Decision-Making in an Embedded Reasoning System

Abstract

The development of reasoning systems that can reason and plan in a continuously changing environment is emerging as an important area of research in Artificial Intelligence. This paper describes some of the features of a Procedural Reasoning System (PRS) that enables it to operate effectively in such environments. The basic system design is first described and it is shown how this architecture supports both goaldirected reasoning and the ability to react rapidly to unanticipated changes in the environment. The decision-making capabilities of the system are then discussed and it is indicated how the system integrates these components in a manner that takes account of the bounds on both resources and knowledge that typify most real-time operations. The system has been applied to handling malfunctions on the space shuttle, threat assessment, and the control of an autonomous robot. 1