An update on the MECA cognitive architecture  

MECA认知架构的更新

作　　者：BORELLI Jose Renato GUDWIN Ricardo Ribeiro BORELLI Jose Renato;GUDWIN Ricardo Ribeiro(坎皮纳斯大学,巴西圣保罗坎皮纳斯13083-970;圣保罗联邦研究所,巴西圣保罗奥托兰迪亚13183-000)

机构地区：[1]University of Campinas,Campinas 13083-970,Brazil [2]Federal Institute of São Paulo,Hortolândia 13183-000,Brazil

出　　处：《宁波大学学报(理工版)》2025年第2期29-48,共20页Journal of Ningbo University:Natural Science and Engineering Edition

基　　金：Supported by the Sao Paulo Research Foundation(FAPESP),CPE SMARTNESS(2021/00199-8)and CEPID/BRAINN(2013/07559-3).

摘　　要：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.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.

关 键 词：cognitive architecture dual-process theory dynamic subsumption cognitive systems toolkit 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]