Issue No. 01 - January (1995 vol. 28)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/2.362628
The research agendas of artificial intelligence and real-time systems are converging as AI methods move toward domains that require real-time responses, and real-time systems move toward complex applications that require intelligent behavior. They meet at the crossroads in an exciting new subfield commonly called "real-time AI." This subfield is still being defined, and the precise goals for various real-time AI systems are in flux. Traditionally, AI systems have been developed without much attention to the resource limitations that motivate real-time systems researchers. However, as these AI systems move from the research labs into real-world applications, they also become subject to the time constraints of the environments in which they operate. Rigorous design techniques developed by real-time systems re-searchers must be used to guarantee that a system will meet domain deadlines, even in worst-case scenarios, particularly for mission-critical assignments. The authors would like to combine guaranteed performance methods with AI planning, problem-solving, and adaptation mechanisms to build a flexible, intelligent control system that can dynamically plan its own behaviors. They describe an organizing conceptual structure, identify research goals, and specify some necessary steps for reaching them. They illustrate possible approaches with important applications that require the best of both fields. A series of examples are provided from an intensive care domain where an intelligent real-time control system could provide constant monitoring of patient needs.
A. K. Agrawala, J. A. Hendler, C. Paul, J. K. Strosnider, D. J. Musliner and E. H. Durfee, "The Challenges of Real-Time AI," in Computer, vol. 28, no. , pp. 58-66, 1995.