Rational Agents, Simulation and Military Operations

This paper expands on a proposed methodology for applying simulation technology to the monitoring and control of ongoing operations. It focuses on the use of rational agents, called Operations Monitors, to compare the progress of the real operation with that of the planned operation. When the Operations Monitors detect differences that threaten the success of the plan, they advise the decision-maker. The purpose of such a system is to avoid information overload of decision-make rs by helping focus attention on those aspects of the operation that have a direct, adverse impact on the probability of mission success. For tractability, each Operations Monitor focuses on a narrow portion of the problem domain. These Operations Monitors operate within a dynamic hieracrchy that expands and contracts as necessary. This paper focuses on the structure and communications mechanisms of the agents as well as the principle that guides the automatic and discretionary instantiation of Operations Monitors. The contributions of this research are 1) to help identify the requirements for a simulation designed for use during operations and 2) the development of a methodology for using simulation, along with rational agents, to compare the real, ongoing operation with the planned operation and make recommendations when appropriate. While several training simulations have been developed, there are currently no tools that provide this simulation-based, agent-assisted operation monitoring/analysis capability to decision-makers.

[1]  Caroline C. Hayes,et al.  DAISY: a design methodology for experience-centered planning support systems , 1998, SMC'98 Conference Proceedings. 1998 IEEE International Conference on Systems, Man, and Cybernetics (Cat. No.98CH36218).

[2]  Udo W. Pooch,et al.  OPSIM: A PURPOSE-BUILT DISTRIBUTED SIMULATION FOR THE MISSION OPERATIONAL ENVIRONMENT , 1999 .

[3]  Raymond J. Mooney,et al.  Theory Refinement Combining Analytical and Empirical Methods , 1994, Artif. Intell..

[4]  Gary Riley,et al.  Expert Systems: Principles and Programming , 2004 .

[5]  Susan I. Hruska,et al.  Hybrid systems: the equivalence of rule-based expert system and artificial neural network inference , 1991 .

[6]  Arthur C. Graesser,et al.  Is it an Agent, or Just a Program?: A Taxonomy for Autonomous Agents , 1996, ATAL.

[7]  Lars Schoultz The Bay of Pigs , 2009 .

[8]  B Hoerni,et al.  Janus , 2007, Revue medicale suisse.

[9]  Pattie Maes,et al.  Agents that reduce work and information overload , 1994, CACM.

[10]  Pattie Maes,et al.  Situated agents can have goals , 1990, Robotics Auton. Syst..

[11]  R. C. Lacher,et al.  Expert networks: Paradigmatic conflict, technological rapproachement , 1993, Minds and Machines.

[12]  J. Yen,et al.  Fuzzy Logic: Intelligence, Control, and Information , 1998 .

[13]  Udo W. Pooch,et al.  Connecting the Operational Environment to a Simulation , 2010 .

[14]  D. E. Sackett Simulations to save time, money, and lives , 1996 .

[15]  J. R. Surdu,et al.  A methodology for applying simulation technologies in the mission operational environment , 1998, 1998 IEEE Information Technology Conference, Information Environment for the Future (Cat. No.98EX228).

[16]  Pattie Maes,et al.  Designing autonomous agents: Theory and practice from biology to engineering and back , 1990, Robotics Auton. Syst..

[17]  Thomas G. Dietterich What is machine learning? , 2020, Archives of Disease in Childhood.

[18]  Victor Andres Triay,et al.  Bay of Pigs , 2001 .

[19]  Barbara Hayes-Roth,et al.  An Architecture for Adaptive Intelligent Systems , 1995, Artif. Intell..

[20]  Susan I. Hruska,et al.  Back-propagation learning in expert networks , 1992, IEEE Trans. Neural Networks.

[21]  P. Maes How to Do the Right Thing , 1989 .

[22]  Amanda Vizedom Command Post of the Future , 2003 .