发表机构
Institute of Cognitive Sciences and Technologies, National Research Council; Center for Mind and Brain Science (CIMeC), University of Trento; University of Montreal（国家研究委员会认知科学与技术研究所; 特伦托大学心智与脑科学中心（CIMeC）; 蒙特利尔大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究探讨生物有机体中基础世界模型，通过五个神经回路例子揭示当前具身人工智能缺失的特征，如内在动力学作用等，还讨论了生物系统原则对未来具身人工智能的影响。
AI 中文摘要
生成式和具身人工智能的最新进展由对多模态数据的大规模预测学习驱动，但现有系统多基于被动训练模式。相反，神经科学和认知科学表明生物智能以相反方式组织，通过与环境交互获得的基础世界模型为语言提供语义框架。本文阐述了支持基础世界建模的神经回路的五个例子，强调了当前具身人工智能中缺失的几个特征，最后讨论了从生物系统得出的原则能否以及如何为未来具身人工智能提供信息。
英文摘要
Recent advances in generative and embodied AI have been driven by large-scale predictive learning over multimodal data. However, the resulting systems remain largely based on passive training regimes where linguistic regularities create the scaffold onto which information from other modalities is attached. Conversely, neuroscience and cognitive science suggest that biological intelligence is organized in the opposite way, where grounded world models acquired through interaction with the environment provide the semantic scaffold to which language is attached. Here, we illustrate five examples of neural circuits supporting grounded world modelling, which underlie navigation in physical and conceptual spaces, affordance-based perception and interaction with objects, active perception and exploratory learning, allostatic control and emotion, and the distinction between self- and world-generated outcomes. These examples highlight several features largely missing from current embodied AI, including the role of intrinsic dynamics as a foundation for learning, the centrality of action in aligning these dynamics with the external world, the prominence of autonomous experience and open-ended learning over passive assimilation of externally provided data, and the fact that early predictive and control mechanisms scaffold higher cognitive abilities such as reasoning, conceptual navigation, planning, imagination, understanding others' minds, and communication. Finally, we discuss whether and how principles derived from biological systems may inform future embodied AI, including training regimes based on social interaction to construct world models that are not only grounded but also socially shared and aligned with human norms and values.
