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

Influence Enhanced Sparse Coordination Graphs for Multi-Agent Reinforcement Learning

引用

Neural Networks 2025年 188卷 107454页

作者： Zhang, Xiwen Chen, Jie Gan, Ming-Gang Chen, Haoxiang State Key Laboratory of Intelligent Control and Decision of Complex Systems School of Automation Beijing Institute of Technology Beijing100081 China

In contemporary Multi-Agent Reinforcement Learning (MARL), effectively enhancing the expressive capacity of value functions has been a persistent research focus. Many studies have employed value decomposition methods;however, due to the neglect of inter-agent collaboration, these methods fall short of achieving optimal performance. Subsequent research introduced coordination graphs into value decomposition methods;nevertheless, these approaches often rely on simplistic rules to evaluate inter-agent collaboration and fail to adequately describe the collaborative relationships of agents in complex environments. Consequently, we propose Influence Enhanced Sparse Coordination Graphs (IESCG) as a solution to provide insights into the aforementioned problem. In this study, we propose influence networks as quantitative descriptions of the importance of collaboration among agents, utilizing them as crucial basis for constructing the topology of Sparse Time-Varying Coordination Graphs. Additionally, we propose Recurrent Payoff Function Networks (RPFN) to incorporate temporal information while providing necessary input to influence networks. Furthermore, Sparse Graph Advantage Selection Coefficients (SGASC) are introduced to stabilize the overall value function across different time steps, ensuring training stability. Experimental investigations conducted on the StarCraft II micromanagement and MACO benchmark indicate that our algorithm not only accelerates convergence and improves winning probabilities but also exhibits more pronounced advantages in complex scenarios. © 2025

关键词： Markov processes

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

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

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

Hybrid optimization of dynamic deployment for networked fire control system

引用

Journal of systems Engineering and Electronics 2013年第6期24卷 954-961页

作者： Chen Chen Jie Chen Bin Xin School of Automation Beijing Institute of Technology Key Laboratory of Complex System Intelligent Control and Decision Ministry of Education

With applying the information technology to the military field, the advantages and importance of the networked combat are more and more obvious. In order to make full use of limited battlefield resources and maximally destroy enemy targets from arbitrary angle in a limited time, the research on firepower nodes dynamic deployment becomes a key problem of command and control. Considering a variety of tactical indexes and actual constraints in air defense, a mathematical model is formulated to minimize the enemy target penetration probability. Based on characteristics of the mathematical model and demands of the deployment problems, an assistance-based algorithm is put forward which combines the artificial potential field （APF） method with a memetic algorithm. The APF method is employed to solve the constraint handling problem and generate feasible solutions. The constrained optimization problem transforms into an optimization problem of APF parameters adjustment, and the dimension of the problem is reduced greatly. The dynamic deployment is accomplished by generation and refinement of feasible solutions. The simulation results show that the proposed algorithm is effective and feasible in dynamic situation.

关键词： deployment optimization artificial potential field (APF) constraint handling generation of feasible solutions memetic algorithm

来源：评论

学校读者我要写书评

暂无评论

Trajectory synchronization of multi-cylinder electrohydraulic lift system with huge load

引用

Journal of Beijing Institute of Technology 2013年第2期22卷 228-234页

作者：何玉东王军政李静赵江波 Key Laboratory of Intelligent Control and Decision of Complex System Beijing Institute of Technology

A kind of four degree-of-freedom （DOF） electrohydraulic lift system is studied in this pa- per, after analyzing the motion characteristics and the mathematic model of the hydraulic cylinders, a cross-coupled synchronization method with load force and synchronization error feedback had been proposed to solve the synchronization problem encountered when realizing the needed roll and pitch attitude of the lift system. In this paper, mathematic model of asymmetric hydraulic cylinder was es- tablished and the lift system had been simplified to a dual-cylinder system. By incorporating the load force and the displacement of each cylinder, a cross-coupled synchronized control method was pro- posed to fit each cylinder＇ s tracking performance and multi-cylinder＇ s trajectory synchronization property. The proposed method not only solved the synchronization problem when multi-cylinder had a same trajectory, but also could fit the coordinated synchronization need when different trajectories of multi-cylinder were desired. Simulations and experiments on a four DOF electrohydraulic lift sys- tem with load of 100 tons verified the effectiveness of the proposed method.

关键词： hydraulic cylinder lift system trajectory synchronization

来源：评论

学校读者我要写书评

暂无评论

Effective approach for outdoor obstacle detection by clustering LIDAR data context

引用

Journal of Beijing Institute of Technology 2016年第4期25卷 483-490页

作者：王军政乔佳楠李静 Key Laboratory of Intelligent Control and Decision of Complex System Beijing Institute of Technology

A method of environment mapping using laser-based light detection and ranging （LIDAR） is proposed in this paper. This method not only has a good detection performance in a wide range of detection angles, but also facilitates the detection of dynamic and hollowed-out obstacles. Essentially using this method, an improved clustering algorithm based on fast search and discovery of density peaks （CBFD） is presented to extract various obstacles in the environment map. By comparing with other cluster algorithms, CBFD can obtain a favorable number of clusterings automatically. Furthermore, the experiments show that CBFD is better and more robust in functionality and performance than the K-means and iterative self-organizing data analysis techniques algorithm （ISODATA）.

关键词： context modeling clustering algorithm based on fast search and discovery of densitypeaks(CBFD) Hull algorithm obstacle detection obstacle fusion

来源：评论

学校读者我要写书评

暂无评论

Motion Planning Method for Obstacle Avoidance of 6-DOF Manipulator Based on Improved A* Algorithm

引用

Journal of Donghua University(English Edition) 2015年第1期32卷 79-85页

作者：汪首坤朱磊 Key Laboratory of Intelligent Control and Decision for Complex System Beijing Institute of Technology

The conventional A* algorithm may suffer from the infinite loop and a large number of search data in the process of motion planning for manipulator. To solve the problem,an improved A* algorithm is proposed in this paper by the means of selecting middle points and applying variable step segments searching during the searching process. In addition,a new method is proposed for collision detection in the workspace. In this paper,the MOTOMAN MH6 manipulator with 6-DOF is applied for motion plan. The algorithm is based on the basis of the simplification for the manipulator and obstacles by cylinder enveloping. Based on the analysis of collision detection,the free space can be achieved which makes it possible for the entire body to avoid collisions with obstacles. Compared with the Conventional A*,the improved algorithm deals with less searching points and performs more efficiently. The simulation developed in VC + + with OpenGL and the actual system experiments prove effectiveness and feasibility of this improved method.

关键词： manipulator collision detection A* algorithm variable step segments searching OpenGL

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：