Abstract
Evolutionary Engineering (EE) is defined to be "the art of using Evolutionary algorithms approach such as genetic algorithms to build complex systems". Usually systems are built/evolved i.e. genetically trained separately of their utilization. That is how it is commonly done. It's a fact that evolution process is heavy on time; that's why Real-Time approach is rarely taken into consideration. This paper analyses ability of genetically trained neural nets to control simulated 3D robot arm tracking a moving object. Indifference from classical Approaches neural network learning (evolution) is performed on line i.e. in real time. The results presented in this paper show that 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 Neighborhood Hypothesis (NH) concept.