迈向世界模型的一步：机器人操作综述
A Step Toward World Models: A Survey on Robotic Manipulation
AI总结：
本文综述了机器人操作中具备世界模型核心能力的方法，分析其在感知、预测和控制中的作用，提炼世界模型的核心组件与功能，以推动可泛化实用世界模型的发展。
摘要：
自主智能体日益被期望在复杂、动态且不确定的环境中运行，执行操作、导航和决策等任务。实现这些能力要求智能体理解世界的内在机制和动力学，超越反应式控制或对观测状态的简单复制。这推动了世界模型作为内部表征的发展，这些表征编码环境状态、捕捉动力学，并支持预测、规划和推理。尽管关注度不断提高，世界模型的定义、范围、架构和基本能力仍然模糊不清。在本综述中，我们不局限于给出一个固定定义，也不将范围限定在明确标注为世界模型的方法上。相反，我们通过回顾机器人操作领域的方法，考察那些展现出世界模型核心能力的方法。我们分析它们在感知、预测和控制中的作用，识别关键挑战和解决方案，并提炼出一个完全实现的世界模型应具备的核心组件、能力和功能。基于这一分析，我们旨在推动进一步的发展，以实现面向机器人的可泛化且实用的世界模型。
英文摘要：
Autonomous agents are increasingly expected to operate in complex, dynamic, and uncertain environments, performing tasks such as manipulation, navigation, and decision-making. Achieving these capabilities requires agents to understand the underlying mechanisms and dynamics of the world, moving beyond reactive control or simple replication of observed states. This motivates the development of world models as internal representations that encode environmental states, capture dynamics, and support prediction, planning, and reasoning. Despite growing interest, the definition, scope, architectures, and essential capabilities of world models remain ambiguous. In this survey, we go beyond prescribing a fixed definition and limiting our scope to methods explicitly labeled as world models. Instead, we examine approaches that exhibit the core capabilities of world models through a review of methods in robotic manipulation. We analyze their roles across perception, prediction, and control, identify key challenges and solutions, and distill the core components, capabilities, and functions that a fully realized world model should possess. Building on this analysis, we aim to motivate further development toward generalizable and practical world models for robotics.
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。
