A Comprehensive Survey on World Models for Embodied AI

作者
Xinqing Li,Xin He,Le Zhang,Yun Liu
出处
期刊:Cornell University - arXiv [Cornell University]
标识
DOI:10.48550/arxiv.2510.16732
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.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
刚刚
sagitar应助金荣采纳,获得50
刚刚
Zn中毒发布了新的文献求助10
刚刚
刚刚
zhang完成签到,获得积分10
1秒前
科研通AI6.2应助Ade采纳,获得10
1秒前
白华苍松发布了新的文献求助10
2秒前
slim完成签到,获得积分20
2秒前
句号完成签到 ,获得积分10
2秒前
王誓言完成签到,获得积分10
3秒前
Zephyrite应助炒饭采纳,获得10
3秒前
绿蚁新醅酒呀完成签到,获得积分10
4秒前
大模型应助neverlost6采纳,获得10
4秒前
4秒前
fly0516关注了科研通微信公众号
4秒前
xie完成签到,获得积分10
5秒前
豆沙包发布了新的文献求助10
5秒前
liekkas完成签到,获得积分10
5秒前
友好的草莓完成签到,获得积分10
5秒前
vicent完成签到 ,获得积分10
6秒前
6秒前
诚心晓露完成签到,获得积分10
6秒前
优秀笑寒完成签到,获得积分10
6秒前
6秒前
李健的小迷弟应助zyq采纳,获得10
6秒前
功能界面完成签到,获得积分20
6秒前
毛豆应助jcc采纳,获得10
7秒前
7秒前
毛豆应助jcc采纳,获得10
7秒前
科研通AI6.2应助江小霜采纳,获得10
7秒前
苏桑焉完成签到 ,获得积分10
7秒前
毛豆应助jcc采纳,获得10
7秒前
毛豆应助jcc采纳,获得10
7秒前
jeauean完成签到,获得积分10
7秒前
毛豆应助jcc采纳,获得10
7秒前
毛豆应助jcc采纳,获得10
7秒前
毛豆应助jcc采纳,获得10
7秒前
毛豆应助jcc采纳,获得10
8秒前
毛豆应助jcc采纳,获得10
8秒前
CipherSage应助Sichen孟采纳,获得10
8秒前
高分求助中
Principles of Economics, 11th Edition 10000
University Physics with Modern Physics, 16th edition 10000
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
Molecular Mechanisms of Photosynthesis, 4th Edition 1000
Organic Reactions, Volume 116 1000
Current concepts in cutaneous toxicity : proceedings of the Fourth Conference on Cutaneous Toxicity, Washington, D.C., May 9-11, 1979 1000
The recovery-stress questionnaires : user manual 800
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 工程类 有机化学 化学工程 生物化学 计算机科学 内科学 物理 复合材料 催化作用 细胞生物学 无机化学 光电子学 物理化学 电极 基因
热门帖子
关注 科研通微信公众号,转发送积分 7258043
求助须知:如何正确求助?哪些是违规求助? 8879902
关于积分的说明 18759865
捐赠科研通 6938388
什么是DOI,文献DOI怎么找? 3201209
关于科研通互助平台的介绍 2375272
邀请新用户注册赠送积分活动 2177039