检索结果-内蒙古大学图书馆

A Degeneracy-Aware LiDAR-Inertial-Visual SLAM for Degenerate Environments

IEEE Sensors Journal 2025年第11期25卷 19376-19385页

作者： Zhu, Hongwei Zhang, Guobao Huang, Yongming Southeast University School of Automation Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing210096 China

Different sensors may experience degeneracy in specific scenarios, which can lead to failures in multi-sensor fusion optimization. To address the challenges of localization and mapping under such degeneracy conditions, this paper proposes a LiDAR-Inertial-Visual SLAM system with integrated degeneracy awareness. In the frontend, the system utilizes the ESIKF for tracking and incorporates a sensor degeneracy detection method to ensure that degraded sensor data do not affect the state error update. In the backend, we replace the conventional point cloud map with an adaptive voxel map to accelerate the retrieval of planar point cloud, and merge LiDAR planar features within a sliding window via region growing algorithm. Furthermore, the point-to-plane distance formula is optimized via the Rayleigh quotient theorem, which reduces the dimensionality of the optimization variables and simplifies the optimization process. Finally, we evaluate the proposed system on several challenging datasets and compare it with various state-of-the-art sensor fusion systems. The experimental results demonstrate that the proposed system achieves high localization accuracy in the majority of challenging scenarios. © 2001-2012 IEEE.

关键词： Inertial navigation systems

来源：评论

学校读者我要写书评

暂无评论

End-to-end multi-task reinforcement learning-based UAV swarm communication attack detection and area coverage

引用

Knowledge-Based systems 2025年 316卷

作者： Yu, Jin Zhang, Ya Sun, Changyin School of Automation Southeast University Nanjing210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing China

This paper proposes an innovative end-to-end multi-task reinforcement learning framework designed to enhance the security and operational stability of UAVs in complex communication attacks environments. In scenarios involving multiple UAV coverage, the framework classifies attack types and predicts UAV behaviors, which enables rapid response and compromised data recovery. First, a spatiotemporal attention mechanism is employed to strengthen the network by capturing temporal dependencies in the communication data and improving the recognition of hybird attack mode, thereby facilitating the integration of detection and repair. Second, the causal inference mechanism introduced in this study extracts true causal relationships from interference, which ensures the accuracy and stability of action predictions for area coverage under attack conditions. Finally, the entire process is modeled as a multi-task Markov decision process, optimizing overall decision-making efficiency. Additionally, the dynamic pheromone induction mechanism is proposed to realize the adaptive regional cooperative coverage of multiple UAVs. The experimental results demonstrate that the proposed algorithm can effectively detect hybrid attacks and predict UAV actions, protecting the multi-UAV cooperative area coverage. © 2025

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Time-varying formation-containment control for heterogeneous multi-agent systems with communication and output delays via observer-based feedback protocol

引用

IEEE Transactions on Automation Science and engineering 2025年 22卷 15435-15448页

作者： Yang, Yi He, Yong China University of Geosciences School of Automation Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Ministry of Education Engineering Research Center of Intelligent Technology for Geo-Exploration Wuhan430074 China

In this article, the time-varying formation-containment control problem of heterogeneous multi-agent systems (MASs) with an observer-based state feedback protocol is studied, where both communication delays and output delays are taken into consideration. By introducing an augmented Lyapunov-Krasovskii functionals (LKFs) candidate and employing less conservative methods to estimate its derivative, an improved quasi-formation-containment criterion is derived. On this basis, some observers and controllers are designed to allow for a larger maximum upper bound (MUB) of time delays on the premise of guaranteeing the fulfillment of the time-varying formation of leaders and the bounded convergence of followers. The estimation of the MUB determines the allowable delay range for system stability under the designed observers and controllers. Moreover, a distributed algorithm is developed to calculate the MUB of time delays, the observer gains, and the controller gains. Finally, two simulation experiments are implemented to demonstrate the obtained results, which verify the superiority and practicability of the criterion and algorithm. © 2004-2012 IEEE.

关键词： State feedback

来源：评论

学校读者我要写书评

暂无评论

Short-term Load Forecasting with Transformer Based on Fusion CNN-BiGRU

IAENG International Journal of Computer Science

引用

IAENG International Journal of Computer Science 2025年第5期52卷 1344-1364页

作者： Xie, Tao Xiao, Zhongchuang He, Xiaojun Fan, Yinchun Chongqing Key Laboratory of Complex Systems and Bionic Control Chongqing University of Posts and Telecommunications Chongqing400065 China Chongqing Key Laboratory of Complex Systems and Bionic Control Chongqing University of Posts and Telecommunications Chongqing400065 China Chongqing Jiaotong University's School of Electromechanical and Vehicle Engineering Chongqing400065 China SINOPEC Sales Co Ltd's Chongqing EJI branch Chongqing400065 China

To improve the accuracy of short-term power load forecasting, a short-term power load forecasting method based on Transformer with fused CNN-BiGRU is proposed. First, the best input data sequence is selected using the Partial Autocorrelation Function (PACF). Next, the importance scores and rankings of the feature data are obtained through the gradient boosting tree algorithm of CatBoost, and the optimal input features are selected. Then, the feature data and load data are combined. Finally, the combined data is used as input for the Transformer fused with CNN-BiGRU. In model training and forecasting, a hybrid forecasting strategy is employed, incorporating elements of multi-step forecasting into single-step forecasting. For the data of each moment, personalized and independent model training is performed, along with forecasting that include hybrid elements. The model replaces the original word embedding and position encoding components of Transformer. It uses CNN-BiGRU to extract high-dimensional feature representations of latent feature information and relative positional information from the input data. The proposed model demonstrates higher forecasting accuracy through validation on two different datasets and comparison with other forecasting models. Additionally, two ablation experiments are conducted. Through systematic ablation experiments, we demonstrate that modifications to the Transformer input layer significantly improve model performance in time series tasks. These results validate the rationality and effectiveness of the proposed approach. The ablation experiments on the method of PACF selecting the optimal input data sequence and CatBoost filtering the optimal input feature data, as well as the hybrid forecasting strategy, further verify the effectiveness and rationality of the data selection methods and forecasting strategies used in this study for short-term power load forecasting. Moreover, to eliminate the zigzagging jitter phenomenon in the foreca

关键词： CatBoost hybrid forecasting strategy PACF Transformer fuses CNN-BiGRU

来源：评论

学校读者我要写书评

暂无评论

Data-driven finite-time adaptive attitude tracking control for spacecraft

引用

Advances in Space Research 2025年第12期75卷 8780-8791页

作者： Wang, Jianhui He, Guangping Bian, Guibin Geng, Shixiong College of Mechanical & Energy Engineering Beijing University Of Technology Beijing100124 China Department of Mechanical and Electrical Engineering North China University of Technology Beijing100144 China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China

This paper proposes a novel data-driven finite-time adaptive control method for the spacecraft attitude tracking control problem with inertial uncertainty. Based on the dynamic regression extension technique, the disturbance unit matrix is introduced, and the parameter estimation law in the form of algebraic equations is presented, which realizes the arbitrarily small convergence of parameter estimation error. The convergence of parameter estimation errors is verified through stability analysis. Globally non-singular fast terminal sliding mode control is designed to achieve finite-time arrival of the sliding surface and convergence of the system state error. The stability analysis of the closed-loop system demonstrates the effectiveness of the proposed method. Furthermore, the effectiveness and superiority of the proposed method are verified through numerical simulations of spacecraft attitude tracking control. © 2025 COSPAR

关键词： Attitude control

来源：评论

学校读者我要写书评

暂无评论

Context-Aided Semantic-Aware Self-Alignment for Video-Based Person Re-Identification

引用

IEEE Transactions on Circuits and systems for Video Technology 2025年

作者： Ran, Zhidan Xiao, Zhiyao Lu, Xiaobo Wei, Xuan Liu, Wei Southeast University School of Automation Nanjing210096 China Ministry of Education Key Laboratory of Measurement and Control of Complex Systems of Engineering Nanjing210096 China

Video-based person re-identification (Re-ID) aims at associating the video sequences of the identical person across multiple cameras. The ubiquitous appearance misalignment poses a major obstacle for video person Re-ID. Existing alignment-based methods generally rely on off-the-shelf semantic parsing models to locate visible human parts, which ignore identifiable personal belongings and cannot handle various interferences (e.g., pedestrian detection errors and occlusions) in video clips. In this work, we propose a novel framework termed Context-Aided Semantic-Aware Self-Alignment (CSSA) for video-based person Re-ID. First, we propose to jointly learn pixel-level part-aligned representations and semantic-aligned global-level representations in an end-to-end manner. Unlike most existing approaches that depend on prior information in terms of pose for part estimation, CSSA can locate different body parts and achieve the pixel-level semantic alignment without extra human topology semantics. Second, a Context-Aided Region Enhancement (CARE) module is proposed to efficiently highlight macro-visual patterns associated with the target pedestrian and suppress noise caused by factors like background clutters and occlusions. Third, we propose a Semantic-Aware Global Feature Alignment (SGFA) method for generating pair-wise semantic-aligned global representations, which play an essential role in both the training and inference phases. Extensive experimental results on multiple challenging benchmarks indicate the superiority and effectiveness of the proposed CSSA. © 1991-2012 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Rethinking iterative stereo matching from a diffusion bridge model perspective

引用

Pattern Recognition 2025年 167卷

作者： Shi, Yuguang Zhou, Sifan Wang, Wei Lu, Xiaobo School of Automation Southeast University Nanjing210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing210096 China

Stereo matching is vital for 3D perception in vision and robotics. Although iteration-based stereo matching has demonstrated competitive performance, it also has inherent limitations, such as the discrete nature of the iteration process, which can lose geometric structure information, and the dependence on a large number of iterations. In this paper, we present a novel iterative-based framework, named Diffusion Models for Iterative Optimization (DMIO). DMIO introduces a Time-based Update Network (T-UN) that embeds time encoding into sub-modules within the update network. This approach correlates temporal and disparity outputs and effectively integrates diffusion models into the iterative framework. This design enables DMIO to allow features containing fine details to be transmitted during the update process and can be seamlessly embedded into most iterative methods. We further design a Motion Agent Attention (MAA) module in the update network, which generates a set of attention weights for the local cost volume to filter redundant information. In addition, we introduce channel attention into the context network, which can generate more expressive features to improve accuracy. Experiments on several public benchmarks for stereo matching show that DMIO achieves over an 8.5% improvement over competing method and requires only 8 iterations to achieve state-of-the-art performance. © 2025 Elsevier Ltd

关键词： Stereo image processing

来源：评论

学校读者我要写书评

暂无评论

Silicon Optical Filter With Widely Tunable Bandwidth Driving by Intelligent Algorithms

引用

Journal of Lightwave Technology 2025年第11期43卷 5358-5365页

作者： Duan, Jiazhu Liu, Cangli Zhang, Dayong Zhao, Xiangjie Liu, Li China Academy of Engineering Physics Institute of Fluid Physics Mianyang621900 China China Academy of Engineering Physics Mianyang621900 China China University of Geosciences School of Automation Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China

Capitalizing two silicon rings assisted a Mach-Zehnder interferometer (MZI) structure, we propose and demonstrate picometer narrowband optical filters featuring widely tunable bandwidths, high extinction ratios and low in-band ripples. By tuning the bandwidth of any ring or the resonance offset between the two rings, the filter bandwidth could be flexibly manipulated. Notably, by controlling the phase of the two rings and the MZI structures, the extinction ratios and shape factors of the filter could be commendably improved. It is worth mentioning that a genetic algorithm is employed to efficiently manipulate the various heaters on the optical filter, enabling the attainment of desired target filtering waveforms. Experimental results demonstrate the filter capability to widely adjust its 3dB-bandwidth while maintaining high extinction ratios, low in-band ripples and favorable shape factors. To the best of our knowledge, it is a record bandwidth tuning range among the algorithm-driven pm-narrowband optical filters. With the dominant advantages and high performance, the proposed optical filters are competent to dynamically process the on-chip narrowband signals. © 1983-2012 IEEE.

关键词： Mach-Zehnder interferometers

来源：评论

学校读者我要写书评

暂无评论

Haptic-Aided Navigation Vehicle: Enhancing Obstacle Detection in Blind Spots and Transparent Object Scenarios

引用

Journal of Shanghai Jiaotong University (Science) 2025年 1-9页

作者： Li, Mingwang Li, Xinde Zhang, Zhentong Zhang, Zeyu Zhao, Haoming School of Software Southeast University Suzhou Jiangsu215000 China School of Automation Southeast University Nanjing210018 China School of Cyber Science and Engineering Southeast University Nanjing211102 China Key Laboratory of Measurement and Control of Complex Systems of Engineering of Ministry of Education Nanjing214135 China Nanjing Center for Applied Mathematics Nanjing211135 China Southeast University Shenzhen Research Institute Shenzhen Guangdong518063 China

As autonomous mobile robots are increasingly deployed in complex environments, traditional vision sensors and LiDAR encounter considerable limitations, particularly in detecting obstacles in blind spots or transparent objects. To address the issue of blind spots, we design a specialized haptic sensing structure and develop the haptic-aided navigation vehicle (HANV). This system integrates haptic sensors and LiDAR to deliver comprehensive perception, significantly enhancing close-range obstacle detection in areas that are typically beyond the range of conventional sensors. To tackle the challenge of transparent obstacles, which are often undetected by both vision and LiDAR sensors, we employ a fusion of haptic sensors and LiDAR. The haptic system provides physical contact feedback, ensuring reliable detection of transparent obstacles such as glass, while LiDAR offers long-range sensing capabilities. This combination enables HANV to navigate effectively in environments with transparent obstacles, overcoming the limitations of traditional sensing systems. Experiment results indicate that the proposed haptic and LiDAR integration substantially improves obstacle detection in both blind spots and environments with transparent obstacles. HANV achieves high success rates, minimal collisions, and efficient obstacle avoidance, particularly excelling in complex, confined spaces where conventional systems prove inadequate. These findings emphasize the efficacy of our approach in enhancing navigation performance in dynamic and challenging environments. (Figure presented.) © Shanghai Jiao Tong University 2025.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Building intelligence identification system via large language model watermarking: a survey and beyond

引用

Artificial Intelligence Review 2025年第8期58卷 1-58页

作者： Wang, Xuhong Jiang, Haoyu Yu, Yi Yu, Jingru Lin, Yilun Yi, Ping Wang, Yingchun Qiao, Yu Li, Li Wang, Fei-Yue Shanghai Artificial Intelligence Laboratory Shanghai200433 China School of Cyber Science and Engineering Shanghai Jiao Tong University Shanghai200240 China Department of Automation BNRist Tsinghua University Beijing100084 China The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China

Large Language Models (LLMs) are increasingly integrated into diverse industries, posing substantial security risks due to unauthorized replication and misuse. To mitigate these concerns, robust identification mechanisms are widely acknowledged as an effective strategy. Identification systems for LLMs now rely heavily on watermarking technology to manage and protect intellectual property and ensure data security. However, previous studies have primarily concentrated on the basic principles of algorithms and lacked a comprehensive analysis of watermarking theory and practice from the perspective of intelligent identification. To bridge this gap, firstly, we explore how a robust identity recognition system can be effectively implemented and managed within LLMs by various participants using watermarking technology. Secondly, we propose a mathematical framework based on mutual information theory, which systematizes the identification process to achieve more precise and customized watermarking. Additionally, we present a comprehensive evaluation of performance metrics for LLM watermarking, reflecting participant preferences and advancing discussions on its identification applications. Lastly, we outline the existing challenges in current watermarking technologies and theoretical frameworks, and provide directional guidance to address these challenges. Our systematic classification and detailed exposition aim to enhance the comparison and evaluation of various methods, fostering further research and development toward a transparent, secure, and equitable LLM ecosystem. © The Author(s) 2025.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：