One of the biggest challenges of anp control paradigm is being able to hand
le large complex systems under unforeseen uncertainties. A system may be ca
lled complex here if its dimension (order) is too high and its model (if av
ailable) is nonlinear, interconnected, and information on the system is unc
ertain such that classical techniques cannot easily handle the problem. Sof
t computing, a collection of fuzzy logic, neuro-computing, genetic algorith
ms and genetic programming, has proven to be a powerful tool for adding aut
onomy to many complex systems. For such systems the size soft computing con
trol architecture will be nearly infinite. Examples of complex systems are
power networks, national air traffic control system, an integrated manufact
uring plant, etc. In this paper a new rule base reduction approach is sugge
sted to manage large inference engines. Notions of rule hierarchy and senso
r data fusion are introduced and combined to achieve desirable goals. New p
aradigms using soft computing approaches are utilized to design autonomous
controllers for a number of robotic applications at the ACE Center are also
presented briefly, (C) 2001 Published by Elsevier Science Inc.