On linguistic decision making devices

This paper describes the development of a new, hierarchical, linguistic based, learning control structure for Complex systems. The complete system will be able to interact with a human operator in a limited natural language at the highest level of the hierarchy, but will be able to control detailed motions of some complex physical system at the lowest level of the hierarchy. Each level of the hierarchy is defined by a formal grammar which can generate exactly the class of admissible control actions at that level. A new linguistic structure, the linguistic decision schema, is proposed to specify the mapping between linguistic elements in adjacent levels. In the most general form, the decision schema incorporates a learning algorithm to obtain asymptotically optimal mappings for control under stochastic environments.