IEEE transactions on artificial intelligence最新文献_第7页

Complex AFNet: A Hybrid Complex-Valued Deep Network for Atrial Fibrillation Detection 复杂AFNet：一种用于房颤检测的混合复杂值深度网络

IEEE transactions on artificial intelligence Pub Date : 2026-09-01 Epub Date: 2026-03-06 DOI: 10.1109/TAI.2026.3671218

P S Pritish Kumar Mahali;Diptiman Mohanta;Tushar Sandhan

{"title":"Complex AFNet: A Hybrid Complex-Valued Deep Network for Atrial Fibrillation Detection","authors":"P S Pritish Kumar Mahali;Diptiman Mohanta;Tushar Sandhan","doi":"10.1109/TAI.2026.3671218","DOIUrl":"https://doi.org/10.1109/TAI.2026.3671218","url":null,"abstract":"Atrial fibrillation (AF) is the most common sustained cardiac arrhythmia, affecting nearly 59 million individuals worldwide by 2019 and significantly increasing stroke risk. This work presents a novel hybrid complex convolutional network for automated AF detection using Gramian angular field (GAF) transformations of electrocardiogram (ECG) signals. The proposed method converts 1-D ECG segments into 2-D image representations through Gramian angular summation field (GASF) and Gramian angular difference field (GADF) transformations, preserving temporal dependencies as geometric relationships in polar coordinates. Our proposed model treats GASF and GADF as real and imaginary components of complex-valued inputs, enabling phase-aware feature extraction through the proposed hybrid architecture combining real-valued and complex-valued convolutional layers. The network incorporates complex convolutions, modified rectified linear unit (ReLU) activations, and residual connections to capture subtle magnitude-phase interactions critical for detecting AF episodes. Evaluated on the PhysioNet AF dataset containing 1436 ECG recordings, this model achieves superior performance with 95.63% test accuracy, 96.43% precision, 92.05% recall, and 94.15% F1-score, outperforming state-of-the-art models by +1.52% accuracy and +2.1% F1-score. Interpretability analysis using Grad-CAM and integrated gradients (IGs) reveals class-specific attention patterns, with the model focusing on GADF for normal rhythm detection and GASF for AF classification, demonstrating clinically relevant pattern recognition capabilities of our model. To facilitate reproducibility and further research, the implementation of the proposed C-AFNet and the associated preprocessing and evaluation scripts are publicly available at this <ext-link>link</ext-link>.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"7 9","pages":"4868-4879"},"PeriodicalIF":0.0,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148859716","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Dynamic Reinforcement Learning Control for Fractional-Order Neural Networks With Higher Order Interactions and Multiple Time Delays 具有高阶交互和多时滞的分数阶神经网络的动态强化学习控制

IEEE transactions on artificial intelligence Pub Date : 2026-09-01 Epub Date: 2026-03-13 DOI: 10.1109/TAI.2026.3673682

Hua Li;Min Xiao;Chengdai Huang;Qingxiang Fang;Xia Huang;Wenwu Yu;Yi Yao;Tingwen Huang;Leszek Rutkowski

{"title":"Dynamic Reinforcement Learning Control for Fractional-Order Neural Networks With Higher Order Interactions and Multiple Time Delays","authors":"Hua Li;Min Xiao;Chengdai Huang;Qingxiang Fang;Xia Huang;Wenwu Yu;Yi Yao;Tingwen Huang;Leszek Rutkowski","doi":"10.1109/TAI.2026.3673682","DOIUrl":"https://doi.org/10.1109/TAI.2026.3673682","url":null,"abstract":"Conventional neural networks’ reliance on pairwise connections limits their ability to model the modular higher order interactions inherent in biological neural systems. The stability analysis and control of large-scale networks that integrate these higher order interactions with fractional-order dynamics and multiple time delays present a significant challenge due to analytical intractability. This study establishes a theoretical and computational framework for a large-scale fractional-order neural network model featuring modular triplet clusters. Analytical criteria for stability and Hopf bifurcation are derived. To address the control challenge, a reinforcement learning (RL) framework is implemented for the adaptive tuning of higher order coupling strength to suppress destabilizing oscillations. Numerical results quantify the profound impact of system parameters on stability while demonstrating the RL controller’s ability to maintain stability where traditional methods fail. By adaptively tuning the coupling strength without any prior knowledge of the system model, the proposed approach effectively suppresses oscillations, showcasing a advantage over model-based controllers for such high-dimensional, analytically intractable systems.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"7 9","pages":"4933-4949"},"PeriodicalIF":0.0,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148859720","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

TrustTiny-HAR: Selective, Open-Set, and Calibrated Activity Recognition on Microcontrollers TrustTiny-HAR：微控制器上的选择性，开集和校准活动识别

IEEE transactions on artificial intelligence Pub Date : 2026-09-01 Epub Date: 2026-03-23 DOI: 10.1109/TAI.2026.3676723

Ismail Lamaakal;Chaymae Yahyati;Yassine Maleh;Khalid El Makkaoui;Ibrahim Ouahbi

{"title":"TrustTiny-HAR: Selective, Open-Set, and Calibrated Activity Recognition on Microcontrollers","authors":"Ismail Lamaakal;Chaymae Yahyati;Yassine Maleh;Khalid El Makkaoui;Ibrahim Ouahbi","doi":"10.1109/TAI.2026.3676723","DOIUrl":"https://doi.org/10.1109/TAI.2026.3676723","url":null,"abstract":"Human activity recognition (HAR) increasingly executes on microcontrollers to satisfy privacy, latency, and energy constraints, yet most deployed TinyML models remain closed set and overconfident when faced with unseen behaviors, placement shifts, or sensor anomalies. We present <italic>TrustTiny-HAR</i>, a resource-efficient pipeline that unifies an int8 time-series backbone with a distilled trust head and a lightweight streaming conformal layer. The unified head produces calibrated class probabilities and a compact out-of-distribution (OOD) surrogate score learned from teacher signals (energy of logits and prototype/Mahalanobis distance), while the conformal layer maintains tiny on-device quantiles to enforce coverage-controlled acceptance thresholds. When evidence is insufficient, the device abstains and may optionally escalate using a 32-D–64-D feature sketch, avoiding raw-signal transmission. Evaluated under leave-one-subject-out protocols on UCI HAR, PAMAP2, and WISDM with multiple OOD stressors (unseen classes, placement shift, injected anomalies), TrustTiny-HAR matches strong int8 baselines on in-distribution macro-F1 (e.g., 93.8 on UCI HAR) while substantially improving calibration (ECE 2.4%) and OOD robustness (AUROC 0.96 for unseen, FPR@95 0.22 for placement shift). As a selective classifier, it attains the desired 90% coverage with conservative risk (e.g., 6.1%) from a buffer of only 128–512 windows. System profiling on nRF52840/STM32L4 shows <inline-formula><tex-math>$lt10%$</tex-math></inline-formula> energy overhead compared with a TinyCNN baseline, with tight RAM/Flash budgets preserved. The result is a practical template for trustworthy, on-device HAR that knows when <italic>not</i> to guess.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"7 9","pages":"5004-5017"},"PeriodicalIF":0.0,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148859725","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Dual Attention Multi-Instance Learning for Identifying Autism Spectrum Disorder Using Resting-State fMRI 基于静息状态功能磁共振成像的双注意多实例学习识别自闭症谱系障碍

IEEE transactions on artificial intelligence Pub Date : 2026-09-01 Epub Date: 2026-03-09 DOI: 10.1109/TAI.2026.3669876

S. Qasim Abbas;Lianhua Chi;Feng Xia;Noorul Amin;Yi-Ping Phoebe Chen

{"title":"Dual Attention Multi-Instance Learning for Identifying Autism Spectrum Disorder Using Resting-State fMRI","authors":"S. Qasim Abbas;Lianhua Chi;Feng Xia;Noorul Amin;Yi-Ping Phoebe Chen","doi":"10.1109/TAI.2026.3669876","DOIUrl":"https://doi.org/10.1109/TAI.2026.3669876","url":null,"abstract":"Deep learning has been widely studied to develop computer-aided diagnosis methods for autism spectrum disorder (ASD) due to abnormalities in functional connectivity (FC) caused by neural activations. However, FC dysconnectivity occurs in limited regions of the brain, and the intricacy of large datasets for aggrandizing generalizability and variability is also responsible for an increase in heterogeneities. Thus, the crucial challenge for a classification framework is to identify and consolidate the distinctive features that can elevate the class separation. To resolve this predicament, we propose a dual attention multi-instance learning framework (DAMILF) for the diagnosis of ASD and its subtypes. The DAMILF comprises four modules: 1) identification of specific regions in functional magnetic resonance imaging (fMRI); 2) patch-level attention subnetwork for extracting and strengthening patch-based localized discriminatory features; 3) attention-aware feature map for balancing the corresponding share of each patch and generating a global feature space for the whole brain; and 4) subject-level subnetwork for supplementary whole brain global feature learning and ASD-related label prediction. Our proposed DAMILF was evaluated on large-scale baseline fMRI data collected from <inline-formula><tex-math>$408$</tex-math></inline-formula> ASD and <inline-formula><tex-math>$476$</tex-math></inline-formula> typical control subjects from the autism brain imaging data exchange (ABIDE-1) repository, and exhibited superior diagnosis performance and a better generalization ability compared with several state-of-the-art methodologies.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"7 9","pages":"4837-4852"},"PeriodicalIF":0.0,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148859727","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Improving Neural Architecture Search by Minimizing Worst-Case Validation Loss 最小化最坏情况验证损失改进神经结构搜索

IEEE transactions on artificial intelligence Pub Date : 2026-09-01 Epub Date: 2026-03-05 DOI: 10.1109/TAI.2026.3670777

Haochen Zhang;Xuefeng Du;Ruisi Zhang;Pengtao Xie

引用次数: 0

Infinite Gaussian Mixture Autoencoder for Adaptive Deep Unsupervised Clustering 自适应深度无监督聚类的无限高斯混合自编码器

IEEE transactions on artificial intelligence Pub Date : 2026-09-01 Epub Date: 2026-03-24 DOI: 10.1109/TAI.2026.3677237

Ying Li;Junyu Xuan;Richard Yida Xu

{"title":"Infinite Gaussian Mixture Autoencoder for Adaptive Deep Unsupervised Clustering","authors":"Ying Li;Junyu Xuan;Richard Yida Xu","doi":"10.1109/TAI.2026.3677237","DOIUrl":"https://doi.org/10.1109/TAI.2026.3677237","url":null,"abstract":"Clustering is a fundamental task in machine learning and data mining. The success of deep learning, especially deep generative models, has given birth to the next generation of clustering—deep unsupervised clustering featured by the capability of clustering large-scale and high-dimensional data. One typical example is the Gaussian mixture variational autoencoder (GMVAE), where the prior of the latent variable is a mixture of Gaussian distributions (GMMs). However, the mixture number manually given in GMVAE greatly impacts on the final clustering performance and also limits the adaptation ability when new clusters come. To solve this issue, we propose an infinite Gaussian mixture autoencoder (IGMVAE), which replaces the plain Gaussian prior in VAE with an infinite Gaussian mixture distribution. Our method adaptively learns the number of mixtures from data, overcoming the manual setting limitation in GMVAE, and dynamically expands clusters for novel categories. Experimental results on three datasets show that our proposed IGMVAE achieves 5.5%–14.25% higher clustering accuracy compared to GMVAE. Moreover, our model is capable of generating high-quality data in a fully unsupervised manner.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"7 9","pages":"5033-5044"},"PeriodicalIF":0.0,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148859740","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Language-Enhanced Supervision-Reduced Analysis Framework for Multibranching Vessels 多分支血管的语言增强监督-减少分析框架

IEEE transactions on artificial intelligence Pub Date : 2026-09-01 Epub Date: 2026-04-07 DOI: 10.1109/TAI.2026.3681535

Xi-Yao Ma;Shi-Qi Liu;Xiao-Liang Xie;Xiao-Hu Zhou;Zeng-Guang Hou;Xin-Kai Qu;Wen-Zheng Han;Ming Wang;Meng Song;Chu-Tian Zhang

{"title":"A Language-Enhanced Supervision-Reduced Analysis Framework for Multibranching Vessels","authors":"Xi-Yao Ma;Shi-Qi Liu;Xiao-Liang Xie;Xiao-Hu Zhou;Zeng-Guang Hou;Xin-Kai Qu;Wen-Zheng Han;Ming Wang;Meng Song;Chu-Tian Zhang","doi":"10.1109/TAI.2026.3681535","DOIUrl":"https://doi.org/10.1109/TAI.2026.3681535","url":null,"abstract":"It is essential to quantitatively analyze coronary arterial angiography (CAG) images for coronary interventional procedures, as they are the gold reference standard for assessing stenosis. However, mainstream methods cannot extract different vascular branches precisely due to inadequate annotated data by experts and difficulty in uniformly defining vascular branches. To address the issue, this article presents a novel framework to analyze multibranching vessels with simple annotation, which localizes the endpoints of the vascular branches first, and then extracts corresponding vessel segments based on the endpoints. Considering it is challenging for current image-based methods to distinguish sparse vessel keypoints, we propose a cross-modal language-enhanced endpoint detection (LEED) network to achieve better performance by providing linguistic knowledge obtained from clinicians. A medical term corpus is established to convert conversation contents to standard texts. Furthermore, we devise a twin-stream vessel segmentation (TS-Seg) algorithm to segment various vascular branches based on gray-level features and detected endpoints. Besides, clinicians are allowed to manually add new endpoints and apply the TS-Seg algorithm alone to analyze any variant vascular branch that has not been defined before. Extensive experiments on two in-house and one public datasets consistently demonstrate the effectiveness and superiority of the proposed framework. Moreover, comprehensive vessel analysis reports are provided based on clinical prior knowledge to assist in preoperative surgery planning and postoperative treatment assessment, showing great potential to improve the efficiency and accuracy of clinical workflow.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"7 9","pages":"5199-5214"},"PeriodicalIF":0.0,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148859750","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

AICCE: AI-Driven Compliance Checker Engine AICCE：人工智能驱动的合规检查引擎

IEEE transactions on artificial intelligence Pub Date : 2026-09-01 Epub Date: 2026-04-10 DOI: 10.1109/TAI.2026.3682692

Mohammad Wali Ur Rahman;Martin Manuel Lopez;Lamia Tasnim Mim;Carter Farthing;Julius Battle;Kathryn Buckley;Salim Hariri

{"title":"AICCE: AI-Driven Compliance Checker Engine","authors":"Mohammad Wali Ur Rahman;Martin Manuel Lopez;Lamia Tasnim Mim;Carter Farthing;Julius Battle;Kathryn Buckley;Salim Hariri","doi":"10.1109/TAI.2026.3682692","DOIUrl":"https://doi.org/10.1109/TAI.2026.3682692","url":null,"abstract":"For digital infrastructure to be safe, compatible, and standards-aligned, automated communication protocol compliance verification is crucial. Nevertheless, current rule-based systems are becoming less and less effective since they are unable to identify subtle or intricate noncompliance, which attackers frequently use to establish covert communication channels in IPv6 traffic. To automate IPv6 compliance verification, this article presents the artificial intelligence-driven compliance checker engine (AICCE), a novel generative system that combines dual-architecture reasoning and retrieval-augmented generation (RAG). Specification segments pertinent to each query can be efficiently retrieved thanks to the semantic encoding of protocol standards into a high-dimensional vector space. Based on this framework, AICCE offers two complementary pipelines: 1) explainability mode, which uses parallel LLM agents to render decisions and settle disputes through organized discussions to improve interpretability and robustness; and 2) script execution mode, which converts clauses into Python rules that can be executed quickly for dataset-wide verification. With the debate mechanism enhancing decision reliability in complicated scenarios and the script-based pipeline lowering per-sample latency, AICCE achieves accuracy and F1-scores of up to 99% when tested on IPv6 packet samples across 16 cutting-edge generative models. By offering a scalable, auditable, and generalizable mechanism for identifying both routine and covert noncompliance in dynamic communication environments, our results show that AICCE overcomes limitations of conventional rule-based compliance checking systems.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"7 9","pages":"5239-5254"},"PeriodicalIF":0.0,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148859701","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

MSFASA-3DNet: Multi-Scale Feature Aggregation and Spatial Attention for 3-D Object Detection MSFASA-3DNet：三维目标检测的多尺度特征聚合和空间关注

IEEE transactions on artificial intelligence Pub Date : 2026-09-01 Epub Date: 2026-03-17 DOI: 10.1109/TAI.2026.3674873

Thurimerla Prasanth;Ram Prasad Padhy;B. Sivaselvan

{"title":"MSFASA-3DNet: Multi-Scale Feature Aggregation and Spatial Attention for 3-D Object Detection","authors":"Thurimerla Prasanth;Ram Prasad Padhy;B. Sivaselvan","doi":"10.1109/TAI.2026.3674873","DOIUrl":"https://doi.org/10.1109/TAI.2026.3674873","url":null,"abstract":"Perception is the most important component in autonomous vehicles (AVs) and robots. LiDAR-based 3-D object detection (3D-OD) provides accurate spatial information for precise object localization. Traditional image-based 3D-OD methods struggle with depth estimation, making them less reliable for 3-D scene understanding. The existing LiDAR-based model uses single or two-stage convolutional networks to perform 3D-OD tasks. The existing models are computationally expensive with complex backbones. We propose an enhanced backbone with multiscale feature extraction and spatial attention to improve LiDAR-based 3D-OD. Our backbone is computationally effective as we have reduced almost 40% of the parameters of existing backbones and achieved competitive accuracy compared to existing models. Multiscale feature extraction captures object details at different resolutions to provide fine and coarse features. Spatial attention concentrates on important regions and suppresses background noise to generate more accurate spatial detections. Our backbone integrates multiscale feature aggregation and spatial attention mechanisms to improve detection accuracy. Our model uses the standard single-stage and grid-based 3D-OD pipeline with our proposed backbone. We conducted extensive ablation experiments to validate our proposed backbone’s efficiency. Our model outperforms existing models by being lightweight, which makes it highly suitable for real-time applications. We evaluated our model using the KITTI benchmark. Our results are featured on the official leaderboard of KITTI.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"7 9","pages":"4950-4962"},"PeriodicalIF":0.0,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148859721","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Robustness-Guaranteed Reinforcement Learning Under Uncertainties in Dynamics Modeling and State Estimates 动态建模和状态估计中不确定性下的鲁棒保证强化学习

IEEE transactions on artificial intelligence Pub Date : 2026-09-01 Epub Date: 2026-03-20 DOI: 10.1109/TAI.2026.3675539

Duofeng Pan;Yongquan Huang;Rong Chen;Wenjie Lu;Manman Hu

{"title":"Robustness-Guaranteed Reinforcement Learning Under Uncertainties in Dynamics Modeling and State Estimates","authors":"Duofeng Pan;Yongquan Huang;Rong Chen;Wenjie Lu;Manman Hu","doi":"10.1109/TAI.2026.3675539","DOIUrl":"https://doi.org/10.1109/TAI.2026.3675539","url":null,"abstract":"Robust reinforcement learning enhances system robustness against uncertainties through bilevel optimization. However, the controller learned by reinforcement learning struggles to offer a strict robustness guarantee, limiting its reliability in real-world applications. This article presents robustness-guaranteed reinforcement learning framework under bounded uncertainties in dynamics modeling and state estimates. By describing the uncertainties and system dynamics models via ReLU neural networks, the states that most violate the proposed robustness conditions can be exactly found, and their robustness is prioritized during training. The solvability of the reinforcement learning problem is particularly studied, yielding a necessary condition that captures the adversarial relationship between control saturation and uncertainties. Subsequently, the attractive region can be prevalidated and the maximum robustness of the controller can be achieved by amplifying the uncertainties to a derived maximum extent in training. The proposed method has been fully evaluated in simulation and its advantages have been proven, including 3-D quadrotor reference trajectory tracking tasks.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"7 9","pages":"4977-4992"},"PeriodicalIF":0.0,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148859723","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0