arXiv 2510.167322026-06-29cs.CV

具身AI世界模型综述

A Comprehensive Survey on World Models for Embodied AI

College of Computer Science and the Academy for Advanced Interdisciplinary Studies, Nankai University（南开大学计算机科学学院与前沿交叉学科研究院）；School of Computer Science and Engineering, Tianjin University of Technology（天津理工大学计算机科学与工程学院）；School of Information and Communication Engineering, University of Electronic Science and Technology of China（电子科技大学信息与通信工程学院）；Institute for Infocomm Research (I2R), Agency for Science, Technology and Research (A*STAR)（新加坡科技研究局资讯通信研究院）；Information Systems Technology and Design (ISTD) Pillar, Singapore University of Technology and Design (SUTD)（新加坡科技设计大学信息系统科技与设计系）

Xinqing Li, Xin He, Le Zhang, Min Wu, Xiaoli Li, Yun Liu

备注：: https://github.com/Li-Zn-H/AwesomeWorldModels

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文系统综述了具身AI中的世界模型，提出了功能、时间建模和空间表示的三轴分类法，并总结了数据资源、评估指标及开放挑战。

摘要：

具身AI要求智能体能够感知、行动并预测行动如何改变未来世界状态。世界模型作为内部模拟器，捕捉环境动态，支持前向和反事实推演，以辅助感知、预测和决策。本综述提出了具身AI中世界模型的统一框架。具体而言，我们形式化了问题设置和学习目标，并提出了一个三轴分类法，包括：(1) 功能：决策耦合型与通用型；(2) 时间建模：序列模拟与推理型与全局差异预测型；(3) 空间表示：全局潜在向量、令牌特征序列、空间潜在网格和分解渲染表示。我们系统化了机器人、自动驾驶和通用视频设置中的数据资源和评估指标，涵盖像素预测质量、状态级理解和任务性能。此外，我们提供了最新模型的定量比较，并提炼了关键开放挑战，包括统一数据集的稀缺性、需要评估物理一致性而非像素保真度的评估指标、模型性能与实时控制所需计算效率之间的权衡，以及在减轻误差累积的同时实现长时域一致性的核心建模难题。最后，我们在 https://this https URL 维护了一个精选文献列表。

英文摘要：

Embodied AI requires agents that perceive, act, and anticipate how actions reshape future world states. World models serve as internal simulators that capture environment dynamics, enabling forward and counterfactual rollouts to support perception, prediction, and decision making. This survey presents a unified framework for world models in embodied AI. Specifically, we formalize the problem setting and learning objectives, and propose a three-axis taxonomy encompassing: (1) Functionality, Decision-Coupled vs. General-Purpose; (2) Temporal Modeling, Sequential Simulation and Inference vs. Global Difference Prediction; (3) Spatial Representation, Global Latent Vector, Token Feature Sequence, Spatial Latent Grid, and Decomposed Rendering Representation. We systematize data resources and metrics across robotics, autonomous driving, and general video settings, covering pixel prediction quality, state-level understanding, and task performance. Furthermore, we offer a quantitative comparison of state-of-the-art models and distill key open challenges, including the scarcity of unified datasets and the need for evaluation metrics that assess physical consistency over pixel fidelity, the trade-off between model performance and the computational efficiency required for real-time control, and the core modeling difficulty of achieving long-horizon temporal consistency while mitigating error accumulation. Finally, we maintain a curated bibliography at https://github.com/Li-Zn-H/AwesomeWorldModels.

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。