Strategy planning by an intelligent machine

The Center for Engineering Systems Advanced Research (CESAR) has recently been established at the Oak Ridge National Laboratory (ORNL) to address long-range, energy-related research in intelligent control systems. The purpose of this paper is to describe our initial investigations in developing efficient strategies to be used by an autonomous robot with hierarchical control structure operating in an unstructured, real-world environment. This research is an integral part of a system with complementary efforts in mathematical modeling, real-time control, sensor integration, etc. Our current work builds upon traditional areas of strength in artificial intelligence (i.e., knowledge representation, inferential reasoning, and parallel planning) through the application requirements of real-time decision making and on-line learning.