检索结果-内蒙古大学图书馆

Conditional Diffusion Model for Skeleton-based Gesture Recognition with Severe Occlusions

IEEE Signal Processing Letters 2025年 32卷 1970-1974页

作者： Liu, Jinting Gan, Minggang Du, Yao Guan, keyi Guo, Jia Beijing Institute of Technology Key Laboratory of Complex System Intelligent Control and Decision School of Automation Beijing China

In the field of skeleton-based gesture recognition, occlusion remains a significant challenge, significantly degrading performance when key joints are occluded or disturbed. To tackle this issue, we propose DiffTrans, a practical conditional diffusion model for occlusion recognition, which enables skeleton-based gesture recognition under high occlusion by generating more likely samples. This study addresses the hand skeleton occlusion problem by framing it as a conditional denoising problem, where unoccluded data serve as observations and occluded data as repair targets. We employ a conditional diffusion model to impute the missing skeleton data and the DSTANet model, which is based on the transformer, to learn the skeleton feature representations. Research results show that the DiffTrans outperforms existing methods under various occlusion modes, maintaining high performance even in scenarios with a high missing rate. © 1994-2012 IEEE.

关键词： Musculoskeletal system

来源：评论

学校读者我要写书评

暂无评论

Model and Simulation of Multipath Error in DLL for GPS Receiver

引用

Chinese Journal of Electronics 2025年第3期23卷 508-515页

作者： Lan Cheng Jie Chen Gang Xie Taiyuan University of Technology Taiyuan China Education Ministry Key Laboratory of Complex System Intelligent Control and Decision Beijing Institute of Technology Beijing China

Although different multipath error models of Delay lock loop (DLL) used in GPS receiver are established, they have never been put together for comparison. Furthermore, no universal simulation method is developed to get a fair comparison among these models. A new model with implicate expression is hence proposed for the coherent DLL and the noncoherent Dot-product (DOT) power mode DLL. Meanwhile, a new simulation method based on the anonymous function in Matlab, which is especially suitable for models with implicit expression, is also proposed to compare the new model with the existing ones. The theoretical analysis and simulation results show that the existing models are the special case of the proposed one. The new simulation method can be used for the comparison of different multipath error models and the multipath error analysis of other DLLs for which only the implicit model is available.

关键词： Analytical models Tracking loops Codes Error analysis Simulation Receivers US Department of Transportation Mathematical models MATLAB Global Positioning system

来源：评论

学校读者我要写书评

暂无评论

Target extraction based on hybrid domain features of array GM-APD lidar 10

Target extraction based on hybrid domain features of array G...

引用

10th Symposium on Novel Optoelectronic Detection Technology and Applications

作者： Zhang, Xin Li, Sining Sun, Jianfeng Jiang, Peng Jin, Haowei National Key Laboratory of Laser Spatial Information Institute of Opto-Electronic Harbin Institute of Technology Heilongjiang Harbin150001 China Zhengzhou Research Institute of Harbin Institute of Technology Henan Zhengzhou450000 China National Key Laboratory of Complex System Control and Intelligent Agent Cooperation Beijing100074 China

ISBN: (数字)9781510688155

ISBN: (纸本)9781510688148

This study proposes a target extraction algorithm for array GM-APD lidar based on hybrid domain features, designed to address the challenges of accurately extracting target region based on the image in complex scenes and high noise interference. We extracted the temporal features of the echo signals and transformed the echo signals into the image domain to enhance the information content and further extract image features. By integrating multi-view K-means clustering and AdaBoost classification methods, we introduced a dynamic weight adjustment mechanism and a region adjustment method based on a correlation coefficient to achieve pixel-type discrimination and target region extraction. Experimental results demonstrate that the proposed method exhibits good robustness and adaptability in complex detection environments. Under conditions of different occlusion, different signal-to-noise ratios, and different target reflectivity, the proposed algorithm significantly outperforms traditional region-growing segmentation methods in terms of accuracy of target region extraction. © 2025 SPIE.

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

Multi-agent reinforcement learning system framework based on topological networks in Fourier space

引用

Applied Soft Computing 2025年 174卷

作者： Sun, Licheng Ding, Ao Ma, Hongbin School of Automation Beijing Institute of Technology Beijing100081 China Key Laboratory of Complex System Intelligent Control and Decision Beijing Institute of Technology Beijing100081 China

Currently, multi-agent reinforcement learning (MARL) has been applied to various domains such as communications, network management, power systems, and autonomous driving, showcasing broad application scenarios and significant research potential. However, in complex decision-making environments, agents that rely solely on temporal value functions often struggle to capture and extract hidden features and dependencies within long sequences in multi-agent settings. Each agent's decisions are influenced by a sequence of prior states and actions, leading to complex spatiotemporal dependencies that are challenging to analyze directly in the time domain. Addressing these challenges requires a paradigm shift to analyze such dependencies from a novel perspective. To this end, we propose a Multi-Agent Reinforcement Learning system framework based on Fourier Topological Space from the foundational level. This method involves transforming each agent's value function into the frequency domain for analysis. Additionally, we design a lightweight weight calculation method based on historical topological relationships in the Fourier topological space. This addresses issues of instability and poor reproducibility in attention weights, along with various other interpretability challenges. The effectiveness of this method is validated through experiments in complex environments such as the StarCraft Multi-Agent Challenge (SMAC) and Google Football. Furthermore, in the Non-monotonic Matrix Game, our method successfully overcame the limitations of non-monotonicity, further proving its wide applicability and superiority. On the application level, the proposed algorithm is also applicable to various multi-agent system domains, such as robotics and factory robotic arm control. The algorithm can control each joint in a coordinated manner to accomplish tasks such as enabling a robot to stand upright or controlling the movements of robotic arms. © 2025 Elsevier B.V.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Six-Degree-of-Freedom intelligent control of Hypersonic Flight Vehicle

引用

IEEE Transactions on Aerospace and Electronic systems 2025年

作者： An, Hao Wang, Yiming Zhong, Xinyu Ye, Yongfeng Harbin Institute of Technology Space Control and Inertial Technology Research Center National Key Laboratory of Complex System Control and Intelligent Agent Cooperation Harbin China

The six-degree-of-freedom control of hypersonic flight vehicle (HFV) faces great challenges due to complex aerodynamics, inherent couplings and multiple constraints. This paper investigates the six-degree-of-freedom guidance and attitude control problem for unpowered gliding HFV. The guidance loop is based on the predictor-corrector method with three improvements of intelligent prediction acceleration, path constraints accommodation and no-fly zones circumvention. To quickly respond to guidance commands, three attitude channels (i.e., roll, pitch and yaw) are completely decoupled by nonlinear dynamic inverse, based on which a high-performance low-complexity attitude controller is proposed. This benefits from the appropriate integration of barrier function and sliding mode control, while design conditions of three alternative performances (i.e., asymptotic, exponential and preset-time convergences) are discussed. Servo dynamics and physical constraints of aerodynamic control surfaces are also well handled. © 2025 IEEE.

关键词： Hypersonic vehicles

来源：评论

学校读者我要写书评

暂无评论

Fully Distributed Output Regulation of Linear Discrete-Time Multi-Agent systems With Markov Switching Topology

引用

IEEE Transactions on Circuits and systems I: Regular Papers 2025年 1-9页

作者： Liu, Jiamin Li, Zhao-Yan Zhou, Bin Jimei University School of Science Xiamen361021 China Harbin Institute of Technology School of Mathematics Harbin150001 China Zhengzhou Research Institute of HIT Zhengzhou450000 China Harbin Institute of Technology Center for Control Theory and Guidance Technology Harbin150001 China National Key Laboratory of Complex System Control and Intelligent Agent Cooperation Harbin150001 China

This paper studies the stochastic cooperative output regulation problem for linear discrete-time multi-agent systems (MASs) with Markov switching topologies and communication/input delays. First, a moment stability criterion for an interconnected time-homogeneous Markov jump linear systems is builded. Then, based on the moment stability criterion, a fully distributed output regulation protocol is designed to solve the stochastic cooperative output regulation problem successively. Finally, a numerical simulation is provided to validate the efficiency of the designed protocol. © 2004-2012 IEEE.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Identify influential nodes in directed networks: A neighborhood entropy-based method

引用

Chaos, Solitons and Fractals 2025年 197卷

作者： Dong, Ang Feng, Ru Qiu, Lipeng Wu, Yali Ren, Yuanguang Zhou, Aoran Department of Information and Control Engineering Xi'an University of Technology Xi'an710048 China Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi'an University of Technology Xi'an710048 China State Key Laboratory of Metal Extrusion and Forging Equipment Technology China National Heavy Machinery Research Institute Co. Ltd Xi'an710016 China

The identification of influential nodes in complex networks is prominent and actively researched topic, with applications across various fields. Despite the emergence of numerous methods, many of these are inadequate for directed networks due to the asymmetry of information flow. To address this challenge, we propose a Neighborhood Entropy-based Method (NEM) for identifying key nodes in directed networks. Inspired by Shannon entropy, the k-orders in-degree entropy and k-orders out-degree entropy of nodes are defined to capture the neighborhood information of the node. A tunable parameter α is introduced to balance the contribution of in-neighbors and out-neighbors on neighbor influence ability, while a decay factor φk is set to adjust the influence of different order neighbors on the node. The importance of a node can be eventually evaluated by the influence capability of its in-neighbors and itself. To assess the effectiveness of NEM, we benchmark it against six existing methods on six real network datasets. The results demonstrate the high correctness of NEM, with its low time complexity enabling efficient application to large-scale directed networks. © 2025 Elsevier Ltd

关键词： k-nearest neighbors

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Learning and control with Event-Triggered Measurements

引用

IEEE Transactions on Automatic control 2025年

作者： Feng, Shilun Shi, Dawei Chen, Tongwen Shi, Ling Beijing Institute of Technology State Key Laboratory of Intelligent Control and Decision of Complex Systems MIIT Key Laboratory of Servo Motion System Drive and Control School of Automation Beijing100081 China University of Alberta Department of Electrical and Computer Engineering EdmontonABT6G 1H9 Canada Hong Kong University of Science and Technology Department of Electronic and Computer Engineering Clear Water Bay Kowloon Hong Kong

Event-triggered control has attracted considerable attention for its effectiveness in resource-restricted applications. To make event-triggered control as an end-to-end solution, a key issue is how to effectively learn unknown system dynamics from event-triggered measurements and consequently, develop a learning-based event-triggered controller. Existing works learn system dynamics based on periodic time-triggered measurements, and it is yet to know how to learn a controller with performance guarantee based on event-triggered measurements. To address this issue, we consider the problem of learning an event-triggered state feedback controller for an unknown linear system based on event-triggered state measurements in this work. In particular, we first analyze the event-triggered measurements within a set-membership framework. We prove that the estimation error belongs to a bounded ellipsoid determined by the historical measurements and the event-triggering condition. Subsequently, we demonstrate that all admissible systems compatible with the collected data samples can be explicitly represented in the form of quadratic matrix inequalities using the state estimates. With the acquired set of admissible systems, a co-design problem for the data-driven controller and event-triggering condition is solved using the linear matrix inequality technique, with guaranteed closed-loop stability and L2-gain performance. Finally, numerical examples and comparisons are provided to illustrate the effectiveness of the proposed event-triggered learning and control approach. © 1963-2012 IEEE.

关键词： Networked control systems

来源：评论

学校读者我要写书评

暂无评论

Near minimum-time feedback attitude control with multiple saturation constraints for agile satellites

引用

Chinese Journal of Aeronautics 2016年第3期29卷 722-737页

作者： Liu Xiangdong Xin Xing Li Zhen Chen Zhen Sheng Yongzhi School of Automation Beijing Institute of Technology National Key Laboratory of Complex System Intelligent Control and Decision Beijing Institute of Technology

Agile satellites are of importance in modern aerospace applications, but high mobility of the satellites may cause them vulnerable to saturation during attitude maneuvers due to limited rating of actuators, This paper proposes a near minimum-time feedback control law for the agile satellite attitude control system. The feedback controller is formed by specially designed cascaded sub-units. The rapid dynamic response of the modified Bang Bang control logic achieves the near optimal property and ensures the non-saturation properties on three-axis. To improve the dynamic performance, a model reference control strategy is proposed, in which the oniline near optimal attitude maneuver path is generated by the cascade controller and is then tracked by a nonlinear back-stepping controller. Furthermore, the accuracy and the robustness of the control system are achieved by momentum-based on-line inertial identification. The rapid attitude maneuvering can be applied for tasks including the move to move case. Numerical simulations are conducted to verify the effectiveness of the proposed control strategy in terms of the saturation-free property and rapidness.

关键词： Actuator saturation Attitude control Identification Momentum transfer Satellites

来源：评论

学校读者我要写书评

暂无评论

Multiplexed model predictive attitude control for nadir-pointing satellite using only magnetorquers

引用

control Engineering Practice 2025年 162卷

作者： Yang, Sen Ling, Keck Voon Wang, Zhenhua Li, Huiping School of Astronautic Harbin Institute of Technology Harbin150001 China School of Electrical and Electronic Engineering Nanyang Technological University Singapore639798 Singapore National Key Laboratory of Complex System Control and Intelligent Agent Cooperation Harbin150001 China School of Marine Science and Technology Northwestern Polytechnical University Xi'an710072 China

Due to the low failure risk of magnetorquers, the control strategy based on magnetic actuators can significantly enhance the reliability of the satellite attitude control system. In light of this advantage, this paper conducts research on model predictive control (MPC) algorithm for nadir-pointing satellites equipped only with magnetorquers. Firstly, to facilitate controller design, the linear time-varying (LTV) model for nadir-pointing satellites is derived by linearizing the nonlinear equations around the operating point. Then, leveraging this linearized representation, an LTV multiplexed MPC (MMPC) method with exponential weighting is proposed. The MMPC scheme allows for faster sampling rates and quicker responses to disturbances, thereby enhancing the overall performance of the satellite attitude control system while retaining the benefits of MPC. Finally, compared with a state-of-the-art SMPC method, the proposed method is particularly advantageous in situations where computational resources are limited, specifically for satellites that rely only on onboard computing capabilities. © 2025

关键词： Nonlinear equations

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：