生物有机体中的具身世界模型及未来具身人工智能

摘要

近年来，生成式人工智能与具身人工智能的进展主要得益于基于多模态数据的大规模预测性学习。然而，由此产生的系统仍然在很大程度上依赖于被动训练范式——即通过语言规律构建框架，再将其他模态的信息附着其上。与之相反，神经科学与认知科学研究表明，生物智能的组织方式恰好相反：通过与环境的互动获得的具身世界模型构成了语义支架，语言则依附于这一支架之上。在此，我们阐述支持具身世界建模的五种神经回路实例，这些回路分别支撑物理空间与概念空间的导航、基于可供性的感知与物体交互、主动感知与探索式学习、动态平衡调控与情绪，以及区分自我生成结果与外部世界生成结果的能力。这些实例凸显了当前具身人工智能系统中普遍缺失的若干特征，包括：内在动力学作为学习基础的核心作用、行动在使这些动力学与外部世界对齐中的中心地位、自主经验与开放式学习相对于被动吸收外部数据的突出性，以及早期预测与调控机制为更高阶认知能力（如推理、概念导航、规划、想象、理解他人心智及沟通）提供支架的事实。最后，我们探讨源自生物系统的原理是否以及如何为未来具身人工智能提供启示，包括基于社会互动的训练范式——构建不仅具身化、且在社会层面共享、并与人类规范及价值观对齐的世界模型。

English

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.

生物有机体中的具身世界模型及未来具身人工智能

Grounded world models in biological organisms and future embodied AI

摘要

Support