controller optimazition. The focus is on tuning the parameters of control rules obtained from traces of human performance. The task considered in the study is the control of load swinging on a model container crane. In the optimization procedure carried out with a genetic algorithm, rule parameter settings were iteratively improved with respect to a selected criterion through experiments on a physical device. The resulting rules exhibited better performance and different control strategy in comparison with human control.
Deskriptorji		ALGORITHMS ARTIFICIAL INTELLIGENCE MAN-MACHINE SYSTEMS