An Adaptive Architecture for Physical Agents

In this paper we describe ICARUS, an adaptive architecture for intelligent physical agents. We contrast the frameworkýs assumptions with those of earlier architectures, taking examples from an in-city driving task to illustrate our points. Key differences include primacy of perception and action over problem solving, separate memories for categories and skills, a hierarchical organization on both memories, strong correspondence between long-term and short-term structures, and cumulative learning of skill hierarchies. We support claims for ICARUSý generality by reporting our experience with driving and three other domains. In closing, we discuss limitations of the current architecture and propose extensions that would remedy them.

[1]  Adele E. Howe,et al.  Improving the Reliability of Artificial Intelligence Planning Systems by Analyzing their Failure Recovery , 1995, IEEE Trans. Knowl. Data Eng..

[2]  P. Johnson-Laird.  Mental models , 1989 .

[3]  Amy L. Lansky,et al.  A Procedural Logic , 1985, IJCAI.

[4]  Anand S. Rao,et al.  An Abstract Architecture for Rational Agents , 1992, KR.

[5]  Allen Newell,et al.  SOAR: An Architecture for General Intelligence , 1987, Artif. Intell..

[6]  David P. Miller,et al.  Experiences with an architecture for intelligent, reactive agents , 1995, J. Exp. Theor. Artif. Intell..

[7]  Allen Newell,et al.  Human Problem Solving. , 1973 .

[8]  James S. Albus,et al.  Engineering of Mind: An Introduction to the Science of Intelligent Systems , 2001 .

[9]  K. VanLehn.  Mind Bugs: The Origins of Procedural Misconceptions , 1990 .

[10]  Allen Newell,et al.  Computer science as empirical inquiry: symbols and search , 1976, CACM.

[11]  Steven Minton,et al.  Quantitative Results Concerning the Utility of Explanation-based Learning , 1988, Artif. Intell..

[12]  John R. Anderson,et al.  Rules of the Mind , 1993 .

[13]  Pat Langley,et al.  An architecture for persistent reactive behavior , 2004, Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems, 2004. AAMAS 2004..

[14]  Ron Sun,et al.  From implicit skills to explicit knowledge: a bottom-up model of skill learning , 2001, Cogn. Sci..

[15]  Jaime G. Carbonell,et al.  Derivational Analogy in PRODIGY: Automating Case Acquisition, Storage, and Utilization , 1993, Machine Learning.

[16]  Michael Freed,et al.  Managing Multiple Tasks in Complex, Dynamic Environments , 1998, AAAI/IAAI.

[17]  A. Newell.  Unified Theories of Cognition , 1990 .

[18]  David E. Kieras,et al.  An Overview of the EPIC Architecture for Cognition and Performance With Application to Human-Computer Interaction , 1997, Hum. Comput. Interact..

[19]  Pat Langley,et al.  Hierarchical Skills and Cognitive Architectures , 2004 .

[20]  Allen Newell,et al.  The logic theory machine-A complex information processing system , 1956, IRE Trans. Inf. Theory.

[21]  Pat Langley,et al.  Retrieval and Learning in Analogical Problem Solving , 2007 .

[22]  Pat Langley,et al.  Learning Teleoreactive Logic Programs from Problem Solving , 2005, ILP.

[23]  John E. Laird,et al.  Accounting for Graded Performance within a Discrete Search Framework , 1996, Cogn. Sci..

[24]  Nils J. Nilsson,et al.  Teleo-Reactive Programs for Agent Control , 1993, J. Artif. Intell. Res..