论文/arXiv 2606.00113·1 个月前

机器人操作的世界模型：综述

本文综述机器人操作世界模型，以动作条件预测系统为定义，梳理表示、行动连接和学习流程用途，并回顾38个操作数据集。

AI 整理

• 本体 SDK 与控制
• 数据与采集
• 具身模型

原文链接：World Models for Robotic Manipulation: A Survey（arXiv 2606.00113 · 发布日期：2026-08-31）

World Models for Robotic Manipulation: A Survey

本文综述机器人操作世界模型，以动作条件预测系统为定义，梳理表示、行动连接和学习流程用途，并回顾38个操作数据集。

核心要点

• 机器人操作需在执行前预判动作如何改变物体、接触和场景几何。
• 论文将世界模型定义为动作条件预测系统，并与感知、逆模型、策略、奖励和价值函数区分。
• 按五类未来表示和功能分类，区分集成预测-行动模型与显式预测规划器。
• 综述38个操作数据集和评估协议，并指出接触建模、幻觉控制、动作对齐等开放挑战。

英文摘要 (Abstract)

ABSTRACT Robotic manipulation depends on the ability to anticipate how actions reshape objects, contacts, and scene geometry before execution. Learned world models provide this capability by predicting task‐relevant future evolution under robot intervention, yet the term now spans latent dynamics models, action‐conditioned video generators, three‐ and four‐dimensional scene predictors, physics‐informed simulators, and predictive modules inside vision‐language‐action systems. This breadth has fragmented the literature and obscured the design choices that matter for manipulation. We survey world models for robotic manipulation through three questions: what future representation is predicted, how prediction is connected to action, and when prediction is used in the robot‐learning pipeline. We operationally define a world model as an action‐conditioned predictive system and distinguish it from perception modules, inverse models, policies, rewards, and value functions. We then organize existing work into five representation families, develop a functional taxonomy that separates integrated prediction–action models from explicit predictive planners, and characterize infrastructure roles including synthetic experience generation, candidate filtering, search‐based evaluation, learned environments, and outcome verification. We further map these roles across pretraining, post‐training, and inference adaptation, review 38 manipulation datasets, and synthesize evaluation protocols for predictive fidelity, task performance, and simulator reliability. This survey shows that world models are evolving from task‐specific dynamics predictors into predictive infrastructure for robot learning, while exposing open challenges in contact modeling, hallucination control, action alignment, and benchmarking under closed‐loop use.

作者：Fangyuan Wang, Ziyuan Wang, Guorui Pei, Mengshi Zhang, 梁燦錫, Jun Hu, Zhongxuan Li, Jinsong Wu, Ning Han, Zeqing Zhang

来源

本页事实对应的公开页面，以原文为准。

1. arXiv 2606.00113：World Models for Robotic Manipulation: A Survey访问 2026-10-21