生物有機體與未來具身人工智慧中的具身世界模型

摘要

生成式與具身化人工智慧的最新進展，主要來自於對多模態數據進行大規模預測學習所驅動。然而，由此產生的系統在很大程度上仍基於被動訓練模式，其中語言規律為其他模態資訊的附著提供了支架。相反地，神經科學與認知科學指出，生物智能的組織方式恰恰相反：透過與環境互動所獲得的、奠基於實際經驗的世界模型，為語言的附著提供了語義支架。本文在此闡述了五個支持奠基於實際經驗的世界模型建構的神經迴路實例，這些機制分別構成：在物理與概念空間中的導航、基於可供性的知覺及物體互動、主動知覺與探索性學習、異質穩定控制與情緒，以及區分自身與外界產生之結果的能力。這些實例凸顯了當前具身化人工智慧多所欠缺的幾項特徵，包括：內在動態特性作為學習基礎的作用、行動在使這些動態特性與外在世界同步中的核心地位、自主經驗與開放式學習相對於被動吸收外部提供數據的顯著性，以及早期預測與控制機制如何為推理、概念導航、計畫、想像、理解他人心智及溝通等高階認知能力提供支架。最後，我們探討源自生物系統的原則是否以及如何能為未來的具身化人工智慧提供啟發，其中包括基於社交互動的訓練模式，以建構不僅奠基於實際經驗，而且能在社會中共享、並與人類規範及價值觀保持一致的世界模型。

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.

生物有機體與未來具身人工智慧中的具身世界模型

Grounded world models in biological organisms and future embodied AI

摘要

Support