Artificial intelligence methods based analysis and control of complex nonlinear systems
Deprecation warning
This website is now archived. Please check out the new website for Centre for Intelligent Systems which includes both A-Lab Control Systems Research lab and Re:creation XR lab.
On this site, please find older content as well, such as list of older completed projects and publications.
The aim of the project is to develop a control strategy combining advantages of classical analytical and different artificial intelligence based methods. The designed system should be capable of automatic control of complex multidimensional and hardly analyzable systems. An intelligent control system should be able not only to make decisions according to a predefined algorithm or/and scenario but also to adapt to changing environment. The adaptive system has
- to be able to react to changes in its environment. It means be reactive;
- to analyze and predict the behavior of its environment. It means be proactive;
- to adjust itself and change its own behavior in response to disturbances and changes in environmental conditions.
Modern time complex intelligent control system consists of two main parts: adaptive control algorithm plus situation awareness. There exist a number of classical control techniques the robustness and high reliability of which is proven by decades. Nevertheless, nowadays in more and more applications we need to control complex systems and processes which cannot (or it is not a trivial task) be represented by classical models. In these applications we need algorithms combining advantages of classical and artificial intelligence based methods. During the last ten years has significantly grown the demand for automatic systems and devices in live-critical applications. This dramatically increases the requirements imposed to the quality of the control system. It means that more and more advanced control systems, precise and as simple as possible control task oriented models of very complex multidimensional and highly nonlinear systems are required. In the framework of this project research will be conducted in two directions, which are connected to each other:
- reliable and satisfying high quality demands control algorithms for complex nonlinear multidimensional systems;
- artificial intelligence based methods for precise recognition of environmental situation by real-time analysis of observed image, video and numerical data.