大型语言模型赋能的无线智能感知技术、应用与趋势综述

颜雨; 刘江湖; 李晓帆

doi:10.11959/j.issn.1000-0801.2025029

您当前的位置：

首页 >

文章列表页 >

大型语言模型赋能的无线智能感知技术、应用与趋势综述

研究 | 更新时间：2025-09-29

- 大型语言模型赋能的无线智能感知技术、应用与趋势综述
- Review of Wireless Intelligent Sensing Technology, Applications and Trends Enabled by Large Language Models
- 天地一体化信息网络 2025年6卷第3期页码：59-73
- 作者机构：
  
  1.海军装备部，北京 100000
  2.暨南大学，广东珠海 519070
- 作者简介：
  
  [ "颜雨（1989-），男，海军装备部工程师，长期从事电子对抗研究工作。" ]
  [ "刘江湖（1997-），男，暨南大学硕士生，主要研究方向为脑机接口技术、无线感知与大模型等。" ]
  [ "李晓帆（1984-），女，暨南大学智能科学与工程学院副教授，主要研究方向为无线感知与大模型、无线信号智能检测与识别、电磁频谱侦测等。" ]
- 基金信息：
  
  国家自然科学基金资助项目(62271232)
- DOI：10.11959/j.issn.1000-0801.2025029
  中图分类号： TP393
- 收稿日期：2025-06-12，
  
  修回日期：2025-08-20，
  
  纸质出版日期：2025-09-20
- 稿件说明：
移动端阅览
颜雨,刘江湖,李晓帆.大型语言模型赋能的无线智能感知技术、应用与趋势综述[J].天地一体化信息网络,2025,06(03):59-73.

YAN Yu,LIU Jianghu,LI Xiaofan.Review of Wireless Intelligent Sensing Technology, Applications and Trends Enabled by Large Language Models[J].Space-Integrated-Ground Information Networks,2025,06(03):59-73.
颜雨,刘江湖,李晓帆.大型语言模型赋能的无线智能感知技术、应用与趋势综述[J].天地一体化信息网络,2025,06(03):59-73. DOI： 10.11959/j.issn.1000-0801.2025029.

YAN Yu,LIU Jianghu,LI Xiaofan.Review of Wireless Intelligent Sensing Technology, Applications and Trends Enabled by Large Language Models[J].Space-Integrated-Ground Information Networks,2025,06(03):59-73. DOI： 10.11959/j.issn.1000-0801.2025029.

摘要

大型语言模型正驱动无线智能感知发生深刻的范式转变：从信号处理迈向高层语义理解。针对该前沿领域，提出了系统性的分析框架，将技术演进归纳为两大主线：通过跨模态对齐实现信号的泛化语义识别以及通过参数高效微调解决模型在边缘设备的部署难题。此外，梳理了其在智能医疗、家居等场景的关键应用，剖析了数据稀缺、跨域泛化等核心挑战，并展望了该技术向多模态融合与主动智能环境演进的未来趋势，旨在为相关研究提供参考。

Abstract

Large language models (LLM) are catalyzing a profound paradigm shift in wireless intelligent sensing:elevating the field from signal processing to high-level semantic understanding. This review offers a systematic analysis framework for this emerging field

Its core contribution is to structure the field's technical evolution along two principal axes: achieving generalized semantic recognition of signals via cross-modal alignment

and resolving edge deployment challenges of models through parameter-efficient fine-tuning (PEFT). Within this framework

this paper examines key applications in scenarios such as smart healthcare and homes

analyzes core challenges like data scarcity and cross-domain generalization

and outlines future trends toward multi-modal fusion and proactive intelligent environments

aiming to provide valuable insights and a roadmap for related research.

关键词

Keywords

references

VASWANI A , SHAZEER N , PARMAR N , et al . Attention is all you need [C ] // Advances in Neural Information Processing Systems 30 (NIPS 2017) . Long Beach, CA, USA : Curran Associates Inc. , 2017 : 5998 - 6008 .

DEVLIN J , CHANG M W , LEE K , et al . Bert: Pre-training of deep bidirectional transformers for language understanding [C ] // Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies . Minneapolis, Minnesota, USA : Association for Computation Linguistics , 2019 : 4171 - 4186 .

RADFORD A , NARASIMHAN K , SALIMANS T , et al . Improving language understanding by generative pre-training [R ] . 2024 .

OUYANG L , WU J , JIANG X , et al . Training language models to follow instructions with human feedback [C ] // Advances in Neural Information Processing Systems 35 (NeurIPS 2022) . New Orleans, LA, USA : Curran Associates Inc. , 2022 : 27730 - 27744 .

BROWN T , MANN B , RYDER N , et al . Language models are few-shot learners [C ] // Advances in Neural Information Processing Systems 33 (NeurIPS 2020) . Vancouver, BC, Canada : Curran Associates Inc. , 2020 : 1877 - 1901 .

ACHIAM J , ADLER S , AGARWAL S , et al . Gpt-4 technical report [EB ] . 2023 .

LIU J , LIU H B , CHEN Y Y , et al . Wireless sensing for human activity: a survey [J ] . IEEE Communications Surveys & Tutorials , 2020 , 22 ( 3 ): 1629 - 1645 .

LI C N , CAO Z C , LIU Y H . Deep AI enabled ubiquitous wireless sensing [J ] . ACM Computing Surveys , 2022 , 54 ( 2 ): 1 - 35 .

MA Y S , ZHOU G , WANG S Q . WiFi sensing with channel state information: a survey [J ] . ACM Computing Surveys , 2019 , 52 ( 3 ): 1 - 36 .

WANG Z Q , MAO S W . AIGC for wireless sensing: diffusion-empowered human activity sensing [J ] . IEEE Transactions on Cognitive Communications and Networking , 2025 , 11 ( 2 ): 657 - 671 .

SHAO J W , TONG J W , WU Q , et al . WirelessLLM: empowering large language models towards wireless intelligence [J ] . Journal of Communications and Information Networks , 2024 , 9 ( 2 ): 99 - 112 .

ZHANG H , REN Y , YUAN H , et al . Wi-Chat: Large language model powered Wi-Fi sensing [EB ] . 2024 .

BAHL P , PADMANABHAN V N . RADAR: an in-building RF-based user location and tracking system [C ] // Proceedings of IEEE INFOCOM 2000 . Conference on Computer Communications. Nineteenth Annual Joint Conference of the IEEE Computer and Communications Societies . Piscataway : IEEE Press , 2000 : 775 - 784 .

SHEN J , WON J Y , CHEN Z , et al . Drift with devil: Security of multi-sensor fusion based localization in high-level autonomous driving under GPS spoofing [C ] // Proceedings of the 29th USENIX Conference on Security Symposium . Boston, MA, USA : USEINX Association , 2020 : 931 - 948 .

JIMÉNEZ RUIZ A R , SECO GRANJA F . Comparing ubisense, BeSpoon, and DecaWave UWB location systems: indoor performance analysis [J ] . IEEE Transactions on Instrumentation and Measurement , 2017 , 66 ( 8 ): 2106 - 2117 .

HALPERIN D , HU W J , SHETH A , et al . Tool release [J ] . ACM SIGCOMM Computer Communication Review , 2011 , 41 ( 1 ): 53 .

WANG W , LIU A X , SHAHZAD M , et al . Understanding and modeling of WiFi signal based human activity recognition [C ] // Proceedings of the 21st Annual International Conference on Mobile Computing and Networking . New York : ACM , 2015 : 65 - 76 .

XU H T , HAN L Y , YANG Q R , et al . Penetrative AI: making LLMs comprehend the physical world [C ] // Proceedings of the Findings of the Association for Computational Linguistics: ACL 2024 . Stroudsburg, PA, USA : ACL , 2024 : 7324 - 7341 .

ZHENG N Y , LI Y C , JIANG S Q , et al . AdaWiFi, collaborative WiFi sensing for cross-environment adaptation [J ] . IEEE Transactions on Mobile Computing , 2025 , 24 ( 2 ): 845 - 858 .

KORELIČ M , MACHIDON O M , PEJOVIĆ V . SELLMA: Semantic location through on-device LLMs and WiFi sensing [EB ] . 2024 .

JI S J , ZHENG X Z , WU C S . HARGPT: are LLMs zero-shot human activity recognizers [C ] // Proceedings of the 2024 IEEE International Workshop on Foundation Models for Cyber-Physical Systems & Internet of Things (FMSys) . Piscataway : IEEE Press , 2024 : 38 - 43 .

TOUVRON H , LAVRIL T , IZACARD G , et al . LLaMA: open and efficient foundation language models [EB ] . 2023 .

RADFORD A , KIM J W , HALLACY C , et al . Learning transferable visual models from natural language supervision [C ] // International Conference on Machine Learning . Virtual : PMLR , 2021 : 8748 - 8763 .

TEAM G , ANIL R , BORGEAUD S , et al . Gemini: a family of highly capable multimodal models [EB ] . 2023 .

ALAYRAC J B , DONAHUE J , LUC P , et al . Flamingo: A visual language model for few-shot learning [C ] // Advances in Neural Information Processing Systems 35 (NeurIPS 2022) . New Orleans, LA, USA : Curran Associates Inc. , 2022 : 23716 - 23736 .

LU J S , BATRA D , PARIKH D , et al . ViLBERT: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks [C ] // Proceedings of the Neural Information Processing Systems . Vancouver, BC, Canada : Curran Associates Inc. , 2019 : 13 - 23 .

LI Z , DELDARI S , CHEN L , et al . Sensorllm: Aligning large language models with motion sensors for human activity recognition [EB ] . 2023 .

CHEN H Y , LAI Z , ZHANG H , et al . Contrastive localized language-image pre-training [EB ] . 2023 .

LIU P F , YUAN W Z , FU J L , et al . Pre-train, prompt, and predict: a systematic survey of prompting methods in natural language processing [EB ] . 2021 .

HUA J Y , SUN H Y , SHEN Z Y , et al . Accurate and efficient wireless device fingerprinting using channel state information [C ] // Proceedings of the IEEE INFOCOM 2018 - IEEE Conference on Computer Communications . Piscataway : IEEE Press , 2018 : 1700 - 1708 .

QUY T D , LIN C Y , SHIH T K . Enhanced human activity recognition using Wi-Fi sensing: leveraging phase and amplitude with attention mechanisms [J ] . Sensors , 2025 , 25 ( 4 ): 1038 .

WANG X Y , GAO L J , MAO S W . PhaseFi: phase fingerprinting for indoor localization with a deep learning approach [C ] // Proceedings of the 2015 IEEE Global Communications Conference (GLOBECOM) . Piscataway : IEEE Press , 2015 : 1 - 6 .

XI Z H , CHEN W X , GUO X , et al . The rise and potential of large language model based agents: a survey [EB ] . 2023 .

TORUNER M D , SHI V , SOLLEE J , et al . Artificial intelligence-driven wireless sensing for health management [J ] . Bioengineering , 2025 , 12 ( 3 ): 244 .

FANG Y , LIU W , ZHANG S . Wi-senser: contactless head movement detection during sleep utilizing WiFi signals [J ] . Applied Sciences , 2023 , 13 ( 13 ): 7572 .

NANDAKUMAR R , GOLLAKOTA S , WATSON N . Contactless sleep apnea detection on smartphones [C ] // Proceedings of the 13th Annual International Conference on Mobile Systems, Applications, and Services . New York : ACM , 2015 : 45 - 57 .

ZHANG D H , HU Y , CHEN Y , et al . BreathTrack: tracking indoor human breath status via commodity WiFi [J ] . IEEE Internet of Things Journal , 2019 , 6 ( 2 ): 3899 - 3911 .

POLO-RODRÍGUEZ A , FIORINI L , ROVINI E , et al . Enhancing smart environments with context-aware chatbots using large language models [EB ] . 2024 .

YU K Y , LI Q , CHEN D , et al . PrivacyGuard: enhancing smart home user privacy [C ] // Proceedings of the 20th International Conference on Information Processing in Sensor Networks (co-located with CPS-IoT Week 2021) . New York : ACM , 2021 : 62 - 76 .

LI X , ZHANG Y , LIU Y . Enhancing BLE RSSI for accurate indoor positioning via deep learning [J ] . Sensors , 2024 , 24 ( 10 ): 3105 .

DU Y Y , DENG H Y , LIEW S C , et al . The power of large language models for wireless communication system development: a case study on FPGA platforms [EB ] . 2023 .

QIAO J G , YANG F , LIU J B , et al . Advancements in indoor precision positioning: a comprehensive survey of UWB and Wi-Fi RTT positioning technologies [J ] . Network , 2024 , 4 ( 4 ): 545 - 566 .

NEIRYNCK D , LUK E , MCLAUGHLIN M . An alternative double-sided two-way ranging method [C ] // Proceedings of the 2016 13th Workshop on Positioning, Navigation and Communications (WPNC) . Piscataway : IEEE Press , 2016 : 1 - 4 .

AHMED S , WANG D Y , PARK J , et al . UWB-gestures, a public dataset of dynamic hand gestures acquired using impulse radar sensors [J ] . Scientific Data , 2021 , 8 ( 1 ): 102 .

GUO C C , ZHANG Z X , YANG Z C , et al . Deep learning-based compressed sensing for image and UWB signal reconstruction [J ] . IEEE Sensors Journal , 2025 , 25 ( 12 ): 22228 - 22238 .

LIEN J , GILLIAN N , KARAGOZLER M E , et al . Soli: Ubiquitous gesture sensing with millimeter wave radar [J ] . ACM Transactions on Graphics , 2016 , 35 ( 4 ): 1 - 19 .

DENG J Q , SHI W , HU J , et al . Semi-supervised t-SNE for millimeter-wave wireless localization [C ] // Proceedings of the 2021 7th International Conference on Computer and Communications (ICCC) . Piscataway : IEEE Press , 2021 : 1015 - 1019 .

CAO Q M , XUE H F , LIU T C , et al . mmCLIP: boosting mmWave-based zero-shot HAR via signal-text alignment [C ] // Proceedings of the 22nd ACM Conference on Embedded Networked Sensor Systems . New York : ACM , 2024 : 184 - 197 .

SHARMA P , KAN E C . Sleep scoring with a UHF RFID tag by near field coherent sensing [C ] // Proceedings of the 2018 IEEE/MTT-S International Microwave Symposium - IMS . Piscataway : IEEE Press , 2018 : 1419 - 1422 .

MAURYA L , ZWIGGELAAR R , CHAWLA D , et al . Non-contact respiratory rate monitoring using thermal and visible imaging: a pilot study on neonates [J ] . Journal of Clinical Monitoring and Computing , 2023 , 37 ( 3 ): 815 - 828 .

NIU K , ZHANG F S , WANG X Z , et al . Understanding WiFi signal frequency features for position-independent gesture sensing [J ] . IEEE Transactions on Mobile Computing , 2022 , 21 ( 11 ): 4156 - 4171 .

GAO R Y , LI W W , XIE Y X , et al . Towards robust gesture recognition by characterizing the sensing quality of WiFi signals [J ] . Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies , 2022 , 6 ( 1 ): 1 - 26 .

HOANG NGUYEN X , NGUYEN V D , LUU Q T , et al . Robust WiFi sensing-based human pose estimation using denoising autoencoder and CNN with dynamic subcarrier attention [J ] . IEEE Internet of Things Journal , 2025 , 12 ( 11 ): 17066 - 17079 .

LYU W J , HE W D , LIN X P , et al . Non-contact monitoring of human vital signs using FMCW millimeter wave radar in the 120 GHz band [J ] . Sensors , 2021 , 21 ( 8 ): 2732 .

PALIPANA S , ROJAS D , AGRAWAL P , et al . FallDeFi [J ] . Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies , 2018 , 1 ( 4 ): 1 - 25 .

LUO F , KHAN S , JIANG B , et al . Vision transformers for human activity recognition using WiFi channel state information [J ] . IEEE Internet of Things Journal , 2024 , 11 ( 17 ): 28111 - 28122 .

LIU Z Y , ALAVI A , LI M Y , et al . Self-supervised learning for time series: contrastive or generative [EB ] . 2024 .

WANG X Y , GUO P X , ZHANG Y . Domain adaptation via bidirectional cross-attention transformer [EB ] . 2022 .

WEI J , WANG X , SCHUURMANS D , et al . Chain-of-thought prompting elicits reasoning in large language models [C ] // Advances in Neural Information Processing Systems 35 (NeurIPS 2022) . New Orleans, LA, USA : Curran Associates Inc. , 2022 : 24824 - 24837 .

KICIMAN E , NESS R , SHARMA A , et al . Causal reasoning and large language models: Opening a new frontier for causality [J ] . Transactions on Machine Learning Research , 2023 , 2023( 1 ): 2835 - 8856 .

ZHANG D , FENG T , XUE L L , et al . Parameter-efficient fine-tuning for foundation models [EB ] . 2025 .

DING N , QIN Y J , YANG G , et al . Parameter-efficient fine-tuning of large-scale pre-trained language models [J ] . Nature Machine Intelligence , 2023 , 5 ( 3 ): 220 - 235 .

SHEN J , LI L , DERY L M , et al . Cross-modal fine-tuning: Align then refine [C ] // Proceedings of the International Conference on Machine Learning . Honolulu, Hawaii, USA : PMLR , 2023 : 31030 - 31056 .

KAPLAN J , MCCANDLISH S , HENIGHAN T , et al . Scaling laws for neural language models [EB ] . 2020 .

YAN Y , CHEN G , WANG C , et al . Wi-FM: a WiFi-based foundation model for human activity recognition [EB ] . 2013 .

ZHOU X L , JIN T , DAI Y P , et al . Three-dimensional human pose estimation from micro-Doppler signature based on SISO UWB radar [J ] . Remote Sensing , 2024 , 16 ( 7 ): 1295 .

WANG Z , ZOU L , WEI S , et al . Large language model enabled semantic communication systems [EB ] . 2023 .

ABBAS M , KAR K , CHEN T . Leveraging large language models for wireless symbol detection via in-context learning [EB ] . 2023 .

XU S Z , KURISUMMOOTTIL THOMAS C , HASHASH O , et al . Large multi-modal models (LMMs) as universal foundation models for AI-native wireless systems [J ] . IEEE Network , 2024 , 38 ( 5 ): 10 - 20 .

马云舰 , 鲁华伟 , 成晨 , 等 . 基于大语言模型的小样本网络入侵检测方法 [J ] . 信息通信技术 , 2024 , 18 ( 3 ): 50 - 56 .

MA Y J , LU H W , CHENG C , et al . Network intrusion detection system based on large language model [J ] . Information and Communications Technologies , 2024 , 18 ( 3 ): 50 - 56 .

LIU B X , LIU X Y , GAO S J , et al . LLM4CP: adapting large language models for channel prediction [J ] . Journal of Communications and Information Networks , 2024 , 9 ( 2 ): 113 - 125 .

HU S G , LI M Y , XU J W , et al . Electromagnetic metamaterial agent [J ] . Light: Science & Applications , 2025 , 14 ( 1 ): 12 .

ZHAO Q , LYU S C , LI Y W , et al . MGML: multigranularity multilevel feature ensemble network for remote sensing scene classification [J ] . IEEE Transactions on Neural Networks and Learning Systems , 2023 , 34 ( 5 ): 2308 - 2322 .

SHEN L H , HSIEH C C , HSIAO A H , et al . CRONOS: colorization and contrastive learning for device-free NLoS human presence detection using Wi-Fi CSI [J ] . IEEE Internet of Things Journal , 2024 , 11 ( 3 ): 5491 - 5510 .

LIU R B , WEI J , LIU F Y , et al . Best practices and lessons learned on synthetic data [EB ] . 2024 .

钟怡 , 毕添琪 , 王菊 , 等 . 面向通信感知一体化的无线跨域感知研究综述 [J ] . 信号处理 , 2023 , 39 ( 6 ): 951 - 962 .

ZHONG Y , BI T Q , WANG J , et al . Survey on cross-domain based device-free sensing technology for integrated sensing and communication [J ] . Journal of Signal Processing , 2023 , 39 ( 6 ): 951 - 962 .

CHAHOUSHI M , NABATI M , ASVADI R , et al . CSI-based human activity recognition using multi-input multi-output autoencoder and fine-tuning [J ] . Sensors , 2023 , 23 ( 7 ): 3591 .

CHERAGHINIA M , SHAHID A , LUCHIE S , et al . A comprehensive overview on UWB radar: applications, standards, signal processing techniques, datasets, radio chips, trends and future research directions [J ] . IEEE Communications Surveys & Tutorials , 2025 , 27 ( 4 ): 2283 - 2324 .

ROWDEN A . Immersive visual analytics of Wi-Fi signal propagation and network health [D ] . College Park : University of Maryland, College Park , 2023 .

WANG J . Development of a smart health monitoring system for elderly care [J ] . Applied and Computational Engineering , 2024 , 45 ( 1 ): 29 - 34 .

杨铮，迟国轩，张桂栋，等 . 无线感知为AI开启新感官 [J ] . 瞭望 , 2020 ( 43 ): 36 - 40 .

YANG Z , CHI G C , ZHANG G D , et al . Wireless sensing opens up new senses for AI [J ] . Outlook , 2020 ( 43 ): 36 - 40 .

IMRAN S A , BISWAS S . LLaSA: a multimodal LLM for human activity analysis through wearable and smartphone sensors [EB ] . 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

暂无数据