FROM CONVENTIONAL CONTROL TO AUTONOMOUS INTELLIGENT METHODS

In this article we review the growth and development of control engine ering, leading to modern adaptive methods and finally to autonomous in telligent control. Although the use of feedback control can be traced back to ancient and medieval times, it is really during the 20th centu ry, with the evolution of the electronics age, that control engineerin g has become a recognized discipline. Well-established methods to mode l and control plants with linear characteristics and unchanging parame ters are already in existence. Nonlinear plants with time-varying inte rnal parameters are more challenging and the so-called ''adaptive'' me thods have been developed to address this issue. The abundance of powe rful computers has led us to think, in terms of controllers that can ' 'learn'' using AI techniques such as expert systems, genetic algorithm s, neural networks, etc. These paradigms have evolved mostly from stud ying biological learning processes. ''Intelligent control'' and ''neur ocontrol'' are terms that are recognized in the literature today as me thods distinct from the more ''conventional'' control methods of the p ast few decades. Future advances in this science will be in the direct ion of: the development of controllers that can learn to improve their performance and to plan while they learn a particular task.