Skip to Main Content
One of the main challenges of any related paradigms in systems engineering is being able to handle complex systems under unforeseen uncertainties. A system may be called complex if its dimension (order) is too high and its model (if available) is nonlinear, interconnected, and information on the system is so uncertain that classical techniques cannot easily handle the problem. A system of systems (SoS) is a "super system," or an integration of complex systems coordinated together in such a way as to achieve a wider set of goals with possible higher significance such as global warming, Mars missions, air traffic control, global earth observation system, etc. Computational Intelligence or Soft Computing, a consortium of fuzzy logic (approximate reasoning), neuro-computing (learning), genetic algorithms and genetic programming (optimization), has proven to be a powerful set of tools for adding autonomy and semi-autonomy to many complex systems. For such systems the size of soft computing control architecture will be nearly infinite. In this presentation, paradigms using soft computing approaches are utilized to design autonomous controller with controller reuse for a number of space applications. The notion of adaptation in autonomous controller reuse can be handled via intelligent tools to add on additional capabilities in real-time scenarios. Learning from past experience is but one such scenario for the reuse of autonomous controllers. These applications include satellite array formations, robotic agents and the Virtual Laboratory (V-LAB??) for multi-physics modeling and simulation.