| Suggested Paper Classification: 07F1 "Cognitive Wireless Systems" or, possibly, 10Bi "Cognitive Wireless Communications and Sensing in Networks"
------------------------------------------------
The ultimate vision of cognitive radio technology encompasses many capabilities including autonomous execution of tasks that today require manual intervention. A conventional radio when operating in a particular communications mode always follows the same procedure and either succeeds or fails at a given task. A cognitive radio, by contrast, can have a "knowledge-driven differential-response" capability; that is, it can use knowledge of radio technology and policy, representations of the goals, and other contextual parameters to reason about a failed attempt to satisfy a goal and to identify alternative actions that would achieve the goal. We have built a prototype simulation framework for a cognitive radio that exhibits this capability in various scenarios. Based upon this experience, this paper proposes a general architecture that merges knowledge-representation technologies (both ontologies and rules) with the processing structures of existing software defined radio technology to enable this capability as well as form a foundation for other cognitive abilities. Besides motivating and describing the general architecture, we show how the prototype successfully simulates knowledge-driven differential response in a scenario where a cognitive radio can interactively guide its user to a location where a desired service is available. |