Plenary lecture IV: Advances in multimodel control

Summary form only given, as follows. In the past ten years, scientists have been interested in the multimodel approach as a technique to study large, non linear and/or non stationary complex systems with partial or total uncertainty. The implications of systems complexity were given by L. Zadeh in his statement of the incompatibility principle: "As the complexity of a system increases, our ability to make precise and yet significant statements about its behavior diminishes until a threshold is reached beyond which precision and significance (or relevance) become almost mutually exclusive characteristics." This principle justifies our need to have recourse to methods and techniques related to soft computing with limited use of precise knowledge as was the case with classical control methods. Hence, fuzzy logic, human expertise and validity estimation appear as well adapted techniques in the multimodel control. In this talk, we present new advances based on our recent work on this topic and propose to position it within the framework of most recent literature.