Iet Radar Sonar and Navigation最新文献_第3页

XAI-Driven Resilient Image Classification in the Presence of Adversarial Perturbations 存在对抗性扰动的xai驱动的弹性图像分类

IF 1.4 4区管理学

Iet Radar Sonar and Navigation Pub Date : 2025-06-04 DOI: 10.1049/rsn2.70041

Amir Hosein Oveis, Elisa Giusti, Alessandro Cantelli-Forti, Marco Martorella

{"title":"XAI-Driven Resilient Image Classification in the Presence of Adversarial Perturbations","authors":"Amir Hosein Oveis, Elisa Giusti, Alessandro Cantelli-Forti, Marco Martorella","doi":"10.1049/rsn2.70041","DOIUrl":"https://doi.org/10.1049/rsn2.70041","url":null,"abstract":"Deep learning (DL) architectures, although being employed in widespread applications, often raise concerns about their trustworthiness due to their opacity in their decision-making processes. Explainable AI (XAI) emerges as a promising solution to mitigate these concerns by providing interpretable rationales for DL network outputs. In domains where risk tolerance is minimal, ensuring trustworthy predictions is essential. This study introduces expmax, a new classifier rooted in XAI principles, designed for multiclass classification problems using convolutional neural network (CNN) architectures. The key strength of expmax, compared to the conventional softmax, lies in its ability to evaluate the model's focus on salient features of targets rather than being distracted by unrelated patterns from the background. This characteristic allows expmax for increased resilience, especially in scenarios with adversarial samples, where conventional classifiers may fail to correctly recognise the target class. The methodology behind expmax is based on fitting a regressor with features that are extracted from the training dataset using the SHapley Additive exPlanations (SHAP) algorithm, along with a target mask area detection algorithm. By using the SHAP-based extracted features, expmax reduces vulnerabilities to perturbations introduced by adversarial inputs. The method is validated on the MTARSI dataset for aircraft recognition in remote sensing images.","PeriodicalId":50377,"journal":{"name":"Iet Radar Sonar and Navigation","volume":"19 1","pages":""},"PeriodicalIF":1.4,"publicationDate":"2025-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/rsn2.70041","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144206603","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Radar Anti-Jamming Performance Evaluation: A Novel Model Based on Measurement Error and RCS Distributions 雷达抗干扰性能评估：一种基于测量误差和RCS分布的新模型

IF 1.4 4区管理学

Iet Radar Sonar and Navigation Pub Date : 2025-05-30 DOI: 10.1049/rsn2.70038

Linqi Zhao, Liang Yan, Xiaojun Duan, Zhengming Wang, Yike Xiao

{"title":"Radar Anti-Jamming Performance Evaluation: A Novel Model Based on Measurement Error and RCS Distributions","authors":"Linqi Zhao, Liang Yan, Xiaojun Duan, Zhengming Wang, Yike Xiao","doi":"10.1049/rsn2.70038","DOIUrl":"https://doi.org/10.1049/rsn2.70038","url":null,"abstract":"The growing complexity of the electromagnetic environment makes accurate radar anti-jamming performance evaluation essential for assessing the effectiveness of electronic countermeasure systems. In jamming scenarios, smaller measurement errors in range indicate a radar's enhanced ability to counteract interference. This paper presents a novel approach to radar anti-jamming performance evaluation based on statistical models of radar cross-section (RCS) fluctuations. Assuming that the RCS follows one of several distributions—Swerling I–II, Swerling III–IV, or Rayleigh—we derive the corresponding distributions of radar parameter measurement errors. In our model, the measurement error is assumed to follow a conditional Gaussian distribution, with its standard deviation modelled as a random variable dependent on both the RCS and the signal-to-interference ratio (SIR). This formulation establishes a quantitative relationship between measurement error, SIR, and RCS, and enables derivation of the error's probability density function (PDF). Consequently, we obtain a novel expression for the radar anti-jamming rate. We compare this model to two conventional approaches: one that assumes a constant error variance across all target ranges and another that assumes a fixed variance that varies with target ranges but without incorporating distributional uncertainty. The proposed Error Distribution Estimation (EDE) model leverages the full probability distribution of measurement errors together with real-time parameter error data fusion. This integration provides a more continuous and nuanced evaluation of radar anti-jamming performance, potentially leading to more reliable assessments under a range of operating conditions.","PeriodicalId":50377,"journal":{"name":"Iet Radar Sonar and Navigation","volume":"19 1","pages":""},"PeriodicalIF":1.4,"publicationDate":"2025-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/rsn2.70038","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144171844","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Software-Defined Sonar for Unmanned Underwater System 无人水下系统软件定义声纳

IF 1.4 4区管理学

Iet Radar Sonar and Navigation Pub Date : 2025-05-27 DOI: 10.1049/rsn2.70037

Hongkun Zhou, Xiyun Ge, Ningyang Wei, Yuhang Gao, Xinyu Liu

引用次数: 0

Sparse Array Design Based on the Combination of Improved Binary Grey Wolf Optimisation and Genetic Algorithm 基于改进二值灰狼优化与遗传算法相结合的稀疏阵列设计

IF 1.4 4区管理学

Iet Radar Sonar and Navigation Pub Date : 2025-05-22 DOI: 10.1049/rsn2.70028

Weinian Li, Lichun Li, Hongyi Pan, Chaoyue Song, Siyao Tian

{"title":"Sparse Array Design Based on the Combination of Improved Binary Grey Wolf Optimisation and Genetic Algorithm","authors":"Weinian Li, Lichun Li, Hongyi Pan, Chaoyue Song, Siyao Tian","doi":"10.1049/rsn2.70028","DOIUrl":"https://doi.org/10.1049/rsn2.70028","url":null,"abstract":"Traditional adaptive beamforming techniques focus solely on optimising the excitation weights of array elements while neglecting the critical influence of element positioning on beamforming performance. To enhance array degrees of freedom and achieve superior beamforming capabilities, this paper proposes a novel joint optimisation method that simultaneously adjusts both element positions and excitation coefficients, targeting maximum output signal-to-interference-plus-noise ratio (MaxSINR). Under the minimum variance distortionless response (MVDR) framework, we derive and analyse the theoretical relationship between output SINR and array configuration. We reformulate the sparse array design as a binary integer optimisation problem by introducing a position selection vector. The solution is efficiently obtained through our enhanced hybrid algorithm, which combines improved binary grey wolf optimisation with genetic algorithm (IBGWO-GA). Compared with the traditional beamforming method, the proposed algorithm can effectively improve the degree of freedom of the array position and realise interference suppression under underdetermined conditions. The optimal design of sparse linear array and sparse planar array in simulation experiments verifies the effectiveness of the proposed method.","PeriodicalId":50377,"journal":{"name":"Iet Radar Sonar and Navigation","volume":"19 1","pages":""},"PeriodicalIF":1.4,"publicationDate":"2025-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/rsn2.70028","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144118221","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Study on the Influence of Space–Time Adaptive Processor on Single Point Position and Real-Time Kinematic for GNSS Antenna Array Anti-jamming Receiver 时空自适应处理器对GNSS天线阵抗干扰接收机单点位置和实时运动学影响的研究

IF 1.4 4区管理学

Iet Radar Sonar and Navigation Pub Date : 2025-05-21 DOI: 10.1049/rsn2.70035

Yaoding Wang, Xiaozhou Ye, Si Chen, Zhenxin Liu

{"title":"Study on the Influence of Space–Time Adaptive Processor on Single Point Position and Real-Time Kinematic for GNSS Antenna Array Anti-jamming Receiver","authors":"Yaoding Wang, Xiaozhou Ye, Si Chen, Zhenxin Liu","doi":"10.1049/rsn2.70035","DOIUrl":"https://doi.org/10.1049/rsn2.70035","url":null,"abstract":"Space-time adaptive processor (STAP) has been widely used in the GNSS antenna array anti-jamming receiver. The cost of STAP algorithms, including the minimum variance distortion-less response (MVDR) algorithm and power inversion (PI) algorithm, is introducing measurement errors. However, there is no systematic answer to the principle of error introduction, the magnitude of error and its influence on single point position (SPP) and real-time kinematic (RTK). We have conducted a systematic study on the above-mentioned issues. Firstly, the principle of error introduction was theoretically studied. Then, a large number of simulations were conducted to evaluate the magnitude of the error. Finally, simulated errors are introduced into the B1I and B3I real measurements to implement SPP and RTK to evaluate the influence of the STAP algorithms on SPP and RTK. Results show that for SPP, the influence of STAP algorithms on the B1I + B3I dual-frequency ionosphere-free combination SPP is larger than that on the B1I single-frequency SPP; for RTK, the influence of STAP algorithms on the B1I + B3I dual-frequency uncombined RTK is smaller than that on the B1I single-frequency RTK. In addition, the influences of the MVDR algorithm on SPP and RTK are smaller than those of the PI algorithm.","PeriodicalId":50377,"journal":{"name":"Iet Radar Sonar and Navigation","volume":"19 1","pages":""},"PeriodicalIF":1.4,"publicationDate":"2025-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/rsn2.70035","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144100894","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Robust Multi-Agent Reinforcement Learning Against Adversarial Attacks for Cooperative Self-Driving Vehicles 针对协作式自动驾驶车辆对抗攻击的鲁棒多智能体强化学习

IF 1.4 4区管理学

Iet Radar Sonar and Navigation Pub Date : 2025-05-19 DOI: 10.1049/rsn2.70033

Chuyao Wang, Ziwei Wang, Nabil Aouf

{"title":"Robust Multi-Agent Reinforcement Learning Against Adversarial Attacks for Cooperative Self-Driving Vehicles","authors":"Chuyao Wang, Ziwei Wang, Nabil Aouf","doi":"10.1049/rsn2.70033","DOIUrl":"https://doi.org/10.1049/rsn2.70033","url":null,"abstract":"Multi-agent deep reinforcement learning (MARL) for self-driving vehicles aims to address the complex challenge of coordinating multiple autonomous agents in shared road environments. MARL creates a more stable system and improves vehicle performance in typical traffic scenarios compared to single-agent DRL systems. However, despite its sophisticated cooperative training, MARL remains vulnerable to unforeseen adversarial attacks. Perturbed observation states can lead one or more vehicles to make critical errors in decision-making, triggering chain reactions that often result in severe collisions and accidents. To ensure the safety and reliability of multi-agent autonomous driving systems, this paper proposes a robust constrained cooperative multi-agent reinforcement learning (R-CCMARL) algorithm for self-driving vehicles, enabling robust driving policy to handle strong and unpredictable adversarial attacks. Unlike most existing works, our R-CCMARL framework employs a universal policy for each agent, achieving a more practical, nontask-oriented driving agent for real-world applications. In this way, it enables us to integrate shared observations with Mean-Field theory to model interactions within the MARL system. A risk formulation and a risk estimation network are developed to minimise the defined long-term risks. To further enhance robustness, this risk estimator is then used to construct a constrained optimisation objective function with a regulariser to maximise long-term rewards in worst-case scenarios. Experiments conducted in the CARLA simulator in intersection scenarios demonstrate that our method remains robust against adversarial state perturbations while maintaining high performance, both with and without attacks.","PeriodicalId":50377,"journal":{"name":"Iet Radar Sonar and Navigation","volume":"19 1","pages":""},"PeriodicalIF":1.4,"publicationDate":"2025-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/rsn2.70033","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144091314","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Centralised Fusion of Cooperative Sensors With Limited Field of View for Multiple Resolvable Group Targets Tracking 有限视场协同传感器集中融合多分辨群目标跟踪

IF 1.4 4区管理学

Iet Radar Sonar and Navigation Pub Date : 2025-05-15 DOI: 10.1049/rsn2.70032

Xirui Xue, Jikun Ye, Daozhi Wei, Shucai Huang, Changxin Luo, Ning Li, Ruining Luo

{"title":"Centralised Fusion of Cooperative Sensors With Limited Field of View for Multiple Resolvable Group Targets Tracking","authors":"Xirui Xue, Jikun Ye, Daozhi Wei, Shucai Huang, Changxin Luo, Ning Li, Ruining Luo","doi":"10.1049/rsn2.70032","DOIUrl":"https://doi.org/10.1049/rsn2.70032","url":null,"abstract":"The coordinated deployment of multi-sensor systems significantly enhances group target detection capabilities, yet persistent tracking remains challenging due to inherent limitations in single-sensor field of view (FoV) coverage. This paper proposes a novel labelled multi-Bernoulli (LMB) filter for resolvable group target (RGT) tracking under the centralised fusion (CF) framework, abbreviated as the CF-LMB-RGT filter. The proposed method introduces the virtual leader kinematic model to capture intra-group motion constraints and incorporates group structure undirected graph into the LMB recursion for interaction prediction. A key innovation lies in the Kullback–Leibler divergence minimised fusion rule that optimally integrates local posteriors within joint FoV regions while explicitly modelling common FoV overlaps, enabling complementary information fusion across nonoverlapping sensor FoVs. Simulation results demonstrate that our method achieves impressive tracking accuracy for RGTs by integrating information from all sensors.","PeriodicalId":50377,"journal":{"name":"Iet Radar Sonar and Navigation","volume":"19 1","pages":""},"PeriodicalIF":1.4,"publicationDate":"2025-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/rsn2.70032","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144074264","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Fault Modes and Methods to Evaluate Integrity Risk for FastSLAM-Based Navigation 基于fastslam的导航系统故障模式及完整性风险评估方法

IF 1.4 4区管理学

Iet Radar Sonar and Navigation Pub Date : 2025-05-15 DOI: 10.1049/rsn2.70029

Pil Hun Choi, Gihun Nam, Dongchan Min, Noah Minchan Kim, Jiyun Lee

{"title":"Fault Modes and Methods to Evaluate Integrity Risk for FastSLAM-Based Navigation","authors":"Pil Hun Choi, Gihun Nam, Dongchan Min, Noah Minchan Kim, Jiyun Lee","doi":"10.1049/rsn2.70029","DOIUrl":"https://doi.org/10.1049/rsn2.70029","url":null,"abstract":"The fast simultaneous localisation and mapping (FastSLAM), utilising the Rao-Blackwellised particle filter, provides a robust navigation solution in urban environments. Ensuring the integrity of FastSLAM is critical for the safety of autonomous driving applications. Our previous work proposed an empirical integrity risk evaluation method for nominal conditions and a probabilistic bound using PAC (probably approximately correct)–Bayesian theory. However, it was limited by overly conservative risk estimates and a lack of consideration for fault conditions. This study introduces a refined integrity evaluation framework with three main contributions. First, a modified weighting and resampling technique is proposed to reduce conservatism in empirical risk without compromising estimation accuracy. Second, a fault monitoring method is introduced to detect and isolate control input faults during the dynamic update step. Third, a conservative integrity risk evaluation approach is developed for FastSLAM to account for data association faults using probabilistic modelling. Simulation results show that the proposed methods significantly improve integrity performance under both nominal and faulted scenarios.","PeriodicalId":50377,"journal":{"name":"Iet Radar Sonar and Navigation","volume":"19 1","pages":""},"PeriodicalIF":1.4,"publicationDate":"2025-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/rsn2.70029","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144074263","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Statistical Analysis of Performance of Optimisation-Based SAR Autofocus 基于优化的SAR自动对焦性能统计分析

IF 1.4 4区管理学

Iet Radar Sonar and Navigation Pub Date : 2025-05-10 DOI: 10.1049/rsn2.70030

Patrick Haughey, Mikhail Gilman, Semyon Tsynkov

{"title":"Statistical Analysis of Performance of Optimisation-Based SAR Autofocus","authors":"Patrick Haughey, Mikhail Gilman, Semyon Tsynkov","doi":"10.1049/rsn2.70030","DOIUrl":"https://doi.org/10.1049/rsn2.70030","url":null,"abstract":"Transionospheric SAR autofocus is a variational algorithm designed to circumvent the deficiencies of conventional autofocus techniques in correcting the distortions of spaceborne SAR images due to ionospheric turbulence. It has demonstrated superior performance in a variety of computer-simulated imaging scenarios. In the current work, we conduct a systematic statistical analysis of transionospheric SAR autofocus aimed at corroborating its robustness and identifying limitations and sensitivities across a broad range of factors that affect the autofocus performance. We employ the range-compressed domain representation where the target reflectivity, antenna signal, and the phase screen depend only on the azimuthal coordinate. The three main factors included in the study are the levels of turbulent perturbations, clutter, and noise. We use the normalised cross correlation (NCC), integrated sidelobe ratio (ISLR), and peak desynchronisation (PD) as a-posteriori performance metrics. A key objective of the current analysis, beyond assessing the autofocus performance, is to identify the directions of how to further improve the algorithm, in terms of both the quality of focusing and associated computational cost.","PeriodicalId":50377,"journal":{"name":"Iet Radar Sonar and Navigation","volume":"19 1","pages":""},"PeriodicalIF":1.4,"publicationDate":"2025-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/rsn2.70030","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143932352","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Joint Optimal Allocation of Resources for Multiple Jammer Based on Multi-Agent Deep Reinforcement Learning 基于多智能体深度强化学习的多干扰机联合资源优化分配

IF 1.4 4区管理学

Iet Radar Sonar and Navigation Pub Date : 2025-05-04 DOI: 10.1049/rsn2.70031

Jieling Wang, Yanfei Liu, Chao Li, Zhong Wang, Yali Li

{"title":"Joint Optimal Allocation of Resources for Multiple Jammer Based on Multi-Agent Deep Reinforcement Learning","authors":"Jieling Wang, Yanfei Liu, Chao Li, Zhong Wang, Yali Li","doi":"10.1049/rsn2.70031","DOIUrl":"https://doi.org/10.1049/rsn2.70031","url":null,"abstract":"In response to the complex scenario where multiple jammers navigate through a netted radar system (NRS), this study presents an optimised allocation algorithm for cooperative jamming resources, namely the Multi-Agent Jamming Resource Allocation (MJCJRA) algorithm, which is based on multi-agent deep reinforcement learning. Initially, the research develops a target fusion detection probability function and a global performance index optimisation function, which are tailored to the specific jamming and radar detection models of the scenario. Subsequently, the multiple jammers are mapped into a multi-agent system with a greedy strategy employed to generate targeted rewards for the jamming agents, enhancing their learning efficiency and performance. The study culminates in the design of evaluation and mixed-strategy networks for the jamming agents. It utilises an exponential mean shift method for soft updates of the target network, adopts priority experience replay and importance sampling methods, and incorporates reward centring into the loss function for network updates. Experimental findings demonstrate that MJCJRA algorithm significantly surpasses the baseline method, the particle swarm optimisation (PSO), the snow ablation optimiser (SAO), the multi-agent deep deterministic policy gradient (MADDPG) and multi-agent proximal policy optimisation (MAPPO), effectively diminishing the detection capability of NRS.","PeriodicalId":50377,"journal":{"name":"Iet Radar Sonar and Navigation","volume":"19 1","pages":""},"PeriodicalIF":1.4,"publicationDate":"2025-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/rsn2.70031","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143905140","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0