MECA认知架构的更新
PDF下载 (169)BORELLI José Renato,GUDWIN Ricardo Ribeiro.MECA认知架构的更新[J].宁波大学学报(理工版),2025,38(2):29-48.DOI:10.20098/j.cnki.1001-5132.2025.0105
BORELLI José Renato,GUDWIN Ricardo Ribeiro.An update on the MECA cognitive architecture[J].Journal of Ningbo University(Natural Science & Engineering Edition),2025,38(2):29-48.DOI:10.20098/j.cnki.1001-5132.2025.0105
| Title: | An update on the MECA cognitive architecture |
| 作者: | BORELLI José Renato, GUDWIN Ricardo Ribeiro |
| Author(s): | BORELLI José Renato, GUDWIN Ricardo Ribeiro |
| 关键词: | 认知架构; 双过程理论; 动态包容; 认知系统工具包 |
| Keywords: | cognitive architecture; dual-process theory; dynamic subsumption; cognitive systems toolkit |
| 分类号: | TP18 |
| DOI: | 10.20098/j.cnki.1001-5132.2025.0105 |
| 文献标识码: | A |
| 摘要: | 多用途增强认知架构(MECA)是一个旨在对“类人过程”这一跨领域复杂过程进行建模的认知框架. MECA最初专注于实施双过程理论方法, 以及集成基于全局工作空间理论的机器意识机制, 现已更新为集成双层包容机制, 支持反应和审议行为、动态目标设定和视觉空间记忆子系统, 增强了其对现实世界的交互性和自适应行为能力. 此外, 随着对计算思想的知识表达新方案的引入, MECA提出对知识进行动态组织, 以处理情景敏感推理和灵活分类. MECA的实施依赖于认知系统工具包(CST), 该工具包使其可与尖端技术实现集成. MECA和CST正在不断被开发和更新、协调和开放, 以纳入最新的AI器件和方法. 这一举措确保了有组织、可监视、可审计和可控制的人工智能解决方案的产生, 大大减少了对“黑匣子”认知过程的依赖, 同时提高了受人工智能驱动的系统的透明度和可解释性. 这些更新增强了MECA作为一种稳固架构的潜力, 使其可用于开发能够进行现实世界交互和自适应学习, 具有自主性、可适应性、情境感知的人工智能系统. |
| Abstract: | The Multipurpose Enhanced Cognitive Architecture (MECA) is a cognitive framework designed to model complex, human-like processes across multiple domains. Originally focusing on implementing a Dual Process Theory approach and integrating a machine consciousness mechanism based on Global Workspace Theory, MECA has been updated to integrate a dual-layer subsumption mechanism, enabling both reactive and deliberative behaviors, dynamic goal setting and a visual-spatial memory subsystem, enhancing MECA’s capacity for real-world interaction and adaptive behavior. Also, with the introduction of the new computational ideas’ knowledge representation scheme, MECA proposes to organize knowledge dynamically to handle context-sensitive reasoning and flexible categorization. MECA’s implementation relies on the Cognitive Systems Toolkit (CST), facilitating its integration with cutting-edge technologies. MECA and CST are being continuously developed and updated, aligned, and open to incorporate the latest AI artifacts and methodologies. This approach ensures the delivery of organized, monitorable, auditable, and controllable AI solutions, significantly reducing reliance on “black box” cognitive processes while enhancing transparency and accountability in AI-driven systems. These updates reinforce MECA’s potential as a robust architecture for developing autonomous, adaptable, and context-aware AI systems capable of real-world interaction and adaptive learning. |
| 参考文献 /References: | [1] LANGLEY P, LAIRD J E, ROGERS S. Cognitive architectures: research issues and challenges[J]. Cognitive Systems Research, 2009, 10(2):141-160. [2] PARAENSE A L O, RAIZER K, DE PAULA S M, et al. The cognitive systems toolkit and the CST reference cognitive architecture[J]. Biologically Inspired Cognitive Architectures, 2016, 17:32-48. [3] KOTSERUBA I, TSOTSOS J K. A review of 40 years of cognitive architecture research: core cognitive abilities and practical applications[EB/OL]. [2024-11-12]. https:// arxiv.org/abs/1610.08602. [4] SAMSONOVICH A V. Toward a unified catalog of implemented cognitive architectures[C]//Proceedings of the First Annual Meeting of the BICA Society. Amsterdam, Netherlands: IOS Press, 2010:195-244. [5] GOERTZEL B, PENNACHIN C, GEISWEILLER N. Brief survey of cognitive architectures[C]//Engineering General Intelligence, Part 1. Paris, Fance: Atlantis Press, 2014:101-142. [6] LUCENTINI D F, GUDWIN R R. A comparison among cognitive architectures: a theoretical analysis[J]. Procedia Computer Science, 2015, 71:56-61. [7] GUDWIN R, PARAENSE A, DE PAULA S M, et al. The multipurpose enhanced cognitive architecture (MECA)[J]. Biologically Inspired Cognitive Architectures, 2017, 22: 20-34. [8] LAIRD J. The soar cognitive architecture[M]. Cambridge, USA: MIT Press, 2012. [9] SUN R. A tutorial on clarion 5.0[EB/OL]. [2024-11-16]. http://www.cogsci.rpi.edu/public_html/rsun/sun.tutorial.pdf. [10] FRANKLIN S, MADL T, D’MELLO S, et al. LIDA: a systems-level architecture for cognition, emotion, and learning[J]. IEEE Transactions on Autonomous Mental Development, 2013, 6(1):19-41. [11] BAARS B J. A cognitive theory of consciousness[M]. Cambridge, England: Cambridge University Press, 1988. [12] BROOKS R. A robust layered control system for a mobile robot[J]. IEEE Journal on Robotics and Automation, 1986, 2(1):14-23. [13] NAKASHIMA H, NODA I, NAKASHIMA H, et al. Dynamic subsumption architecture for programming intelligent agents[C]//Proceedings of the 3rd International Conference on Multi Agent Systems. Paris, France, 1998: 190-197. [14] HAMADI Y, JABBOUR S, SAÏS L. Learning for dynamic subsumption[C]//2009 21st IEEE International Conference on Tools with Artificial Intelligence. Newark, USA, 2009:328-335. [15] HECKEL F W P, YOUNGBLOOD G M, HECKEL F W P, et al. Multi-agent coordination using dynamic behavior- based subsumption[C]//Proceedings of the Sixth AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment. California, USA, 2010:132-137. [16] GEORGE D, HAWKINS J. Towards a mathematical theory of cortical micro-circuits[J]. PLoS Computational Biology, 2009, 5(10):e1000532. [17] JILK D J, LEBIERE C, O’REILLY R C, et al. SAL: an explicitly pluralistic cognitive architecture[J]. Journal of Experimental & Theoretical Artificial Intelligence, 2008, 20(3):197-218. [18] CAMARGO E, SAKABE E Y, GUDWIN R. Existence, hypotheses and categories in knowledge representation[J]. Procedia Computer Science, 2022, 213:496-503. [19] BARSALOU L W. Grounded cognition: past, present, and future[J]. Topics in Cognitive Science, 2010, 2(4): 716-724. [20] GÄRDENFORS P. Geometry of meaning: semantics based on conceptual spaces[M]. Cambridge, USA: MIT Press, 2014. [21] OSMAN M. An evaluation of dual-process theories of reasoning[J]. Psychonomic Bulletin & Review, 2004, 11(6):988-1010. [22] ST B T EVANS J. In two minds: dual-process accounts of reasoning[J]. Trends in Cognitive Sciences, 2003, 7(10): 454-459. [23] ST B T EVANS J. Dual-processing accounts of reasoning, judgment, and social cognition[J]. Annual Review of Psychology, 2008, 59:255-278. [24] ST B T EVANS J, STANOVICH K E. Dual-process theories of higher cognition: advancing the debate[J]. Perspectives on Psychological Science, 2013, 8(3):223- 241. [25] FRANKISH K. Dual-process and dual-system theories of reasoning[J]. Philosophy Compass, 2010, 5(10):914-926. [26] KAHNEMAN D. Thinking, fast and slow[M]. New York, USA: Macmillan, 2011. [27] SLOMAN S A. The empirical case for two systems of reasoning[J]. Psychological Bulletin, 1996, 119(1):3-22. [28] STANOVICH K E, WEST R F. Individual differences in reasoning: implications for the rationality debate?[J]. The Behavioral and Brain Sciences, 2000, 23(5):645-665, 665-726. [29] ARKIN R C. Behavior-based robotics[M]. Cambridge, USA: MIT Press, 1998. [30] BARSALOU L W. Perceptual symbol systems[J]. Behavioral and Brain Sciences, 1999, 22(4):577-660. [31] BARSALOU L W. Grounded cognition[J]. Annual Review of Psychology, 2008, 59:617-645. [32] NARAYANAN S. Moving right along: a computational model of metaphoric reasoning about events[EB/OL]. [2024-11-29]. https://cdn.aaai.org/AAAI/1999/AAAI99-018. Pdf. [33] BERGEN B, CHANG N, NARAYAN S. Simulated action in an embodied construction grammar[C]// Proceedings of the Twenty Sixth Annual Conference of the Cognitive Science Society, 2004:108-113. [34] ROY D. Semiotic schemas: a framework for grounding language in action and perception[J]. Artificial Intelligence, 2005, 167(1/2):170-205. [35] CANGELOSI A, RIGA T. An embodied model for sensorimotor grounding and grounding transfer: experiments with epigenetic robots[J]. Cognitive Science, 2006, 30(4): 673-689. [36] DOMINEY P F, HOEN M, INUI T. A neurolinguistic model of grammatical construction processing[J]. Journal of Cognitive Neuroscience, 2006, 18(12):2088-2107. [37] MADDEN C, HOEN M, DOMINEY P F. A cognitive neuroscience perspective on embodied language for human-robot cooperation[J]. Brain and Language, 2010, 112(3):180-188. [38] LALLEE S, MADDEN C, HOEN M, et al. Linking language with embodied and teleological representations of action for humanoid cognition[J]. Frontiers in Neurorobotics, 2010, 4:8. [39] FRANK S L, VIGLIOCCO G. Sentence comprehension as mental simulation: an information-theoretic perspective [J]. Information, 2011, 2(4):672-696. [40] PEZZULO G, CALVI G. Computational explorations of perceptual symbol systems theory[J]. New Ideas in Psychology, 2011, 29:275-297. [41] GÄRDENFORS P. Conceptual spaces: the geometry of thought[M]. Cambridge, USA: MIT Press, 2004. [42] HOFSTADTER D, MITCHELL M. The copycat project: a model of mental fluidity and analogy-making[M]. New York, USA: BasicBooks, 1994:205-268. [43] FRANKLIN S, KELEMEN A, MCCAULEY L. IDA: a cognitive agent architecture[C]//SMC’98 Conference Proceedings 1998 IEEE International Conference on Systems, Man, and Cybernetics. San Diego, USA, 2002: 2646-2651. [44] BAARS B J, FRANKLIN S. An architectural model of conscious and unconscious brain functions: global workspace theory and IDA[J]. Neural Networks, 2007, 20(9):955-961. [45] GUDWIN R, PARAENSE A, DE PAULA S M, et al. An urban traffic controller using the MECA cognitive architecture[J]. Biologically Inspired Cognitive Architectures, 2018, 26:41-54. [46] GUDWIN R, ROHMER E, PARAENSE A, et al. The TROCA Project: an autonomous transportation robot controlled by a cognitive architecture[J]. Cognitive Systems Research, 2020, 59:179-197. [47] BADDELEY A. Human memory: theory and practice[M]. Hove, USA: Psychology Press, 1997. [48] MASLOW A H. A theory of human motivation[J]. Psychological Review, 1943, 50(4):370-396. [49] SUN R. Motivational representations within a com- putational cognitive architecture[J]. Cognitive Computation, 2009, 1(1):91-103. [50] SUN R, WILSON N. Motivational processes within the perception: action cycle[M]. New York: Springer, 2010: 449-472. [51] MCCALL R. Fundamental motivation and perception for a systems-level cognitive architecture[EB/OL]. [2024-12- 01]. https://digitalcommons.memphis.edu/cgi/viewcontent. cgi?article=2098&context=etd. [52] GUDWIN R, ROHMER E, PARAENSE A, et al. A double-layer subsumption mechanism for enforcing sequential behaviors in a cognitive architecture[C]//2021 IEEE Symposium Series on Computational Intelligence. Orlando, USA, 2021:1-7. [53] BADDELEY A. The episodic buffer: a new component of working memory?[J]. Trends in Cognitive Sciences, 2000, 4(11):417-423. [54] BADDELEY A D. Is working memory still working?[J]. American Psychologist, 2001, 56(11):851-864. [55] TULVING E. Concepts of human memory[EB/OL]. [2024-12-06]. https://alicekim.ca/concepts91.pdf. [56] TULVING E. Episodic memory: from mind to brain[J]. Annual Review of Psychology, 2002, 53:1-25. [57] HOWARD M W, FOTEDAR M S, DATEY A V, et al. The temporal context model in spatial navigation and relational learning: toward a common explanation of medial temporal lobe function across domains[J]. Psychological Review, 2005, 112(1):75-116. [58] CABEZA R, CIARAMELLI E, OLSON I R, et al. The parietal cortex and episodic memory: an attentional account[J]. Nature Reviews Neuroscience, 2008, 9(8): 613-625. [59] CUVELIER T, DIDIER F, FURNON V, et al. OR-tools’ vehicle routing solver: a generic constraint-programming solver with heuristic search for routing problems[EB/OL]. [2024-11-26]. https://hal.science/hal-04015496v1/document. [60] MIKOLOV T, CHEN K, CORRADO G, et al. Efficient estimation of word representations in vector space [EB/OL]. [2024-11-26]. https://arxiv.org/pdf/1301.3781. [61] GABSI I, KAMMOUN H, MTAR R, et al. Word2Vec- GloVe-BERT embeddings for query expansion[C]// Intelligent Systems Design and Applications. Switzerland: Springer Nature, 2024:167-177. |
| 备注/Memo: | Received date: 2025−01−05 JOURNAL OF NINGBO UNIVERSITY ( NSEE ): http://journallg.nbu.edu.cn/ Foundation item: Supported by the São Paulo Research Foundation (FAPESP), CPE SMARTNESS（2021/00199-8）and CEPID/BRAINN （2013/07559-3）. Biography: BORELLI José Renato, PhD student/professor, specializing in: cognitive architectures, cognitive systems, intelligent systems, artificial minds, robotics, etc. Email: jrborelli@ifsp.edu.br *Corresponding author: GUDWIN Ricardo Ribeiro, associate professor, specializing in: cognitive architectures, cognitive systems, computational semiotics, intelligent systems and artificial minds. Email: gudwin@unicamp.br 宁波大学学报（理工版）网址：http://journallg.nbu.edu.cn/ |
