Integration of linguistic and numerical information for hybrid intelligent control

For complex engineering systems, two kinds of information are available; numerical data received from sensor measurement, and linguistic rules obtained from human operators and domain experts. However, some of information obtained in this manner are hybrid, that is, their components are not homogeneous but a blend of direct and indirect, numerical and linguistic information. In order to integrate the above linguistic and numerical information for hybrid intelligent control, which employ an integration of fuzzy logic, neural networks, genetic algorithms and related intelligent control methodologies, based on inverse learning and some simple and intuitive information combination operators, we propose two integration schemes. One is neurofuzzy based integration, and another is fuzzy rules extraction based integration. The effectiveness of the proposed methods are verified through hybrid intelligent control of a biped walking robot.