×

Cross-paradigm analysis of autonomous agent architecture. (English) Zbl 1033.68592

Summary: Autonomous agent architectures are design methodologies – collections of knowledge and strategies which are applied to the problem of creating situated intelligence. This article attempts to integrate this knowledge across several architectural traditions, paying particular attention to features which have tended to be selected under the pressure of extensive use in real-world systems. We determine that the following strategies provide significant assistance in the design of autonomous intelligent agents: (i) modularity, which simplifies both design and control; (ii) hierarchically organized action selection, which focusses attention and provides prioritization when different modules conflict; and (iii) parallel environment monitoring which allows a system to be responsive and opportunistic by allowing attention to shift and priorities to be re-evaluated. We offer a review of four architectural paradigms: behaviour-based AI; two- and three-layered systems; belief, desire and intention architectures (particularly PRS); and Soar/ACT-R. By documenting trends within each of these communities towards establishing the components above, we argue that this convergent evolution is strong evidence for the components’ utility. We then use this information to recommend specific strategies for researchers working under each paradigm to further exploit the knowledge and experience of the field as a whole.

MSC:

68T01 General topics in artificial intelligence
68U99 Computing methodologies and applications

Software:

SOAR
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Adams J. A., Psychological Bulletin 96 (1) pp 3– (1984) · doi:10.1037/0033-2909.96.1.3
[2] Albus J. S., Journal of Experimental and Theoretical Artificial Intelligence 9 (2) pp 147– (1997)
[3] Anderson J. R., Rules of the Mind (1993)
[4] Anderson J. R., Rational Models of Cognition (1998)
[5] Appleby S., BT Technology Journal 12 (2) pp 104– (1994)
[6] Baerends G. P., Animal Behaviour 24 pp 726– (1976) · doi:10.1016/S0003-3472(76)80002-4
[7] Barber, K. S. and Martin, C. E. Agent autonomy: specification, measurement, and dynamic adjustment. Proceedings of the Autonomy Control Software Workshop at Autonomous Agents (Agents ’99). Seattle, WA. pp.8–15.
[8] Bates J., Technical Report CMU-CS-92-144, in: An architecture for action, emotion, and social behavior (1992)
[9] Beer R. D., Mind as Motion: Explorations in the Dynamics of Cognition pp 121– (1995)
[10] Benson S., Learning actionmodels for reactive autonomous agents (1996)
[11] Bizzi E., Trends in Neuroscience 18 pp 442– (1995) · doi:10.1016/0166-2236(95)94494-P
[12] Blumberg B. M., Old tricks, new dogs : ethology and interactive creatures (1996)
[13] Bohm D., Wholeness and the Implicate Order (1980)
[14] Bonasso R. P., Journal of Experimental and Theoretical Artificial Intelligence 9 (2) pp 237– (1997) · Zbl 05468589 · doi:10.1080/095281397147103
[15] Breazeal C., Proceedings of the International Conference on Intelligent Robots (IROS-99) pp 858– (1999)
[16] Brooks R. A., IEEE Journal of Robotics and Automation 2 pp 14– (1986) · doi:10.1109/JRA.1986.1087032
[17] Brooks R. A., Proceedings of the 1991 International Joint Conference on Artificial Intelligence pp 569– (1991)
[18] Brooks R. A., American Assoc. of Act. Inf. pp 961– (1998)
[19] Bruner J. S., The Analysis of Action pp 313– (1982)
[20] Bryson J., The subsumption strategy development of a music modelling system (1992)
[21] Bryson J., The Biology and Technology of Intelligent Autonomous Agents (1995)
[22] Bryson J., AISB’99 Symposium on Creativity in Entertainment and Visual Art pp 9– (1999)
[23] Bryson J., Intelligent Virtual Agents 2 pp 113– (1999)
[24] Bryson J., The study of sequential and hierarchical organisation of behaviour via Artificial mechanisms of action selection (2000)
[25] Bryson J., The Fourth International Workshop on Agent Theories, Architectures, and Languages (ATAL97) (1998)
[26] Byrne R. W., Brain and Behavioral Sciences 21 (5) pp 667– (1998)
[27] Carlson N. R., Physiology of Behavior (1994)
[28] Chapman D., Artificial Intelligence pp 333– (1987)
[29] Chomsky N., Syntactic Structures (1957)
[30] Connell J., Minimalist Mobile Robotics : A Colony-style Architecture for a Mobile Robot (1990) · Zbl 0729.68090
[31] Dawkins R., Growing Points in Ethology pp 7– (1976)
[32] d’Inverno, M., Kinny, D., Luck, M. and Wooldridge, M. A formal specification of dMARS. Proceedings of the Fourth International Workshop on Agent Theories, Architectures and Languages. Edited by: Singh, In M. P., Rao, A. S. and Wooldridge, M. J. Providence, RI: Springer-Verlag. · doi:10.1007/BFb0026757
[33] Firby J., Proceedings of the National Conference on Artificial Intelligence (AAAI) pp 202– (1987)
[34] Fodor J. A., The Modularity of Mind (1983)
[35] Freud S., The Interpretation of Dreams (1900)
[36] Gardner M., Brain and Behavioral Sciences 21 (5) pp 695– (1998) · doi:10.1017/S0140525X98291746
[37] Gat E., Reliable goal-directed reactive control of autonomous mobile robots (1991)
[38] Georgeff M. P., Proceedings of the Sixth National Conference on Artificial Intelligence (AAAI-87) pp 677– (1987)
[39] Goldfield E. C., Emergent Forms : origins and early development of human action and perception (1995)
[40] Greenfield P. M., Brain and Behavioral Sciences 14 pp 531– (1991) · doi:10.1017/S0140525X00071235
[41] Hendriks-Jansen H., Catching Ourselves in the Act: Situated Activity, Interactive Emergence, Evolution, and Human Thought (1996)
[42] Henson R. N. A., Short-term memory for serial order (1996)
[43] Hexmoor H. H., Representing and learning routine activities (1995)
[44] Hexmoor H., Journal of Experimental and Theoretical Artificial Intelligence 9 (2) pp 123– (1997) · doi:10.1080/095281397147040
[45] Horswill I. D., Specialization of perceptual processes (1993)
[46] Houghton G., PSYCHE 2 (25) (1995)
[47] Huber M. J., Proceedings of the Third International Conference on Autonomous Agents (Agents ’99) pp 236– (1999) · doi:10.1145/301136.301202
[48] Hull C., Principles of Behaviour: an Introduction to Behaviour Theory (1943)
[49] Hume D., Essay Concerning Human Understanding (1748)
[50] Humphrys M., Action selection methods using reinforcement learning (1997)
[51] Jorion P. J. M., Brain and Behavioral Sciences 21 (5) pp 695– (1998) · doi:10.1017/S0140525X98341746
[52] Karmiloff-Smith A., Beyond Modularity : A Developmental Perspective on Cognitive Change (1992)
[53] Kelso J. S., Dynamic Patterns : The Self-Organization of Brain and Behavior (1995)
[54] Kitano H., Proceedings of The First International Conference on Autonomous Agent (1997)
[55] Kline C., AISB’99 Symposium on AI and Creativity in Entertainment and Visual Art pp 16– (1999)
[56] Kortenkamp D., Artificial Intelligence and Mobile Robots : Case Studies of Successful Robot Systems (1998)
[57] Laird J. E., Technical Report CSE-TR-219-94, in: The evolution of the Soar cognitive architecture (1994)
[58] Lashley K. S., Cerebral mechanisms in behavior (1951)
[59] Leon, V., Kortenkamp, D. and Schreckenghost, D. A planning, scheduling and control architecture for advanced life support systems. NASA Workshop on Planning and Scheduling for Space. Oxnard, CA.
[60] Mac Aogáin E., Brain and Behavioral Sciences 21 (5) pp 696– (1998) · doi:10.1017/S0140525X98361749
[61] Maes P., Designing Autonomous Agents : Theory and Practice from Biology to Engineering and back (1990)
[62] Maes P., Designing Autonomous Agents: Theory and Practice from Biology to Engineering and Back pp 49– (1990)
[63] Maes P., SIGART Bulletin 2 (4) pp 115– (1991) · doi:10.1145/122344.122367
[64] Maes P., From Animals to Animats pp 478– (1991)
[65] Malcolm C., DAI Research Paper 875, in: A hybrid behavioural/knowledge-based approach to robotic assembly (1997)
[66] Marjanovic M., From Animals to Animats 4 (SAB96) (1996)
[67] Matarić M. J., Technical Report 1228, in: Adistributed model formobile robot environment-learning and navigation (1990)
[68] Matheson T., Journal of Experimental Biology 200 pp 93– (1997)
[69] McClelland J., Parallel Distributed Processing: Explorations in the Microstructure of Cognition (1988)
[70] McDougall W., Outline of Psychology (1923)
[71] McGurk H., Nature 264 pp 746– (1976) · doi:10.1038/264746a0
[72] Minsky M., The Society of Mind (1985)
[73] Myers, K. L. A procedural knowledge approach to task-level control. Proceedings of the Third International Conference on AI Planning Systems. Edinburgh.
[74] Neely J. H., Basic Processes in Reading: Visual Word Recognition (1991)
[75] Nelson K., Netherlands Journal of Zoology 40 (4) pp 585– (1990) · doi:10.1163/156854290X00127
[76] Newell A., Unified Theories of Cognition (1990)
[77] Newell A., Human Problem Solving (1972)
[78] Nilsson N., Technical note 323, in: Shakey the robot (1984)
[79] Nilsson N., Journal of Artificial Intelligence Research 1 pp 139– (1994)
[80] Norman D. A., Consciousness and Self Regulation : Advances in Research and Theory pp 1– (1986) · doi:10.1007/978-1-4757-0629-1_1
[81] Parker L. E., IEEE Transactions on Robotics and Automation 14 (2) (1998) · doi:10.1109/70.681242
[82] Pebody M., Advances in Artificial Life (Third European Conference on Artificial Life) pp 679– (1995)
[83] Piaget J., The Construction of Reality in the Child (1954) · doi:10.1037/11168-000
[84] Port R. F., Mind as Motion : Explorations in the Dynamics of Cognition (1995)
[85] Reeves R., Intelligent Autonomous Systems Four (IAS95) (1995)
[86] Reilly W. S. N., Technical Report CMU-CS-96-138, in: Believable social and emotional agents (1996)
[87] Rosenblatt K., Proceedings of the IEEE/INNS International Joint Conference on Neural Networks (1989)
[88] Russell S. J., Artificial Intelligence: A Modern Approach (1995) · Zbl 0835.68093
[89] Saltzman E. L., Mind as Motion : Explorations in the Dynamics of Cognition (1995)
[90] Sloman A., Proceedings of the Second European Conference on Cognitive Modelling pp 58– (1998)
[91] Steels L., The ’Artificial life’ route to ’Artificial intelligence’. Building situated embodied agents (1994)
[92] Stone P., Artificial Intelligence 110 (2) pp 241– (1999) · Zbl 1047.68631 · doi:10.1016/S0004-3702(99)00025-9
[93] Thórisson K. R., International Journal of Applied Artificial Intelligence 13 (4) pp 519– (1999)
[94] Tinbergen N., The Study of Instinct (1951) · Zbl 0045.23203
[95] Townsend J. T., Mind as Motion: Explorations in the Dynamics of Cognition pp 101– (1995)
[96] Tyrrell T., Computational mechanisms for action selection (1993)
[97] van Gelder T., Behavioral and Brain Sciences 21 (5) pp 616– (1998)
[98] Vereijken B., Brain and Behavioral Sciences 21 (5) pp 695– (1998) · doi:10.1017/S0140525X98451744
[99] Wilkins D. E., Proceedings of AIPS-98 pp 154– (1998)
[100] Wilkins D. E., Journal of Experimental and Theoretical Artificial Intelligence 7 (1) pp 197– (1995) · Zbl 0939.68834 · doi:10.1080/09528139508953802
[101] Wooldridge M., Knowledge Engineering Review 10 (2) pp 115– (1995) · doi:10.1017/S0269888900008122
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.