Context-based adaptive control in autonomous systems

In this paper we introduce the concept of a context as a tool for adaptive control in autonomous systems. We provide a mechanism to represent the context information, and apply it to devise a practical methodology to prioritize the operations in an autonomous system. We illustrate the methodology using an intrusion management system and an autonomous battlefield theater. The context specification information is used as input parameters to the decision support mechanism that controls the operations in an autonomous system. Our specification of the context allows it to change dynamically, as the system operations progress. A context that changes dynamically thus provides a modified set of input parameters to the operations control mechanism, so that the forward-looking behavior of the autonomous system can be modulated in an adaptive manner.