An Embodied Intelligence-Based Method for Single-UAV Tracking of Maneuvering Radiation Sources in Unknown Environments

LIANG Hongtao; FU Yangmeizi; WAN Yiyao; LIU Xiaodong; WU Qihui

doi:10.12263/DZXB.20260273

您当前的位置：

首页 >

文章列表页 >

An Embodied Intelligence-Based Method for Single-UAV Tracking of Maneuvering Radiation Sources in Unknown Environments

更新时间：2026-06-09

- An Embodied Intelligence-Based Method for Single-UAV Tracking of Maneuvering Radiation Sources in Unknown Environments
- ACTA ELECTRONICA SINICA Pages: 1-15(2026)
- 作者机构：
  
  1.南京航空航天大学电子信息工程学院，江苏南京 211106
  2.南昌大学信息工程学院，江西南昌 330031
- 作者简介：
- 基金信息：
  
  National Key Research and Development Project(2023YFB2904500);Yangtze River Delta Science and Technology Innovation Community Joint Research (Basic Research) Project(2024CSJZN00300)
- DOI：10.12263/DZXB.20260273
  CLC： TN929.5;TN911.7
- Received：17 April 2026，
  
  Accepted：15 May 2026，
  
  Online First：09 June 2026，
- 稿件说明：
移动端阅览
LIANG Hongtao, FU Yangmeizi, WAN Yiyao, et al. An Embodied Intelligence-Based Method for Single-UAV Tracking of Maneuvering Radiation Sources in Unknown Environments[J/OL]. ACTA ELECTRONICA SINICA, 2026, 1-15.
DOI：

LIANG Hongtao, FU Yangmeizi, WAN Yiyao, et al. An Embodied Intelligence-Based Method for Single-UAV Tracking of Maneuvering Radiation Sources in Unknown Environments[J/OL]. ACTA ELECTRONICA SINICA, 2026, 1-15. DOI： 10.12263/DZXB.20260273.

摘要

在电子侦察、频谱监测与应急搜救等任务中，单架无人机仅凭接收信号强度指示（Received Signal Strength Indicator， RSSI）对非合作机动辐射源进行被动追踪具有重要的战略与工程意义。然而，现有RSSI定位方法高度依赖环境传播参数先验，且将参数估计、状态滤波与路径规划串行割裂，难以适应以发射功率与路径损耗指数为代表的核心传播参数未知且目标持续机动的动态场景；同时，单通道标量RSSI固有的低空间分辨力进一步加剧了探索与利用之间的结构性矛盾。为此，本文提出一种基于具身智能的单无人机闭环追踪方法，以结构化不确定度指标作为跨层信息流的统一载体，将感知、认知与决策通过不确定度的双向传递进行深度耦合，形成以闭环信息流驱动的协同追踪架构。在感知层，构建参数先验推断网络，从历史时空观测序列中提取传播参数的经验分布，为后续贝叶斯推断提供数据驱动的初始化依据。在认知层，针对未知传播参数与机动状态的联合估计难题，设计基于Rao-Blackwellized条件分解的双链解耦推断机制，外层粒子滤波在线估计大尺度衰落参数，内层自适应交互多模型滤波器精确推断目标机动状态，并引入有效样本量监测下的粒子复苏与信念继承机制，避免参数重采样对状态追踪连续性的破坏。在决策层，为缓解上述探索-利用矛盾，构建融合信息增益与模型预测控制的分层规划策略，并引入可学习的排序门控网络对追踪、探测与保守等候选策略进行实时效用评估，使无人机依据信念不确定度自适应地从广域探索转换为紧密伴飞。仿真结果表明，所提方法在传播参数完全未知的冷启动条件下各项核心指标均优于所对比的基线方法，且在无人工标定先验模式下的追踪性能接近乃至在部分指标上超越若干基线在参数已知条件下的理想表现，验证了所提架构在恶劣感知条件下的自适应能力与鲁棒性。

Abstract

Passive tracking of uncooperative maneuvering radiation sources by a single unmanned aerial vehicle (UAV) using only received signal strength indicator (RSSI) measurements is of considerable strategic and engineering value for missions such as electronic reconnaissance

spectrum monitoring

and emergency search and rescue. However

existing RSSI localization methods rely heavily on environmental propagation priors and treat parameter estimation

state filtering

and path planning as isolated serial processes

leaving them unable to handle dynamic scenarios in which core propagation parameters such as transmit power and path loss exponent are unknown and the target keeps maneuvering. The inherent low spatial resolution of scalar RSSI from a single channel further intensifies the structural conflict between exploration and exploitation. To address these challenges

this paper proposes an embodied intelligence-based closed-loop tracking method for a single UAV

which adopts structured uncertainty metrics as a unified carrier of cross-layer information flow and deeply couples perception

cognition

and decision-making through bidirectional propagation of uncertainty

forming a cooperative tracking architecture driven by closed-loop information flow. At the perception layer

a parameter prior inference network is built to extract the empirical distribution of propagation parameters from historical spatio-temporal observation sequences

providing data-driven initialization for the subsequent Bayesian inference. At the cognition layer

a dual-chain decoupled inference mechanism based on Rao-Blackwellized conditional decomposition is designed for the joint estimation of unknown propagation parameters and maneuvering states

in which the outer particle filter estimates large-scale fading parameters online while the inner adaptive interacting multiple model filter accurately infers maneuvering states of the target. A particle revival mechanism guided by effective sample size monitoring is further introduced together with a belief inheritance mechanism to prevent parameter resampling from disrupting the continuity of state tracking. At the decision layer

to mitigate the exploration-exploitation conflict noted above

a hierarchical planning strategy fusing information gain with model predictive control is constructed

and a learnable ranking gating network is introduced to perform real-time utility evaluation over candidate strategies including tracking

probing

and conservative options

allowing the UAV to adaptively transition from broad-area exploration to tight escort flying according to belief uncertainty. Simulation results show that the proposed method outperforms the compared baseline approaches across all core metrics under cold-start conditions with completely unknown propagation parameters

and the tracking performance under the mode without manual calibration priors approaches and in certain metrics surpasses the ideal performance of several baselines operating with known parameters

which verifies the adaptability and robustness of the proposed architecture under degraded sensing conditions.

关键词

Keywords

references

Zeng Y , Wu Q Q , Zhang R . Accessing from the sky: A tutorial on UAV communications for 5G and beyond [J ] . Proceedings of the IEEE , 2019 , 107 ( 12 ): 2327 - 2375 . DOI: 10.1109/jproc.2019.2952892 http://dx.doi.org/10.1109/jproc.2019.2952892

安建平 , 李建国 , 于季弘 , 等 . 空天通信网络关键技术综述 [J ] . 电子学报 , 2022 , 50 ( 2 ): 470 - 479 .

An Jianping , Li Jianguo , Yu Jihong , et al . Key technologies of space-air-ground communication networks: A survey [J ] . Acta Electronica Sinica , 2022 , 50 ( 2 ): 470 - 479 . (in Chinese)

Obeidat H , Shuaieb W , Obeidat O , et al . A review of indoor localization techniques and wireless technologies [J ] . Wireless Personal Communications , 2021 , 119 ( 1 ): 289 - 327 . DOI: 10.1007/s11277-021-08209-5 http://dx.doi.org/10.1007/s11277-021-08209-5

Zhou F H , Wang C Y , Wu G Y , et al . Accurate spectrum map construction for spectrum management through intelligent frequency-spatial reasoning [J ] . IEEE Transactions on Communications , 2023 , 71 ( 7 ): 3932 - 3945 . DOI: 10.1109/tcomm.2023.3267569 http://dx.doi.org/10.1109/tcomm.2023.3267569

Coluccia A , Fascista A . On the hybrid TOA/RSS range estimation in wireless sensor networks [J ] . IEEE Transactions on Wireless Communications , 2018 , 17 ( 1 ): 361 - 371 . DOI: 10.1109/twc.2017.2766628 http://dx.doi.org/10.1109/twc.2017.2766628

Wojcicki P , Zientarski T , Charytanowicz M , et al . Estimation of the path-loss exponent by Bayesian filtering method [J ] . Sensors , 2021 , 21 ( 6 ): 1934 . DOI: 10.3390/s21061934 http://dx.doi.org/10.3390/s21061934

Vaghefi R M , Gholami M R , Buehrer R M , et al . Cooperative received signal strength-based sensor localization with unknown transmit powers [J ] . IEEE Transactions on Signal Processing , 2013 , 61 ( 6 ): 1389 - 1403 . DOI: 10.1109/tsp.2012.2232664 http://dx.doi.org/10.1109/tsp.2012.2232664

Zholamanov B , Saymbetov A , Nurgaliyev M , et al . RSSI fingerprint-based indoor localization solutions using machine learning algorithms: A comprehensive review [J ] . Smart Cities , 2025 , 8 ( 5 ): 153 . DOI: 10.3390/smartcities8050153 http://dx.doi.org/10.3390/smartcities8050153

Liu J Y , Liu X D , Liang H T , et al . A data-and-semantic dual-driven intelligent inference framework for simultaneously spectrum map construction and signal source localization [J ] . IEEE Internet of Things Journal , 2025 , 12 ( 12 ): 18750 - 18764 . DOI: 10.1109/jiot.2025.3556727 http://dx.doi.org/10.1109/jiot.2025.3556727

段世红 , 何昊 , 徐诚 , 等 . 未知环境下基于深度序列蒙特卡罗树搜索的信源导航方法 [J ] . 电子学报 , 2022 , 50 ( 7 ): 1744 - 1752 .

Duan Shihong , He Hao , Xu Cheng , et al . DS-MCTS: A deep sequential Monte-Carlo tree search method for source navigation in unknown environments [J ] . Acta Electronica Sinica , 2022 , 50 ( 7 ): 1744 - 1752 . (in Chinese)

Zhou F H , Liu C Y , Zhang H , et al . SpectrumFM: A foundation model for intelligent spectrum management [J ] . IEEE Journal on Selected Areas in Communications , 2026 , 44 : 4471 - 4488 . DOI: 10.1109/jsac.2025.3644783 http://dx.doi.org/10.1109/jsac.2025.3644783

Cheng C , Tourneret J Y , Lu X D . A Rao-blackwellized particle filter with variational inference for state estimation with measurement model uncertainties [J ] . IEEE Access , 2020 , 8 : 55665 - 55675 . DOI: 10.1109/access.2020.2981948 http://dx.doi.org/10.1109/access.2020.2981948

Li X H , Lu B , Li Y X , et al . Adaptive interacting multiple model for underwater maneuvering target tracking with one-step randomly delayed measurements [J ] . Ocean Engineering , 2023 , 280 : 114933 . DOI: 10.1016/j.oceaneng.2023.114933 http://dx.doi.org/10.1016/j.oceaneng.2023.114933

Popović M , Vidal-Calleja T , Hitz G , et al . An informative path planning framework for UAV-based terrain monitoring [J ] . Autonomous Robots , 2020 , 44 ( 6 ): 889 - 911 . DOI: 10.1007/s10514-020-09903-2 http://dx.doi.org/10.1007/s10514-020-09903-2

Charrow B , Liu S K , Kumar V , et al . Information-theoretic mapping using cauchy-schwarz quadratic mutual information [C ] // 2015 IEEE International Conference on Robotics and Automation . Piscataway : IEEE , 2015 : 4791 - 4798 . DOI: 10.1109/icra.2015.7139865 http://dx.doi.org/10.1109/icra.2015.7139865

Hoffmann F , Charlish A , Ritchie M , et al . Policy rollout action selection in continuous domains for sensor path planning [J ] . IEEE Transactions on Aerospace and Electronic Systems , 2021 , 57 ( 4 ): 2247 - 2264 . DOI: 10.1109/taes.2021.3057649 http://dx.doi.org/10.1109/taes.2021.3057649

Carvalho Chanel C , Teichteil-Königsbuch F , Lesire C . Multi-target detection and recognition by UAVs using online POMDPs [J ] . Proceedings of the AAAI Conference on Artificial Intelligence , 2013 , 27 ( 1 ): 1381 - 1387 . DOI: 10.1609/aaai.v27i1.8551 http://dx.doi.org/10.1609/aaai.v27i1.8551

Goel H , Lipschitz L J , Agarwal S , et al . Reinforcement learning for agile active target sensing with a UAV [PP/OL ] . V1. arXiv ( 2022-12-16 )[ 2026-05-18 ] . https://doi.org/10.48550/arXiv.2212.08214 https://doi.org/10.48550/arXiv.2212.08214 .

Xia Z Y , Du J , Wang J J , et al . Multi-agent reinforcement learning aided intelligent UAV swarm for target tracking [J ] . IEEE Transactions on Vehicular Technology , 2022 , 71 ( 1 ): 931 - 945 . DOI: 10.1109/tvt.2021.3129504 http://dx.doi.org/10.1109/tvt.2021.3129504

Sunberg Z , Kochenderfer M . Online algorithms for POMDPs with continuous state, action, and observation spaces [J ] . Proceedings of the International Conference on Automated Planning and Scheduling , 2018 , 28 : 259 - 263 . DOI: 10.1609/icaps.v28i1.13882 http://dx.doi.org/10.1609/icaps.v28i1.13882

Hu J Z , Zhang H L , Song L Y , et al . Reinforcement learning for a cellular Internet of UAVs: Protocol design, trajectory control, and resource management [J ] . IEEE Wireless Communications , 2020 , 27 ( 1 ): 116 - 123 . DOI: 10.1109/mwc.001.1900262 http://dx.doi.org/10.1109/mwc.001.1900262

Bajcsy R , Aloimonos Y , Tsotsos J K . Revisiting active perception [J ] . Autonomous Robots , 2018 , 42 ( 2 ): 177 - 196 . DOI: 10.1007/s10514-017-9615-3 http://dx.doi.org/10.1007/s10514-017-9615-3

Liang H T , Diao Y H , Wu Y H , et al . Synergetic empowerment: Wireless communications meets embodied intelligence [PP/OL ] . V2. arXiv ( 2026-05-26 )[ 2026-05-18 ] . https://doi.org/10.48550/arXiv.2509.10481 https://doi.org/10.48550/arXiv.2509.10481 .

Liu H P , Guo D , Cangelosi A . Embodied intelligence: A synergy of morphology, action, perception and learning [J ] . ACM Computing Surveys , 2025 , 57 ( 7 ): 1 - 36 . DOI: 10.1145/3717059 http://dx.doi.org/10.1145/3717059

Duan J F , Yu S , Tan H L , et al . A survey of embodied AI: From simulators to research tasks [J ] . IEEE Transactions on Emerging Topics in Computational Intelligence , 2022 , 6 ( 2 ): 230 - 244 . DOI: 10.1109/tetci.2022.3141105 http://dx.doi.org/10.1109/tetci.2022.3141105

An Z L , Yu X Q , Wang C , et al . Embodied intelligence: Recent advances and future perspectives [J ] . The Innovation Informatics , 2025 , 1 ( 1 ): 100008 . DOI: 10.59717/j.xinn-inform.2025.100008 http://dx.doi.org/10.59717/j.xinn-inform.2025.100008

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Embodied-Intelligence-Driven Electromagnetic Spectrum Resource Allocation for Low-Altitude UAV Data Offloading and Beam Tracking

Adaptive Output Consensus of Heterogeneous Open Multi-Agent Systems under Actuator Attacks

A Unified Remote Sensing Image Restoration Framework Integrating Frequency-Domain Physical Perception and Higher-Order Semantic Fusion

Identification and Migration of Silent Security Patches in Blockchain Systems via Information Fusion

Spatial-FineDef: An Approach for Detecting Small Defects in Wind Turbine Blades that Integrate Multi-Scale Perception and Adaptive Enhancement

Related Author

ZHAO Zhongling

HE Hao

SONG Tian

Related Institution

School of Cyberspace Science and Technology, Beijing Institute of Technology of China

The State Key Laboratory of Integrated Service Networks, Xidian University

⁰