Modeling Human Behavior With Integrated Cognitive Architectures: Comparison, Evaluation, and Validation

The Air Force Research Laboratory and the Office of Naval Research funded a multi-year project with several objectives: to build computer models that would allow comparisons to be made between humans and machines performing the same tasks - specifically, multiple task management and attention sharing within Air Traffic Control system; to see how well these models would perform in different task scenarios; to build a standard modeling architecture so that components could be added to the basic model by research laboratories all over the world; and to incorporate an Al system within the computer models that will allow the systems to learn from their tasks. This book summarizes the results of four years of collaborative research within this project. Its publication accomplishes three goals: it provides a single coherent reference source documenting the human data and models from the AMBR Model Comparison, shares lessons learned and insights with the members of the scientific and technical communities who are most likely to benefit from them, and stimulates and motivates additional research and future model comparison. Modeling Human Behavior With Integrated Cognitive Architectures will be essential for military, governmental, and institutional scientists who work on the design, optimization, and training of workers in complex task management and decision making. It will also be useful in graduate courses in cognitive psychology and cognitive, industrial, and computer science engineering.

Table of Contents:
Contents: Preface. Part I: Overview, Experiments, and Software.K.A. Gluck, R.W. Pew, M.J. Young, Background, Structure, and Preview of the Model Comparison. Y.J. Tenney, D.E. Diller, S. Deutsch, K. Godfrey, The AMBR Experiments: Methodology and Human Benchmark Results. S. Deutsch, D.E. Diller, B. Benyo, L. Feinerman, The Simulation Environment for the AMBR Experiments. Part II: Models of Multitasking and Category Learning.C. Lebiere, Constrained Functionality: Application of the ACT-R Cognitive Architecture to the AMBR Modeling Comparison. W. Zachary, J. Ryder, J. Stokes, F. Glenn, J-C. Le Mentec, T. Santarelli, A COGNET/iGEN Cognitive Model That Mimics Human Performance and Learning in a Simulated Work Environment. R.G. Eggleston, K.L. McCreight, M.J. Young, Distributed Cognition and Situated Behavior. R.S. Chong, R.E. Wray, Inheriting Constraint in Hybrid Cognitive Architectures: Applying the EASE Architecture to Performance and Learning in a Simplified Air Traffic Control Task. Part III: Conclusions, Lessons Learned, and Implications.D.E. Diller, K.A. Gluck, Y.J. Tenney, K. Godfrey, Comparison, Convergence, and Divergence in Models of Multitasking and Category Learning, and in the Architectures Used to Create Them. B.C. Love, In Vivo or In Vitro: Cognitive Architectures and Task-Specific Models. G.E. Campbell, A.E. Bolton, HBR Validation: Integrating Lessons Learned From Multiple Academic Disciplines, Applied Communities, and the AMBR Project. R.W. Pew, K.A. Gluck, S. Deutsch, Accomplishments, Challenges, and Future Directions for Human Behavior Representation.

About the Author :
Kevin A. Gluck (Edited by) ,  Richard W. Pew (Edited by)