

浏览全部资源
扫码关注微信
1.山东大学 控制科学与工程学院,山东 济南 250062
2.浪潮软件集团有限公司,山东 济南 2500101
3.重庆大学 电气工程学院,重庆 400044
4.江苏第二师范学院,江苏 南京 211200
Received:12 August 2025,
Revised:2025-10-30,
Accepted:06 November 2025,
移动端阅览
GUO Shuaishuai, ZHU Jiabing, YE Jia, et al. A survey on model context protocol (MCP) for embodied intelligence and robotic internet of things:From semantic control to real-time security assurance[J/OL]. Chinese Journal on Internet of Things, 2026.
具身智能与机器人物联网的发展呈现自主化、协同化和多模态融合的趋势,大量异构具身智能体接入物联网系统,对网络架构的互操作性和安全性提出了更高要求,面对传统协议在语义表达与动态上下文适应性上的局限,本文引入并系统阐述了模型上下文协议(Model Context Protocol
MCP)作为统一“语义控制平面”的核心作用。我们提出并详细构建了“Context→QoS/Sec 编译器”这一创新框架,旨在将高层任务意图与环境上下文(包括优先级、时延抖动容忍度、安全敏感等级等)精确、可验证地映射至底层数据平面(如ROS2/DDS、OPC UA/TSN、5G/6G)的实时服务质量(QoS)参数与安全侧写。我们进一步聚焦当前研究面临的深层挑战,包括代价模型的可识别性、异构约束的同构化、系统可验证性与可解释性、以及工程演化中的稳定性与最优性权衡,并针对性地提出了未来可行的研究路线。
The development of embodied intelligence and the robotic Internet of Things (IoT) is characterized by increasing autonomy
collaboration
and multimodal fusion. The large-scale integration of heterogeneous embodied intelligent agents into IoT systems poses higher requirements for interoperability
and security in network architectures. In this context
the introduction of a unified Model Context Protocol (MCP) to standardize device capability descriptions and task interactions has become essential. This paper presents a comprehensive survey of MCP in the integration of embodied intelligence and robotic IoT. The core concepts of MCP and its roles in multimodal perception
communication
computation
and control collaboration are introduced. The challenges in standardization
scalability
and cross-domain adaptation are summarized
and future research directions are discussed. Studies indicate that MCP has the potential to significantly enhance resource utilization efficiency
task execution coordination
and system security in embodied intelligence and robotic IoT
providing a unified protocol foundation for next-generation intelligent IoT systems.
王柏村 , 陶飞 , 方续东 , 刘超 , 刘宇飞 等 . 智能制造——比较性综述与研究进展 [J ] . Engineering , 2021 ,( 6 ): 80 - 122 .
王文晟 , 谭宁 , 黄凯 , 张雨浓 等 . 基于大模型的具身智能系统综述 . 自动化学报 , 2025 , 51 ( 1 ): 1 - 19 .
Wang W S , Tan N , Huang K , Zhang Y N , et.al . Embodied intelligence systems based on large models: A survey . Acta Automatica Sinica , 2025 , 51 ( 1 ): 1 - 19 .
Ghobakhloo M. , Iranmanesh M. , Tseng M. L. , Grybauskas A. , Stefanini A. , & Amran A. ( 2023 ). Behind the definition of Industry 5.0: a systematic review of technologies, principles, components, and values [J ] . Journal of Industrial and Production Engineering , 40 ( 6 ), 432 - 447 .
郝肇铁 , 郭斌 , 赵凯星 , 吴磊 , 丁亚三 , 李哲涛 , 刘思聪 , 於志文 . 从规则驱动到群智涌现: 多机器人空地协同研究综述 . 自动化学报 , 2024 , 50 ( 10 ): 1877 - 1905 .
Hao Z T , Guo B , Zhao K X , Wu L , Ding Y S , Li Z T , Liu S C , Yu Z W . From rule-driven to collective intelligence emergence: A review of research on multi-robot air-ground collaboration . Acta Automatica Sinica , 2024 , 50 ( 10 ): 1877 - 1905 .
John A. Duncan , Farshid Alambeigi , Mitchell W. Pryor . A Survey of Multimodal Perception Methods for Human-Robot Interaction in Social Environments [J ] . ACM Transactions on Human-Robot Interaction , 2024 , 13 ( 4 ): 1 - 50 .
牛志升 . 面向6G网络的高可靠低延时通信计算与控制 [J ] . 中国科学(信息科学) , 2024 , 54 ( 5 ): 1267 - 1282 .
Niu Z S . uRLLC3: ultra-reliable and low-latency communication, computing, and control for 6G networks [J ] . Science in China (Information Sciences) , 2024 , 54 ( 5 ): 1267 - 1282 .
Krejčí J , Babiuch M , Suder J , Krys V , Bobovský Z . Internet of Robotic Things: Current Technologies, Challenges, Applications, and Future Research Topics . Sensors . 2025 , 25 ( 3 ): 765 .
S. Ullah , S. Khan , D. Vanecek and I. Ur Rehman , Machine Learning and Digital-Twins-Based Internet of Robotic Things for Remote Patient Monitoring [J ] . IEEE Access , 2025 , 13 : 57141 - 57165 .
Q. Li , Q. J. Ye , N. Zhang , W. Zhang and F. Hu , Digital-Twin-Enabled Industrial IoT : Vision, Framework, and Future Directions [J ] . IEEE Wireless Communications , Early Access.
孙长银 , 袁心 , 王远大 , 柳文章 . 具身智能自主无人系统技术 [J ] . 自动化学报 , 2025 , 51 ( 4 ): 762 − 777 .
Sun C Y , Yuan X , Wang Y D , Liu W Z . Embodied intelligence autonomous unmanned systems technology [J ] . Acta Automatica Sinica , 2025 , 51 ( 4 ): 762 − 777 .
Zongxi Liu , Hongyang Du . Model Context Protocol-based Internet of Experts For Wireless Environment-aware LLM Agents [J ] . ArXiv: 2505.01834 .
Xinyi Hou , Yanjie Zhao , Shenao Wang , Haoyu Wang . Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directions [J ] . arXiv preprint , arXiv: 2503.23278 .
Arash Ahmadi , Sarah Sharif , Yaser M. Banad . MCP Bridge: A Lightweight, LLM-Agnostic RESTful Proxy for Model Context Protocol Servers [J ] . arXiv preprint , arXiv: 2504.08999 .
Abul Ehtesham , Aditi Singh , Gaurav Kumar Gupta . A survey of agent interoperability protocols: Model Context Protocol (MCP), Agent Communication Protocol (ACP), Agent-to-Agent Protocol (A2A), and Agent Network Protocol (ANP) [J ] . arXiv preprint , arXiv: 2505.02279 .
Junfeng Jiao , Jihyung Park , Yiming Xu , Kristen Sussman , Lucy Atkinson . SafeMate: A Modular RAG-Based Agent for Context-Aware Emergency Guidance [J ] . arXiv preprint , arXiv: 2505.02306 .
刘阳 , 柏永杰 , 林倞 . 面向人机物高效融合与协作的具身智能技术体系 [J ] . 机器人 , 2025 : 1 - 22 .
Liu Y , Bo Y J , LIN L . Technological System for Embodied Intelligence Towards Efficient Integration and Coordination of Human, Robot, and Physical World [J ] . ROBOT , 2025 : 1 - 22 .
Z . Li et al. MIPD: A Multi-Sensory Interactive Perception Dataset for Embodied Intelligent Driving[J ] , IEEE Transactions on Intelligent Transportation Systems , 2025 , Early Access.
Mon-Williams R. , Li G. , Long R. et al . Embodied large language models enable robots to complete complex tasks in unpredictable environments [J ] . Nature Machine Intelligence, 2025 , 7 : 592 – 601 .
曾凯 , 王耀南 , 谭浩然 等 . AI大模型驱动的具身智能人形机器人技术与展望 [J ] . 中国科学:信息科学 , 2025 , 55 ( 05 ): 967 - 992 .
Zeng K , Wang Y N , Tan H R , et.al . Prospects and technology of embodied intelligent humanoid robots driven by AI large models [J ] . Science in China (Information Sciences) , 2025 , 55 ( 05 ): 967 - 992 .
K . C. Okafor et,al. HAC-19: A Co-Infection Model for Infectious Diseases Using IoT-Networked Robots [J ] , IEEE Internet of Things Journal , 2025 , 12 ( 16 ): 33545 - 3356 .
C . Chen et,al. A UAV Power Line Patrolling System With Edge Intelligence and Beidou SMS in Signal Loss Area [J ] . IEEE Internet of Things Journal , 2025 , 12 ( 15 ): 30020 - 30035 .
K. Ren , G. Wang , A. S. Morgan and K. Hang . Collision-Inclusive Manipulation Planning for Occluded Object Grasping via Compliant Robot Motions [J ] , IEEE Robotics and Automation Letters , 2025 , 10 ( 9 ): 9120 - 9127 .
Y. Kayataş and S . Kabadayı . An AI-Assisted Autonomous IoRT Agent for Smart Spaces[C ] . 2024 9th International Conference on Computer Science and Engineering (UBMK), Antalya, Turkiye , 2024 : 613 - 618 .
沈甜雨 , 陶子锐 , 王亚东 等 . 具身智能研究的关键问题:自主感知、行动与进化 [J ] . 自动化学报 , 2025 , 51 ( 01 ): 43 - 71 .
SHEN T Y , TAO Z R , WANG Y D , et.al . Key Problems of Embodied Intelligence Research: Autonomous Perception, Action, and Evolution [J ] . Acta Automatica Sinica , 2025 , 51 ( 01 ): 43 - 71 .
徐文渊 , 冀晓宇 , 闫琛 等 . 具身智能安全治理 [J ] . 中国科学院院刊 , 2025 , 40 ( 03 ): 429 - 439 .
Xu W Y , Ji X Y , Yan C , et al . Embodied artificial intelligence security and governance [J ] . Bulletin of Chinese Academy of Sciences , 2025 , 40 ( 3 ): 429 - 439 .
Y. Toyomoto , T. Oshima and T. Hatanaka . Robot Zoo Aqua: Aquatic Control Testbed of Multiple USVs on Robot Operating System 2 [C ] . 2024 SICE Festival with Annual Conference (SICE FES) , Kochi City, Japan , 2024 : 196 - 201 .
A. Singh , A. Shetty , A. Ehtesham , S. Kumar and T. T. Khoei . A Survey of Large Language Model-Based Generative AI for Text-toSQL: Benchmarks, Applications, Use Cases, and Challenges [J ] . 2025 IEEE 15th Annual Computing and Communication Workshop and Conference (CCWC) , Las Vegas, NV, USA , 2025 : 00015 - 00021 .
Model Context Protocol . https://modelcontextprotocol.io/introduction [OL ] , Accessed on April 11 , 2025 .
F. Sunavala, Introducing Model Context Protocol (MCP) in Azure AI Foundry: Create an MCP Server with Azure AI Agent Service [OL ] , https://devblogs.microsoft.com/foundry/integrating-azure-ai-agentsmcp/ , Accessed on April 11, 2025 .
Szeider S . MCP-solver: Integrating language models with constraint programming systems [J ] . 2024 , arXiv preprint, arXiv: 2501.00539 .
Cao X , Shi L , Wang X , Duan Y , Yang X , Zhang X . MCP: A Named Entity Recognition Method for Shearer Maintenance Based on Multi Level Clue-Guided Prompt Learning [J ] . Applied Sciences , 2025 , 15 ( 4 ).
M. Mueller, How to Use Model Context Protocol the Right Way [OL ] , https://boomi.com/blog/model-context-protocol-how-to-use/ , Accessed on April 14, 2025 .
M. Tanveer, Model Context Protocol (MCP): The Next Frontier in Information Security [OL ] , https://medium.com/@threatpointer/mode- l-context protocol-mcp-the-next-frontier-in-information-security-097 cfc18bf2c , Accessed on April 14, 2025 .
O. Santos, AI Model Context Protocol (MCP) and Security [OL ] , https://community.cisco.com/t5/security-blogs/ai-model-context-protocolmcp-and-security/ba-p/5274394 , Accessed on April 14, 2025 .
S. Nitesh Palamakula , Agent-to-Agent Protocol vs . Model Context Protocol (MCP) [OL ] , https://medium.com/@sainitesh/ agent-to-agent- protocolsvs-model-context-protocol-mcp-b46e31599647 , Accessed on April 15, 2025 .
S. Nitesh Palamakula , Agent-to-Agent Protocol vs . Model Context Protocol (MCP) [OL ] , https://medium.com/@sainitesh/agent-to-agent -protocolsvs-model-context-protocol-mcp-b46e31599647 , Accessed on April 15, 2025 .
S. Guo , J. Zhu , J. Ye , A. Zhang , and G. Min , Task-Oriented Communications for Agentic IoT : An LLM-Driven QoS/Security Policy Generation via Dynamic Model Context Protocol, accepted by IEEE WCSP 2025, Chongqing, China .
0
Views
17
下载量
0
CSCD
Publicity Resources
Related Articles
Related Author
Related Institution
京公网安备11010802024621