具身智能机器人技术演进与未来展望

徐俊; 郭喆晨; 王凯龙; 杨天; 丁志壮; 梅雪松

doi:null

您当前的位置：

首页 >

文章列表页 >

具身智能机器人技术演进与未来展望

更新时间：2026-07-15

- 具身智能机器人技术演进与未来展望
- Research Progress on Embodied Intelligent Robots
- 西安交通大学学报 2026年
- 作者机构：
  
  1.西安交通大学机器人研究院西安 710049
  2.陕西省智能机器人重点实验室西安 710049
- 作者简介：
- 基金信息：
- DOI：
  中图分类号： TG156
- 收稿：2026-06-17，
  
  修回：2026-07-10，
  
  录用：2026-07-13，
- 稿件说明：
移动端阅览
徐俊, 郭喆晨, 王凯龙, 等. 具身智能机器人技术演进与未来展望[J/OL]. 西安交通大学学报, 2026.

XU Jun, GUO Zhechen, WANG Kailong, et al. Research Progress on Embodied Intelligent Robots[J/OL]. JOURNAL OF XI’AN JIAOTONG UNIVERSITY, 2026.
徐俊, 郭喆晨, 王凯龙, 等. 具身智能机器人技术演进与未来展望[J/OL]. 西安交通大学学报, 2026. DOI：

XU Jun, GUO Zhechen, WANG Kailong, et al. Research Progress on Embodied Intelligent Robots[J/OL]. JOURNAL OF XI’AN JIAOTONG UNIVERSITY, 2026. DOI：

摘要

具身智能机器人作为人工智能（AI）与机器人技术深度融合的前沿方向，已成为发展新质生产力和“人工智能+”行动的重要抓手，是实现通用智能的关键载体。本文系统梳理了机器人近代发展历程与人工智能符号主义、行为主义、连接主义三大学派技术演进脉络。归纳了国内外代表性学者对具身智能的定义与核心内涵，提出了涵盖数字孪生（Digital Twin）、现实世界（Reality）、互动（Engagement）、感知（Awareness）、执行（Motion）五大核心要素的具身智能机器人DREAM技术框架，并总结其物理载体依赖、孪生映射、自成长三大核心特征。深入剖析了当前具身智能的主流技术路线，包括一体化端到端模型路线、分层式模型路线、世界模型路线。分类阐述具身智能机器人的载体形式，涵盖了固定底座式、轮式、足式、飞行式及水下、空间、软体等特殊类型。总结了具身智能机器人的分级标准，结合当前具身智能机器人在工业制造、家庭服务、特种环境等应用场景以及面临的挑战，对具身智能机器人的未来发展趋势进行展望，为具身智能机器人研究提供参考。

Abstract

As a cutting-edge field representing the deep integration of artificial intelligence (AI) and robotics

embodied AI robots have become a key driver for developing new forms of productive capacity and advancing the ‘AI+’ initiative

and serve as a crucial vehicle for achieving general intelligence. This paper systematically reviews the modern history of robotics and traces the technological evolution of the three major schools of thought in artificial intelligence: symbolism

behaviorism and connectionism. It summarizes the definitions and core concepts of embodied AI proposed by leading scholars both domestically and internationally

and proposes the DREAM technical framework for embodied intelligent robots

which encompasses five core elements: Digital Twin

Reality

Engagement

Awareness

and Motion. It also summarizes its three core characteristics: physical carrier dependency

twin mapping

and self-growth. It provides an in-depth analysis of the current mainstream technical approaches in embodied AI

including the integrated end-to-end model approach

the hierarchical model approach

and the world model approach. It categorizes and describes the carrier forms of embodied AI robots

covering fixed-base

wheeled

legged

flying

and special types such as underwater

space-based

and soft robots. It summarizes the classification criteria for embodied AI robots. By examining their current applications in industrial manufacturing

domestic services and specialized environments

alongside the challenges they face

the paper outlines future development trends for embodied AI robots

thereby providing a reference for future research in this field.

关键词

Keywords

references

叶浩生 . 有关具身认知思潮的理论心理学思考 [D ] , 2011 .

王文晟 , 谭宁 , 黄凯 , et al . 基于大模型的具身智能系统综述 [J ] . 自动化学报 , 2025 , 51 ( 1 ): 1 - 19 .

陶永 , 万嘉昊 , 王田苗 , et al . 构建具身智能新范式: 人形机器人技术现状及发展趋势综述 [J ] . 机械工程学报 , 2025 , 61 ( 15 ): 121 - 147 .

陈铂垒 , 康嘉绪 , 钟萍 , et al . 面向具身人工智能的物体目标导航综述 [J ] . 软件学报 , 2024 , 36 ( 4 ): 1715 - 1757 .

袁依格 , 何卓丰 , 李威 , et al . 具身智能驱动的智能制造应用发展研究 [J ] . 中国工程科学 , 2025 , 27 ( 3 ): 67 .

高超 , 杨莹 , 陈世超 , et al . 多模态模型驱动的具身智能研究综述 [J ] . 智能感知工程 , 2025 , 2 ( 2 ): 1 - 12 .

Cordeschi R . AI turns fifty: revisiting its origins [J ] . Applied Artificial Intelligence , 2007 , 21 ( 4-5 ): 259 - 279 .

林艳 . 人工智能的符号主义纲领及其困境 [J ] . 求索 , 2019 , 6 : 186 - 193 .

Brooks R . A robust layered control system for a mobile robot [J ] . IEEE journal on robotics and automation , 2003 , 2 ( 1 ): 14 - 23 .

Sutton RS , Barto AG . Reinforcement learning: An introduction [M ] : MIT press Cambridge , 1998 .

Hopfield JJ . Neural networks and physical systems with emergent collective computational abilities [J ] . Proceedings of the national academy of sciences , 1982 , 79 ( 8 ): 2554 - 2558 .

Rumelhart DE , Hinton GE , Williams RJ . Learning representations by back-propagating errors [J ] . Nature , 1986 , 323 ( 6088 ): 533 - 536 .

Hinton GE , Salakhutdinov RR . Reducing the dimensionality of data with neural networks [J ] . Science , 2006 , 313 ( 5786 ): 504 - 507 .

Vaswani A , Shazeer N , Parmar N , et al . Attention is all you need [J ] . Advances in neural information processing systems , 2017 , 30 .

蔡恒进 . 行为主义, 联结主义和符号主义的贯通 [J ] . 上海师范大学学报 (哲学社会科学版) , 2020 , 49 ( 4 ): 87 - 96 .

赵冬斌 , 邵坤 , 朱圆恒 , et al . 深度强化学习综述: 兼论计算机围棋的发展 [J ] . 控制理论与应用 , 2016 , 33 ( 6 ): 701 - 717 .

叶浩生 . 具身认知的原理与应用 [M ] . 北京 : 商务印书馆 , 2017 .

郑南宁 , 杨勐 , 姜维周 , et al . 具身智能发展趋势与展望 [J ] . 中国工程科学 , 2026 , 28 ( 2 ): 1 .

Fei-Fei L , Krishna R . Searching for computer vision north stars [J ] . Daedalus , 2022 , 151 ( 2 ): 85 - 99 .

刘华平 , 郭迪 , 孙富春 , et al . 基于形态的具身智能研究: 历史回顾与前沿进展 [J ] . 自动化学报 , 2023 , 49 ( 6 ): 1131 - 1154 .

蒋树强 , 宋新航 , 张思贤 . 具身智能系统的 “大脑” 里都有什么? [J ] . 计算 , 2025 , 1 ( 4 ): 35 - 42 .

孙长银 . “试错” 驱动的具身智能学习及进化 [J ] . 计算 , 2025 , 1 ( 4 ): 43 - 48, 63 .

Ahn M , Brohan A , Brown N , et al . Do as i can, not as i say: Grounding language in robotic affordances [J ] . arXiv preprint arXiv: 220401691 , 2022 .

Zitkovich B , Yu T , Xu S , et al . Rt-2: Vision-language-action models transfer web knowledge to robotic control [C ] : PMLR , 2023 : 2165 - 2183 .

O’Neill A , Rehman A , Maddukuri A , et al . Open x-embodiment: Robotic learning datasets and rt-x models: Open x-embodiment collaboration 0 [C ] : IEEE , 2024 : 6892 - 6903 .

Bu Q , Cai J , Chen L , et al . Agibot world colosseo: A large-scale manipulation platform for scalable and intelligent embodied systems [J ] . arXiv preprint arXiv: 250306669 , 2025 .

Liang J , Huang W , Xia F , et al . Code as policies: Language model programs for embodied control [C ] : IEEE , 2023 : 9493 - 9500 .

Lorente A . Value Creation and Value Capture in AI: A Triple Helix Model [C ] , 2025 : 1637 - 1646 .

Belkhale S , Ding T , Xiao T , et al . Rt-h: Action hierarchies using language [J ] . arXiv preprint arXiv: 240301823 , 2024 .

Huang W , Xia F , Xiao T , et al . Inner monologue: Embodied reasoning through planning with language models [J ] . arXiv preprint arXiv: 220705608 , 2022 .

Ha D , Schmidhuber J . Recurrent world models facilitate policy evolution [J ] . Advances in neural information processing systems , 2018 , 31 .

Wu P , Escontrela A , Hafner D , et al . Daydreamer: World models for physical robot learning [C ] : PMLR , 2023 : 2226 - 2240 .

Assran M , Duval Q , Misra I , et al . Self-supervised learning from images with a joint-embedding predictive architecture [C ] , 2023 : 15619 - 15629 .

Bommasani R , Arora S , Chayes J , et al . Advancing science-and evidence-based AI policy [J ] . Science , 2025 , 389 ( 6759 ): 459 - 461 .

Yang J , Yang S , Gupta AW , et al . Thinking in space: How multimodal large language models see, remember, and recall spaces [C ] , 2025 : 10632 - 10643 .

兰沣卜 , 赵文博 , 朱凯 , et al . 基于具身智能的移动操作机器人系统发展研究 [J ] . 中国工程科学 , 2024 , 26 ( 1 ): 139 .

胡杰 , 张铁 . SCARA 机器人控制系统的设计与研究 [J ] . 机械设计与制造 , 2012 , ( 5 ): 162 - 164 .

朱磊磊 , 陈军 . 轮式移动机器人研究综述 [J ] . 机床与液压 , 2009 , ( 8 ): 242 - 247 .

陈致远 , 涂群章 , 张详坡 , et al . 足式爬行机器人研究进展与发展趋势 [J ] . Journal of Ordnance Equipment Engineering , 2020 , 41 ( 9 ): 1 - 12 .

Huang G-Y , Li W-F . Humanoid Robot Walking and Grasping Method Using Similarity Reward-Augmented Generative Adversarial Imitation Learning [J ] . Sensors , 2026 , 26 ( 9 ): 2756 .

刘伟龙 , 李彬 , 侯兰东 , et al . 基于深度强化学习的四足机器人研究综述 [J ] . 2022 .

Cao H , Shen J , Zhang Y , et al . Proximal cooperative aerial manipulation with vertically stacked drones [J ] . Nature , 2025 , 646 ( 8085 ): 576 - 583 .

Gupta H , Guo X , Ha H , et al . UMI-on-Air: Embodiment-Aware Guidance for Embodiment-Agnostic Visuomotor Policies [J ] . arXiv preprint arXiv: 251002614 , 2025 .

李硕 , 吴园涛 , 李琛 , et al . 水下机器人应用及展望 [J ] . 中国科学院院刊 , 2022 , 37 ( 7 ): 910 - 920 .

李硕 , 刘健 , 徐会希 , et al . 我国深海自主水下机器人的研究现状 [J ] . 中国科学: 信息科学 , 2018 , 48 ( 9 ): 1152 - 1164 .

张辉 , 左孝中 , 张伟 , et al . 空间双臂机器人漂浮基座扰动最小化轨迹规划 [J ] . Electronics Optics & Control , 2025 , 32 ( 2 ): 24 - 31 .

高胜 , 常玉连 , 张瑞杰 , et al . 基于自由漂浮空间机器人的空间焊缝跟踪 [J ] . 焊接学报 , 2008 , ( 11 ): 65 - 68 .

管清华 , 孙健 , 刘彦菊 , et al . 气动软体机器人发展现状与趋势 [J ] . 中国科学: 技术科学 , 2020 , 50 ( 7 ): 897 - 934 .

王国彪 , 陈殿生 , 陈科位 , et al . 仿生机器人研究现状与发展趋势 [J ] . 机械工程学报 , 2015 , 51 ( 13 ): 27 - 44 .

Kaminaga H , Otsuki S , Nakamura Y . Development of high-power and backdrivable linear electro-hydrostatic actuator [C ] : IEEE , 2014 : 973 - 978 .

Pratt JE , Krupp BT . Series elastic actuators for legged robots [C ] : SPIE , 2004 : 135 - 144 .

Wensing PM , Wang A , Seok S , et al . Proprioceptive actuator design in the mit cheetah: Impact mitigation and high-bandwidth physical interaction for dynamic legged robots [J ] . Ieee transactions on robotics , 2017 , 33 ( 3 ): 509 - 522 .

Guo K , Guo Y , Fang S , et al . Design and analysis of a permanent magnet frameless motor [J ] . IEEE Journal of Emerging and Selected Topics in Power Electronics , 2024 , 12 ( 3 ): 3124 - 3134 .

Hollander KW , Sugar TG . Design of lightweight lead screw actuators for wearable robotic applications [J ] . 2006 .

Townsend W . The BarrettHand grasper–programmably flexible part handling and assembly [J ] . Industrial Robot: an international journal , 2000 , 27 ( 3 ): 181 - 188 .

Grebenstein M , Chalon M , Friedl W , et al . The hand of the DLR hand arm system: Designed for interaction [J ] . The International Journal of Robotics Research , 2012 , 31 ( 13 ): 1531 - 1555 .

Xue H , Ren J , Chen W , et al . Reactive diffusion policy: Slow-fast visual-tactile policy learning for contact-rich manipulation [J ] . arXiv preprint arXiv: 250302881 , 2025 .

Mao Z , Xie Z , Fang K , et al . In-plant autonomous mobile robot scheduling and routing problem considering battery consumption model [J ] . Transportation Research Part C: Emerging Technologies , 2026 , 183 : 105488 .

Wisth D , Camurri M , Fallon M . Vilens: Visual, inertial, lidar, and leg odometry for all-terrain legged robots [J ] . Ieee transactions on robotics , 2022 , 39 ( 1 ): 309 - 326 .

Cheng N , Xu J , Guan C , et al . Touch100k: A large-scale touch-language-vision dataset for touch-centric multimodal representation [J ] . Information Fusion , 2025 , 124 : 103305 .

Karaman S , Frazzoli E . Sampling-based algorithms for optimal motion planning [J ] . The International Journal of Robotics Research , 2011 , 30 ( 7 ): 846 - 894 .

Chi C , Feng S , Xu Z , et al . Visuomotor policy learning via action diffusion . Google Patents , 2025 .

Kwon T , Di Palo N , Johns E . Language models as zero-shot trajectory generators [J ] . IEEE Robotics and Automation Letters , 2024 , 9 ( 7 ): 6728 - 6735 .

Beer JM , Fisk AD , Rogers WA . Toward a framework for levels of robot autonomy in human-robot interaction [J ] . Journal of human-robot interaction , 2014 , 3 ( 2 ): 74 .

Erden MS , Tomiyama T . Human-intent detection and physically interactive control of a robot without force sensors [J ] . Ieee transactions on robotics , 2010 , 26 ( 2 ): 370 - 382 .

Long X , Zhao Q , Zhang K , et al . A survey: Learning embodied intelligence from physical simulators and world models [J ] . arXiv preprint arXiv: 250700917 , 2025 .

Wang Y , Sun A . Toward embodied agi: A review of embodied ai and the road ahead [J ] . arXiv preprint arXiv: 250514235 , 2025 .

王烽 , 毛思通 . 具身智能: 核心挑战, 关键技术演进与产业前景展望 [J ] . 自动化博览 , 2026 , 43 ( 1 ): 50 - 57 .

Xu J , Sun Q , Han Q-L , et al . When embodied AI meets Industry 5.0: Human-centered smart manufacturing [J ] . IEEE/CAA Journal of Automatica Sinica , 2025 , 12 ( 3 ): 485 - 501 .

Ren L , Dong J , Liu S , et al . Embodied intelligence toward future smart manufacturing in the era of AI foundation model [J ] . IEEE/ASME Transactions on Mechatronics , 2024 , 30 ( 4 ): 2632 - 2642 .

Fan H , Liu X , Fuh JYH , et al . Embodied intelligence in manufacturing: leveraging large language models for autonomous industrial robotics [J ] . Journal of Intelligent Manufacturing , 2025 , 36 ( 2 ): 1141 - 1157 .

Ren Y , Liu Y , Ji T , et al . AI Agents and Agentic AI–navigating a plethora of concepts for future manufacturing [J ] . Journal of Manufacturing Systems , 2025 , 83 : 126 - 133 .

Lee I . Service robots: a systematic literature review [J ] . Electronics , 2021 , 10 ( 21 ): 2658 .

Lisondra M , Benhabib B , Nejat G . Embodied ai with foundation models for mobile service robots: A systematic review [J ] . Robotics , 2026 , 15 ( 3 ): 55 .

孙长银 , 袁心 , 王远大 , et al . 具身智能自主无人系统技术 [J ] . 自动化学报 , 2025 , 51 ( 4 ): 762 - 777 .

东鹏欧 , 欣丁 , 晶茗杨 , et al . 基于立体环境智能检测的快速应急响应机器人设计 [J ] . 智能城市应用 , 2025 , 8 ( 3 ): 107 - 109 .

相辉玉 , 许创 , 张宝海 . 双臂救援机器人现状及发展综述 [J ] . Construction Machinery & Equipment , 2026 , 57 ( 4 ): 106 .

Guo S , He Y , Shi L , et al . Modal and fatigue analysis of critical components of an amphibious spherical robot [J ] . Microsystem Technologies , 2017 , 23 ( 6 ): 2233 - 2247 .

Bi Z , Meruva K . Modeling and prediction of fatigue life of robotic components in intelligent manufacturing [J ] . Journal of Intelligent Manufacturing , 2019 , 30 ( 7 ): 2575 - 2585 .

Ishiki A , Neeves K , Marr D . Thermally assisted microbot transport through high-viscosity media [J ] . Scientific Reports , 2025 .

Li G , Svogor I , Beltrame G . Long-term pattern formation and maintenance for battery-powered robots [J ] . Swarm Intelligence , 2019 , 13 ( 1 ): 21 - 57 .

Almohamade SS , Clark JA , Law J . Dataset for collaborative robotics [J ] . Data , 2026 , 11 ( 5 ).

Mei H , Peng L . On multi-robot data collection and offloading for space-aerial-surface computing [J ] . IEEE Wireless Communications , 2023 , 30 ( 2 ): 90 - 96 .

Jiang S-Q , Zhang S-X , Tao S-D , et al . Self model for embodied artificial intelligence [J ] . Journal of Computer Science and Technology , 2026 : 1 - 16 .

Li Q , Liang Y , Wang Z , et al . Cogact: A foundational vision-language-action model for synergizing cognition and action in robotic manipulation [J ] . arXiv preprint arXiv: 241119650 , 2024 .

Zhang Z , Chen R , Ye J , et al . Whale: Towards generalizable and scalable world models for embodied decision-making [J ] . arXiv preprint arXiv: 241105619 , 2024 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

非线性最优机器人手眼标定

一种运动分岔并联机构的结构约束与运动模式分析

结合精度补偿的机器人优化手眼标定方法

电子级超纯氮深冷空分流程节能优化研究

不同板叠材料热声热机能量转换过程数值模拟研究