Abstract
This article aims to present an account of the state of the art research in the field of integrated cognitive architectures by providing a review of six cognitive architectures, namely Soar, ACT-R, ICARUS, BDI, the subsumption architecture and CLARION. We conduct a detailed functional comparison by looking at a wide range of cognitive components, including perception, memory, goal representation, planning, problem solving, reasoning, learning, and relevance to neurobiology. In addition, we study the range of benchmarks and applications that these architectures have been applied to. Although no single cognitive architecture has provided a full solution with the level of human intelligence, important design principles have emerged, pointing to promising directions towards generic and scalable architectures with close analogy to human brains.
Similar content being viewed by others
References
Amir E, Maynard-Zhang P (2004) Logic-based subsumption architecture. Artif Intell 153: 167–237
Anderson M (2003) Embodied cognition: a field guide. Artif Intell 149: 91–130
Anderson J, Schunn C (2000) Implications of the ACT-R learning theory: No magic bullets. Adv Instr Psychol 5: 1–34
Anderson JR, Bothell D, Byrne MD, Douglass S, Lebiere C, Qin Y (2004) An intergrated theory of the mind. Psychol Rev 111: 1036–1060
Bratman M, Israel D, Pollack M (1988) Plans and resource-bounded practical reasoning. Comput Intell 4(4): 349–355
Braubach L, Pokahr A, Moldt D, Lamersdorf W (2005) Goal representation for BDI agent systems. In: Proceedings, 2nd international workshop on programming multiagent systems: languages and tools, pp 9–20
Brooks RA (1991) How to build complete creatures rather than isolated cognitive simulators. In: Proceedings, architectures for intelligence, pp 225–240
Brooks R (1999) Cambrian intelligence: the early history of the new AI. MIT Press, Boston, MA
Bryson J, Smaill A, Wiggins G (2005) The reactive accompanist: applying subsumption architecture to software design. Tech. rep., Department of Artificial Intelligence, University of Edinburgh
Butler G, Gantchev A, Grogona P (2001) Object-oriented design of the subsumption architecture. Softw Pract Exper 31: 911–923
Chong RS (2004) Architectural explorations for modeling procedural skill decay. In: Proceedings, sixth international conference on cognitive modeling
Dastani M, van der Torre L (2002) An extension of BDI CTL with functional dependencies and components. In: Proceedings, 9th international conference on logic for programming, artificial intelligence, and reasoning, pp 115–129
Dastani M, Hulstijn J, van der Torre L (2001) BDI and QDT: a comparison based on classical decision theory. In: Proceedings, AAAI symposium, pp 16–26
Dennett D (1987) The intentional stance. MIT Press, Cambridge MA
Georgeff M, Ingrand F (1989) Decision-making in an embedded reasoning system. In: Proceedings, international joint conference on artificial intelligence, pp 972–978
Guerra-Hernandez A, Fallah-Seghrouchni AE, Soldano H (2004) Learning in BDI multi-agent systems. In: Proceedings, 4th international workshop on computational logic in multi-agent systems. Fort Lauderdale, FL
Hartley R, Pipitone F (1991) Experiments with the subsumption architecture. In: Proceedings, IEEE international conference on robotics and automation, pp 1652–1658
Köse H (2000) Towards a robust cognitive architecture for autonomous mobile robots. Master’s thesis, Boğaziçi University
Kopp S, Gesellensetter L, Krämer N, Wachsmuth I (2005) A conversational agent as museum guide—design and evaluation of real-world application. Intell Virtual Agents 5: 329–343
Laird J, Newell A, Rosenbloom P (1987) SOAR: An architecture for general intelligence. Artif Intell 33(1): 1–64
Laird J, Rosenbloom P, Newell A (1986a) Chunking in Soar: The anatomy of a general learning mechanism. Mach Learn 1: 11–46
Laird J, Rosenbloom P, Newell A (1986b) Universal subgoaling and chunking: the automatic generation and learning of goal hierarchies. Kluwer, Boston, MA
Langley P (2004) A cognitive architecture for physical agents. Retrieved 28 Oct 2006 from http://www.isle.org/~langley/talks/icarus.6.04.ppt
Langley P, Choi D (2006) A unified cognitive architecture for physical agents. In: Proceedings, twenty-first national conference on artificial intelligence, pp 1469–1474
Langley P, Arai S, Shapiro D (2004) Model-based learning with hierarchical relational skills. In: Proceedings, ICML-2004 workshop on relational reinforcement learning
Lehman J, Laird J, Rosenbloom P (2006) A gentle introduction to soar, an architcture for human cognition: 2006 update. Retrieved 17 May 2007 from http://ai.eecs.umich.edu/soar/sitemaker/docs/misc/GentleIntroduction-2006.pdf
Madden M, Howley T (2003) Transfer of experience between reinforcement learning environments with progressive difficulty. Artif Intell Rev 21(3–4): 375–398
Nakashima H, Noda I (1998) Dynamic subsumption architecture for programming intelligent agents. In: Proceedings, IEEE international conference on multi-agent systems, pp 190–197
Newell A (1990) Unified theories of cognition. Harvard University Press, Cambridge, MA
Norling E (2004) Folk psychology for human modelling: extending the BDI paradigm. In: Proceedings, international joint conference on autonomous agents and multi-agent systems (AAMAS’04), pp 202–209
Nuxoll A, Laird J (2004) A cognitive model of episodic memory integrated with a general cognitive architecture. In: Proceedings, sixth international conference on cognitive modeling, pp 220–225
Nuxoll A, Laird J, James M (2004) Comprehensive working memory activation in soar. In: Proceedings, sixth international conference on cognitive modeling, pp 226–230
Rao AS, Georgeff MP (1991) Modeling rational agents within a bdi-architecture. In: Proceedings, second international conference on principles of knowledge representation and reasoning. Morgan Kaufmann, San Mateo, CA, pp 473–484
Rickel J, Johnson W (2000) Task-oriented collaboration with embodied agents in virtual worlds. In: Cassell J, Sullivan J, Prevost S(eds) Embodied conversational agents. MIT Press, Boston, pp 95–122
Sardina S, de Silva L, Padgham L (2006) Hierarchical planning in BDI agent programming languages: a formal approach. In: Proceedings, autonomous agents and multi-agent systems (AAMAS), pp 1001–1008
Si J, Barto AG, Powell WB, Wunsch D (eds) (2004) Handbook of learning and approximate dynamic programming. Wiley-IEEE Press, New York, NY
Stollberg M, Rhomberg F (2006) Survey on goal-driven architectures, Tech. rep., DERI, Austria
Subagdja B, Sonenberg L (2005) Learning plans with patterns of actions in bounded-rational agents. In: Proceedings, 9th international conference on knowledge-based and intelligent information & engineering systems (KES’05), vol 3, pp 30–36
Sun R (2003) A tutorial on CLARION 5.0. Tech. rep., Cognitive Science Department, Rensselaer Polytechnic Institute
Sun R, Peterson T (1996) Learning in reactive sequential decision tasks: the CLARION model. In: Proceedings, IEEE international conference on neural networks, pp 1073–1078
Sun R, Peterson T (1998) Hybrid learning incorporating neural and symbolic processes. In: Proceedings, IEEE international conference on fuzzy systems, pp 727–732
Sun R, Sessions C (1998) Learning to plan probabilistically from neural networks. In: Proceedings of IEEE international conference on neural networks, pp 1–6
Sun R, Zhang X (2006) Accounting for a variety of reasoning data within a cognitive architecture. J Exp Theor Artif Intell 18(2): 169–191
Sun R, Merrill E, Peterson T (2001) From implicit skills to explicit knowledge: a bottom-up model of skill learning. Cogn Sci 25(2): 203–244
Sun R, Slusarz P, Terry C (2005) The interaction of the explicit and the implicit in skill learning: a dual-process approach. Psychol Rev 112(1): 159–192
Sutton R, Barto A (1998) Reinforcement learning: an introduction. MIT Press, Cambridge, MA
Swartout W, Gratch J, Hill REH, Marsella S, Rickel J, Traum D (2006) Toward virtual humans. Artif Intell Mag 27(2): 96–108
Tan A-H (2004) FALCON: a fusion architecture for learning, cognition, and navigation. In: Proceedings, international joint conference on neural networks, pp 3297–3302
Tan A-H (2007) Direct code access in self-organizing neural networks for reinforcement learning. In: Proceedings, international joint conference on artificial intelligence (IJCAI’07), pp 1071–1076
Tan A-H, Carpenter G A, Grossberg S (2007) Intelligence through interaction: towards a unified theory for learning. In: Proceedings, international symposium on neural networks (ISNN’07), LNCS4491, pp 1098–1107
Tan A-H, Lu N, Xiao D (2008) Integrating temporal difference methods and self-organizing neural networks for reinforcement learning with delayed evaluative feedback. IEEE Trans Neural Netw 9(2):230–244
Toal D, Flanagan C, Jones C, Strunz B (1996) Subsumption architecture for the control of robots. In: IMC-13
Vernon D, Metta G, Sandini G (2007) A survey of artificial cognitive systems: implications for the autonomous development of mental capabilities in computational agents. IEEE Trans Evol Comput 11(2): 151–180
Watkins C, Dayan P (1992) Q-learning. Mach Learn 8(3/4): 279–292
West R, Stewart T, Lebiere C, Chandrasekharan S (2005) Stochastic resonance in human cognition: ACT-R versus game theory, associative neural networks, recursive neural networks, Q-learning, and humans. In: 27th annual meeting of the cognitive science society
Wooldridge M (1996) A logic for BDI planning agents. In: Working notes, 3rd model age workshop: formal models of agents
Wray R, Chong R, Phillips J, Rogers S, Walsh B (1994) A survey of cognitive and agent architectures. Retrieved 28 Jan 2007 from http://ai.eecs.umich.edu/cogarch0/
Xiao D, Tan A-H (2007) Self-organizing neural architectures and cooperative learning in multi-agent environment. IEEE Trans Syst Man Cybern B 37(6): 1567–1580
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Chong, HQ., Tan, AH. & Ng, GW. Integrated cognitive architectures: a survey. Artif Intell Rev 28, 103–130 (2007). https://doi.org/10.1007/s10462-009-9094-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10462-009-9094-9