AI賦能的通感算一體化關(guān)鍵技術(shù)研究綜述

朱政宇; 殷夢琳; 姚信威; 徐勇軍; 孫鋼燦; 徐明亮

doi:10.11999/JEIT250242

AI賦能的通感算一體化關(guān)鍵技術(shù)研究綜述

doi: 10.11999/JEIT250242 cstr: 32379.14.JEIT250242

1.
鄭州大學(xué)電氣與信息工程學(xué)院鄭州 450001
2.
浙江工業(yè)大學(xué)計算機(jī)科學(xué)與技術(shù)學(xué)院杭州 310014
3.
重慶郵電大學(xué)通信與信息工程學(xué)院重慶 400065
4.
鄭州大學(xué)計算機(jī)與人工智能學(xué)院鄭州 450001

詳細(xì)信息

作者簡介:
朱政宇：男，副教授，研究方向為無線通信和信號處理、5G、物聯(lián)網(wǎng)、機(jī)器學(xué)習(xí)、大規(guī)模MIMO、毫米波通信、無人機(jī)通信、物理層安全、無線協(xié)作網(wǎng)絡(luò)、凸優(yōu)化技術(shù)和攜能傳輸?shù)?/p>
殷夢琳：女，碩士生，研究方向為通感算一體化技術(shù)、深度學(xué)習(xí)等

姚信威：男，教授，研究方向為群智感知與協(xié)同、智聯(lián)網(wǎng)、智能機(jī)器人等

徐勇軍：男，教授，研究方向為反向散射通信、UAV通信、異構(gòu)無線網(wǎng)絡(luò)等

孫鋼燦：男，教授，研究方向為深度學(xué)習(xí)、機(jī)器學(xué)習(xí)、無線通信、物理層安全技術(shù)等

徐明亮：男，教授，研究方向為人工智能、大數(shù)據(jù)、機(jī)器人、工業(yè)軟件等

通訊作者:
孫鋼燦　iegcsun@zzu.edu.cn

中圖分類號: TN915.0
計量
- 文章訪問數(shù): 250
- HTML全文瀏覽量: 84
- PDF下載量: 36
- 被引次數(shù): 0
出版歷程
- 收稿日期: 2025-04-07
- 修回日期: 2025-06-04
- 網(wǎng)絡(luò)出版日期: 2025-06-14

Overview of the Research on Key Technologies for AI-powered Integrated Sensing, Communication and Computing

1.
School of Electrical and Information Engineering, Zhengzhou University, Zhengzhou 450001, China
2.
School of Compute Science and Technology, Zhejiang University Of Technology, Hangzhou 310014, China
3.
School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing 400065, China
4.
School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou 450001, China

摘要

摘要: 通感算一體化技術(shù)與人工智能算法相結(jié)合已成為一個非常重要的領(lǐng)域，因其頻譜利用率高、硬件成本低等優(yōu)點，已經(jīng)成為第6代(6G)網(wǎng)絡(luò)中的關(guān)鍵技術(shù)之一。人工智能(AI)賦能的通感算一體化系統(tǒng)通過集成感知、通信、計算和人工智能功能，可在日益復(fù)雜和動態(tài)的環(huán)境中實現(xiàn)快速數(shù)據(jù)處理、實時資源優(yōu)化和智能決策，已經(jīng)廣泛應(yīng)用于智能車載網(wǎng)絡(luò)，包括無人機(jī)和自動汽車，以及雷達(dá)應(yīng)用、定位和跟蹤、波束成形等領(lǐng)域。該文在引入人工智能算法來提高通感算一體化系統(tǒng)性能的基礎(chǔ)上，簡要介紹了人工智能和通感算一體化的特征與優(yōu)勢，重點討論了AI賦能的通感算一體化系統(tǒng)的智能網(wǎng)絡(luò)框架、應(yīng)用前景、性能指標(biāo)和關(guān)鍵技術(shù)，并在最后對AI賦能的通感算一體化面臨的挑戰(zhàn)進(jìn)行了研究展望，未來的6G無線通信網(wǎng)絡(luò)將超越純粹的數(shù)據(jù)傳輸管道，成為一個集成傳感、通信、計算和智能的綜合平臺，以提供無處不在的人工智能服務(wù)。
- 6G /
- 人工智能 /
- 通感算一體化 /
- 深度強(qiáng)化學(xué)習(xí)
Abstract: The Integration of Sensing, Communication and Computing (ISCC) combined with Artificial Intelligence(AI) algorithms has emerged as a critical enabler of Sixth-Generation (6G) networks due to its high spectral efficiency and low hardware cost. AI-powered ISCC systems, which combine sensing, communication, computing, and intelligent algorithms, support fast data processing, real-time resource allocation, and adaptive decision-making in complex and dynamic environments. These systems are increasingly applied in intelligent vehicular networks—including Unmanned Aerial Vehicles (UAVs) and autonomous driving—as well as in radar, positioning, tracking, and beamforming. This overview outlines the development and advantages of AI-enabled ISCC systems, focusing on performance benefits, application potential, evaluation metrics, and enabling technologies. It concludes by discussing future research directions. Future 6G networks are expected to evolve beyond data transmission to form an integrated platform that unifies sensing, communication, computing, and intelligence, enabling pervasive AI services. Significance AI-powered ISCC marks a transformative shift in wireless communication, enabling more efficient spectrum utilization, reduced hardware cost, and improved adaptability in complex environments. This integration is central to the development of 6G networks, which aim to deliver intelligent and efficient services across applications such as autonomous vehicles, UAVs, and smart cities. The significance of this research lies in its potential to reshape the management and optimization of communication, sensing, and computing resources, advancing the realization of a ubiquitously connected and intelligent infrastructure. Progress Recent advances in AI—particularly in machine learning, deep learning, and reinforcement learning—have substantially improved the performance of ISCC systems. These methods enable real-time data processing, intelligent resource management, and adaptive decision-making, which are critical for future 6G requirements. Notable progress includes AI-driven waveform design, beamforming, channel estimation, and dynamic spectrum allocation, all of which enhance ISCC efficiency and reliability. Additionally, the integration of edge computing and federated learning has mitigated challenges related to latency, data privacy, and scalability, facilitating broader deployment of AI-enabled ISCC systems. Conclusions Research on AI-powered ISCC systems highlights the benefits of integrating AI with sensing, communication, and computing. AI algorithms improve resource efficiency, sensing precision, and real-time adaptability, making ISCC systems well suited for dynamic and complex environments. The adoption of lightweight models and distributed learning has broadened applicability to resource-limited platforms such as drones and IoT sensors. Overall, AI-enabled ISCC systems advance the realization of 6G networks, where sensing, communication, and computing are unified to support intelligent and ubiquitous services. Prospects The advancement of AI-powered ISCC systems depends on addressing key challenges, including data quality, model complexity, security, and real-time performance. Future research should focus on developing robust AI models capable of generalizing across diverse wireless environments. Progress in lightweight AI and edge computing will be critical for deployment in resource-constrained devices. The integration of multi-modal data and the design of secure, privacy-preserving algorithms will be essential to ensure system reliability and safety. As 6G networks evolve, AI-powered ISCC systems are expected to underpin intelligent, efficient, and secure communication infrastructures, reshaping human-technology interaction in the digital era.
- 6G /
- Artificial Intelligence (AI) /
- Integration of Sensing Communication and Computing (ISCC) /
- Deep reinforcement learning

HTML全文

圖 1 6G驅(qū)動AI賦能通感算一體化系統(tǒng)

下載: 全尺寸圖片幻燈片

圖 2 人工智能、機(jī)器學(xué)習(xí)、深度學(xué)習(xí)之間的關(guān)系

下載: 全尺寸圖片幻燈片

圖 3 DRL原理圖

下載: 全尺寸圖片幻燈片

圖 4 FL原理框架

下載: 全尺寸圖片幻燈片

圖 5 AI賦能通感算一體化網(wǎng)絡(luò)架構(gòu)

下載: 全尺寸圖片幻燈片

圖 6 AI賦能通感算一體化應(yīng)用場景

下載: 全尺寸圖片幻燈片

表 1 5G與6G部分性能指標(biāo)對比

性能指標(biāo)	5G	6G	提升效果
峰值速率	10～20 Gbit/(s·Hz)(理論值)	100 Gbit/(s·Hz) ～1 Tbit/(s·Hz)(理論值)	10～100倍
用戶體驗速率	0.1～1 Gbit/(s·Hz)	數(shù)十Gbit/(s·Hz)	10～100倍
時延	1 ms	10～100 μs	10～100倍
連接密度	10⁶設(shè)備/km²	10⁷～10⁸設(shè)備/km²	10～100倍
頻譜效率	約100 bit/(s·Hz)	150～300 bit/(s·Hz)	1.5～3倍
覆蓋范圍	地面基站為主	空天地一體化覆蓋	全球無縫覆蓋

下載: 導(dǎo)出CSV

表 2 AI賦能通感算一體化系統(tǒng)與傳統(tǒng)正交頻分復(fù)用波形系統(tǒng)性能對比

對比維度	AI賦能通感算一體化系統(tǒng)	傳統(tǒng)正交頻分復(fù)用波形系統(tǒng)	關(guān)鍵差異來源
通信性能^[18,19]	AI優(yōu)化波束成形，誤碼率降低10%～30% 頻譜效率提升	高峰均功率比導(dǎo)致信號失真固定子載波分配效率受限	AI動態(tài)優(yōu)化波形與資源分配
感知精度^[19–21]	MSE降低20%～50% 支持多目標(biāo)跟蹤與語義提取	快速傅里葉變換低信噪比誤差大單目標(biāo)檢測為主	AI增強(qiáng)信號去噪能力
計算效率^[16,22]	邊緣智能降低30%～60%時延實時信道建模	云端集中計算時延高多徑分離需迭代處理	云邊端協(xié)同架構(gòu)優(yōu)化
時空頻復(fù)雜度	LSTM波束預(yù)測控制時延動態(tài)頻譜共享	凸優(yōu)化算法耗時長固定子載波分配	AI動態(tài)資源調(diào)度技術(shù)
能耗	AI輔助降低功耗	全子載波高功耗	智能功率優(yōu)化策略

下載: 導(dǎo)出CSV

表 3 AI賦能通感算一體化系統(tǒng)關(guān)鍵技術(shù)簡要匯總

參考文獻(xiàn)	關(guān)鍵技術(shù)	AI作用	性能指標(biāo)	訓(xùn)練模型	應(yīng)用場景
[25]	波形設(shè)計	優(yōu)化波形生成、選擇、調(diào)整、匹配等，以適應(yīng)通信感知雙重需求，并降低復(fù)雜度	保密率	DRL等	自動駕駛
[21,26]	波束賦形	提高了頻譜效率，減輕了多徑衰落，確保了動態(tài)城市環(huán)境中的無縫連接和可靠性	和速率	DRL, DL等	自動駕駛
[28–30]	信道估計	提升信道估計的精度、降低計算復(fù)雜性，實現(xiàn)動態(tài)適配	估計精度	GAN, CNN等	自動駕駛
[32]	干擾管理	在資源有限場景中，實時應(yīng)對并緩解通信與感知任務(wù)中的干擾問題	均方誤差	DNN, ML等	無人機(jī)監(jiān)測
[33,34]	動態(tài)頻譜分配	提供智能化的優(yōu)化算法和學(xué)習(xí)模型，實現(xiàn)高效的動態(tài)分配，提升系統(tǒng)性能	準(zhǔn)確率、頻譜效率	DRL, RNN等	工業(yè)物聯(lián)網(wǎng)

下載: 導(dǎo)出CSV

參考文獻(xiàn)(35)

[1]	ZHANG Shunqing, XIANG Chenlu, and XU Shugong. 6G: Connecting everything by 1000 times price reduction[J]. IEEE Open Journal of Vehicular Technology, 2020, 1: 107–115. doi: 10.1109/OJVT.2020.2980003.
[2]	余顯祥, 姚雪, 楊婧, 等. 面向感知應(yīng)用的通感一體化信號設(shè)計技術(shù)與綜述[J]. 雷達(dá)學(xué)報, 2023, 12(2): 247–261. doi: 10.12000/JR23015. YU Xianxiang, YAO Xue, YANG Jing, et al. Radar-centric DFRC signal design: Overview and future research avenues[J]. Journal of Radars, 2023, 12(2): 247–261. doi: 10.12000/JR23015.
[3]	TAN D K P, HE Jia, LI Yanchun, et al. Integrated sensing and communication in 6G: Motivations, use cases, requirements, challenges and future directions[C]. IEEE International Online Symposium on Joint Communications & Sensing (JC&S), Dresden, Germany, 2021: 1–6. doi: 10.1109/JCS52304.2021.9376324.
[4]	WU Nan, JIANG Rongkun, WANG Xinyi, et al. AI-enhanced integrated sensing and communications: Advancements, challenges, and prospects[J]. IEEE Communications Magazine, 2024, 62(9): 144–150. doi: 10.1109/MCOM.001.2300724.
[5]	林奕森, 甘德樵, 葛曉虎. AI賦能6G: 綠色通信的未來[J]. 移動通信, 2024, 48(8): 20–24, 55. doi: 10.3969/j.issn.1006-1010.20240621-0001. LIN Yisen, GAN Deqiao, and GE Xiaohu. AI-powered 6G: The future of green communications[J]. Mobile Communications, 2024, 48(8): 20–24, 55. doi: 10.3969/j.issn.1006-1010.20240621-0001.
[6]	閆實, 彭木根, 王文博. 通信-感知-計算融合: 6G愿景與關(guān)鍵技術(shù)[J]. 北京郵電大學(xué)學(xué)報, 2021, 44(4): 1–11. doi: 10.13190/j.jbupt.2021-081. YAN Shi, PENG Mugen, and WANG Wenbo. Integration of communication, sensing and computing: The vision and key technologies of 6G[J]. Journal of Beijing University of Posts and Telecommunications, 2021, 44(4): 1–11. doi: 10.13190/j.jbupt.2021-081.
[7]	王輝, 孟士堯, 賈敏. 空天地一體化場景中的6G通感算融合與數(shù)字孿生技術(shù)[J]. 無線電通信技術(shù), 2024, 50(6): 1057–1066. doi: 10.3969/j.issn.1003-3114.2024.06.001. WANG Hui, MENG Shiyao, and JIA Min. 6G communication-sensing-computing integrated space-air-ground digital twin network[J]. Radio Communications Technology, 2024, 50(6): 1057–1066. doi: 10.3969/j.issn.1003-3114.2024.06.001.
[8]	陳新宇, 王衛(wèi)斌, 陸光輝. 基于AI agent的6G內(nèi)生智能技術(shù)框架及其應(yīng)用[J]. 移動通信, 2024, 48(7): 28–32. doi: 10.3969/j.issn.1006-1010.20240613-0001. CHEN Xinyu, WANG Weibin, and LU Guanghui. 6G native intelligent technology framework and its application based on AI agent[J]. Mobile Communications, 2024, 48(7): 28–32. doi: 10.3969/j.issn.1006-1010.20240613-0001.
[9]	ZHAO Junhui, Ren Ruixing, ZOU Dan, et al. IoV-Oriented integrated sensing, computation, and communication: System design and resource allocation[J]. IEEE Transactions on Vehicular Technology, 2024, 73(11): 16283–16294. doi: 10.1109/TVT.2024.3422270.
[10]	SALEM H, QUAMAR M D M, MANSOOR A, et al. Data-Driven integrated sensing and communication: Recent advances, challenges, and future prospects[J]. arXiv: 2308.09090, 2023.
[11]	陳真, 杜曉宇, 唐杰, 等. 基于深度強(qiáng)化學(xué)習(xí)的RIS輔助通感融合網(wǎng)絡(luò): 挑戰(zhàn)與機(jī)遇[J]. 電子信息學(xué)報, 2024, 46(9): 3467–3473. doi: 10.11999/JEIT240086. CHEN Zhen, DU Xiaoyu, TANG Jie, et al. DRL-based RIS-assisted ISAC Network: Challenges and opportunities[J]. Journal of Electronics & Information Technology, 2024, 46(9): 3467–3473. doi: 10.11999/JEIT240086.
[12]	HOU Peng, HUANG Yi, ZHU Hongbin, et al. Distributed DRL-based integrated sensing, communication, and computation in cooperative UAV-enabled intelligent transportation systems[J]. IEEE Internet of Things Journal, 2025, 12(5): 5792–5806. doi: 10.1109/JIOT.2024.3489655.
[13]	LIANG Yipeng, XHEN Qimei, and HAO Jiang. Federated learning with integrated sensing, communication, and computation: Frameworks and performance analysis[J]. arXiv: 2409.11240, 2024.
[14]	LIU Peixi, ZHU Guangxu, WANG Shuai, et al. Toward ambient intelligence: Federated edge learning with task-oriented sensing, computation, and communication integration[J]. IEEE Journal of Selected Topics in Signal Processing, 2023, 17(1): 158–172. doi: 10.1109/JSTSP.2022.3226836.
[15]	JIAO Licheng, SHAO Yilin, SUN Long, et al. Advanced deep learning models for 6G: Overview, opportunities, and challenges[J] IEEE Access, 2024, 12: 133245–133314. doi: 10.1109/ACCESS.2024.3418900.
[16]	王新奕, 費澤松, 周一青, 等. 面向物聯(lián)網(wǎng)的通感算智融合: 關(guān)鍵技術(shù)與未來展望[J]. 電子與信息學(xué)報, 2025, 47(4): 888-908. DOI: 10.11999/JEIT240806. WANG Xinyi, FEI Zesong, ZHOU Yiqing, et al. Integrated sensing, communication, computation, and intelligence towards IoT: Key technologies and future directions[J]. Journal of Electronics & Information Technology, 2025, 47(4): 888-908. DOI: 10.11999/JEIT240806.
[17]	王友祥, 裴郁杉, 黃蓉, 等. 6G通感算一體化網(wǎng)絡(luò)架構(gòu)和關(guān)鍵技術(shù)研究[J]. 移動通信, 2023, 47(9): 2–10. doi: 10.3969/j.issn.1006-1010.20230904-0002. WANG Youxiang, PEI Yushan, HUANG Rong, et al. Network architecture and key technologies for 6G integrated communication, sensing and computing[J]. Mobile Communications, 2023, 47(9): 2–10. doi: 10.3969/j.issn.1006-1010.20230904-0002.
[18]	ZHANG Jifa, GUO Shaoyong, GONG Shiqi, et al. Intelligent waveform design for integrated sensing and communication[J]. IEEE Wireless Communications, 2025, 32(1): 166–173. doi: 10.1109/MWC.003.2400044.
[19]	KHORAMNEJAD F and HOSSAIN E. Generative AI for the optimization of next-generation wireless networks: Basics, state-of-the-art, and open challenges[J]. IEEE Communications Surveys & Tutorials, 2025. doi: 10.1109/COMST.2025.3535554.
[20]	LIU Chang, YUAN Weijie, LI Shuangyang, et al. Learning-based predictive beamforming for integrated sensing and communication in vehicular networks[J]. IEEE Journal on Selected Areas in Communications, 2022, 40(8): 2317–2334. doi: 10.1109/JSAC.2022.3180803.
[21]	LIU Yiyang, ZHANG Siyao, LI Xinmin, et al. Deep reinforcement learning-based beamforming design in ISAC-assisted vehicular networks[C]. IEEE Wireless Communications and Networking Conference, Dubai, United Arab Emirates, 2024: 1–6. doi: 10.1109/WCNC57260.2024.10571018.
[22]	VALCARCE A, KELA P, MANDELLI S, et al. The role of AI in 6G MAC[C]. 2024 Joint European Conference on Networks and Communications & 6G Summit, Antwerp, Belgium, 2024: 723–728. doi: 10.1109/EuCNC/6GSummit60053.2024.10597082.
[23]	REN Ruixing. Integrated sensing, communication and computation: Research status and future prospects[J]. 2024.
[24]	馬丁友, 劉祥, 黃天耀, 等. 雷達(dá)通信一體化: 共用波形設(shè)計和性能邊界[J]. 雷達(dá)學(xué)報, 2022, 11(2): 198–212. doi: 10.12000/JR21146. MA Dingyou, LIU Xiang, HUANG Tianyao, et al. Joint radar and communications: Shared waveform designs and performance bounds[J]. Journal of Radars, 2022, 11(2): 198–212. doi: 10.12000/JR21146.
[25]	LIU Qian, ZHU Yuqian, LI Ming, et al. DRL-based secrecy rate optimization for RIS-assisted secure ISAC systems[J]. IEEE Transactions on Vehicular Technology, 2023, 72(12): 16871–16875. doi: 10.1109/TVT.2023.3297602.
[26]	ZHONG Kai, HU Jinfeng, PAN Cunhua, et al. Joint waveform and beamforming design for RIS-aided ISAC systems[J]. IEEE Signal Processing Letters, 2023, 30: 165–169. doi: 10.1109/LSP.2023.3242554.
[27]	徐明楓, 李陽, 韓凱峰, 等. 基于GAN的導(dǎo)頻配置和信道估計聯(lián)合優(yōu)化算法[J]. 信息通信技術(shù)與政策, 2023, 49(9): 58–66. doi: 10.12267/j.issn.2096-5931.2023.09.009. XU Mingfeng, LI Yang, HAN Kaifeng, et al. GAN-based joint pilot configuration and channel estimation optimization method[J]. Information and Communications Technology and Policy, 2023, 49(9): 58–66. doi: 10.12267/j.issn.2096-5931.2023.09.009.
[28]	BALEVI E, DOSHI A, and ANDREWS J G. Massive MIMO channel estimation with an untrained deep neural network[J]. IEEE Transactions on Wireless Communications, 2020, 19(3): 2079–2090. doi: 10.1109/TWC.2019.2962474.
[29]	SAFARI M S, POURAHMADI V, and SODAGARI S. Deep UL2DL: Data-driven channel knowledge transfer from uplink to downlink[J]. IEEE Open Journal of Vehicular Technology, 2020, 1: 29–44. doi: 10.1109/OJVT.2019.2962631.
[30]	DU Ying, LI Yang, XU Mingfeng, et al. A joint channel estimation and compression method based on GAN in 6G communication systems[J]. Applied Sciences, 2023, 13(4): 2319. doi: 10.3390/app13042319.
[31]	NGUYEN C, HOANG T M, and CHEEMA A A. Channel estimation using CNN-LSTM in RIS-NOMA assisted 6G network[J]. IEEE Transactions on Machine Learning in Communications and Networking, 2023, 1: 43–60. doi: 10.1109/TMLCN.2023.3278232.
[32]	LIU Xiangnan, ZHANG Haijun, LONG Keping, et al. Distributed unsupervised learning for interference management in integrated sensing and communication systems[J]. IEEE Transactions on Wireless Communications, 2023, 22(12): 9301–9312. doi: 10.1109/TWC.2023.3269815.
[33]	GAO Kaixuan, WANG Huiqiang, LU Hongwu, et al. Toward 5G NR high-precision indoor positioning via channel frequency response: A new paradigm and dataset generation method[J]. IEEE Journal on Selected Areas in Communications, 2022, 40(7): 2233–2247. doi: 10.1109/JSAC.2022.3157397.
[34]	SAIDUTTA Y M, ABDI A, and FEKRI F. Joint source-channel coding over additive noise analog channels using mixture of variational autoencoders[J]. IEEE Journal on Selected Areas in Communications, 2021, 39(7): 2000–2013. doi: 10.1109/JSAC.2021.3078489.
[35]	LIU Boxun, LIU Yuanyu, GAO Shijian, et al. LLM4CP: Adapting large language models for channel prediction[J]. Communications and Information Networks, 2024, 9(2): 113–125. doi: 10.23919/JCIN.2024.10582829.