世界动作模型：具身AI的下一个前沿
World Action Models: The Next Frontier in Embodied AI
AI总结：
本文探讨了具身AI中的世界动作模型（WAMs），通过整合环境动态预测模型，统一预测状态建模与动作生成，提出结构化分类体系并分析数据生态，为该领域提供系统性综述。
摘要：
视觉-语言-动作（VLA）模型在具身策略学习中实现了强大的语义泛化，但其学习的是反应式观察到动作的映射，而未显式建模物理世界在干预下的演变。越来越多的研究通过将环境动态预测模型整合到动作生成流程中来解决这一限制。我们称这种新兴范式为世界动作模型（WAMs）：具身基础模型，统一预测状态建模与动作生成，目标是联合分布未来状态和动作，而非仅动作。然而，文献在架构、学习目标和应用场景上仍碎片化，缺乏统一的概念框架。我们正式定义WAMs并澄清其与相关概念的区别，追溯VLA和环境模型研究的基础和早期整合，导致这一范式的出现。我们对现有方法进行结构化分类，分为级联型和联合型WAMs，并进一步按生成模式、条件机制和动作解码策略细分。我们系统分析推动WAMs发展的数据生态系统，涵盖机器人远程操作、便携式人类演示、模拟和互联网级第一人称视频，并综合新兴的评估协议，围绕视觉保真度、物理常识和动作合理性组织。总体而言，本文提供了WAMs领域的首次系统性综述，澄清了关键架构范式及其权衡，并指出了该快速发展的领域中的开放挑战和未来机遇。
英文摘要：
Vision-Language-Action (VLA) models have achieved strong semantic generalization for embodied policy learning, yet they learn reactive observation-to-action mappings without explicitly modeling how the physical world evolves under intervention. A growing body of work addresses this limitation by integrating world models, predictive models of environment dynamics, into the action generation pipeline. We term this emerging paradigm World Action Models (WAMs): embodied foundation models that unify predictive state modeling with action generation, targeting a joint distribution over future states and actions rather than actions alone. However, the literature remains fragmented across architectures, learning objectives, and application scenarios, lacking a unified conceptual framework. We formally define WAMs and disambiguate them from related concepts, and trace the foundations and early integration of VLA and world model research that gave rise to this paradigm. We organize existing methods into a structured taxonomy of Cascaded and Joint WAMs, with further subdivision by generation modality, conditioning mechanism, and action decoding strategy. We systematically analyze the data ecosystem fueling WAMs development, spanning robot teleoperation, portable human demonstrations, simulation, and internet-scale egocentric video, and synthesize emerging evaluation protocols organized around visual fidelity, physical commonsense, and action plausibility. Overall, this survey provides the first systematic account of the WAMs landscape, clarifies key architectural paradigms and their trade-offs, and identifies open challenges and future opportunities for this rapidly evolving field.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
