检索结果-内蒙古大学图书馆

Comprehensive Performance Optimization of a Novel Anthropomorphic Dexterous Hand

IEEE robotics and automation Letters 2025年第7期10卷 6816-6823页

作者： Yifan Ma Weiwei Shang Fei Zhang Shunxiang Pang Shuqing Dai Zhengkun Yi Guotao Li Shuang Cong Department of Automation University of Science and Technology of China Hefei China Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China

Grasp and in-hand manipulation of dexterous hands are essential for daily operational tasks. In this study, an optimized design method for a novel anthropomorphic dexterous hand is proposed, which improves the comprehensive performance of grasp and manipulability of the dexterous hand. The constraints of multi-fingered contact force and kinematics are established with full consideration of the applicability to the objects of different sizes and the shape characteristics of finger contact surface. The performance index of in-hand manipulation ability is proposed, and the optimization problem is constructed through the technique for order preference by similarity to ideal solution (TOPSIS) to achieve multi-objective optimization of precision grasp and in-hand manipulation. Finally, simulation and experiment verify the feasibility of our prototype and optimization method. The results show that the in-hand translation space and in-hand rotation range are increased by 20% and 8.5%, respectively. Our dexterous hand has excellent abilities of multi-fingered interaction and in-hand manipulation, which can perform 33 grasp gestures and two/three-fingered in-hand manipulation. This study provides a valuable reference for the design of dexterous hands with anthropomorphic functions.

关键词： Thumb Hands Kinematics Grasping Force Performance analysis IP networks Electronics packaging Cables Accuracy

来源：评论

学校读者我要写书评

暂无评论

High-precision magnetic field measurement system based on a coherent population trapping magnetometer onboard the SATech-01 satellite

引用

Science China(Technological Sciences) 2025年第2期68卷 227-242页

作者： Hongbo XUE Wei SONG Haoran ZHAO Yiteng ZHANG Shanzhi YE Jindong WANG Ran TAO Peng SANG Keli CHEN Xingzi BI Bingjun CHENG Bin ZHOU Yongliang XUE Yingying TANG Liu LIU Jinsong LI Xiaocheng ZHU Baoquan LI Jinguo LIU Wen CHEN Xiaofeng ZHANG Yonghe ZHANG Lei LI State Key Laboratory of Space Weather National Space Science CenterChinese Academy of SciencesBeijing 100190China Key Laboratory of Solar Activity and Space Weather National Space Science CenterChinese Academy of SciencesBeijing 100190China Key Laboratory of Electronics and Information Technology for Space Systems National Space Science CenterChinese Academy of SciencesBeijing 100190China State Key Laboratory of Robotics Shenyang Institute of AutomationChinese Academy of SciencesShenyang 110016China Innovation Academy for Microsatellites Chinese Academy of SciencesShanghai 201304China

On July 27,2022,a high-precision system for measuring the magnetic field based on a coherent population trapping magnetometer(referred to as the CPT system)was launched onboard the Space Advanced Technology demonstration satellite(SATech-01)by a ZK-1A *** payload comprises a scalar coherent population trapping magnetometer(CPTM),triaxial anisotropic magnetoresistance magnetometer(AMRM),and nano star tracker mounted on a non-magnetic telescopic tubular *** configuration enables synchronized measurement of scalar and vector geomagnetic fields,as well as the attitude,making the payload with its compact sensors suitable for applications on miniature satellite *** November 7,2022,the novel telescopic tubular mast was deployed in orbit,extending to a length of 5.28 *** CPTM,an absolute scalar magnetometer with an omnidirectional sensor,is the first China-developed quantum/atomic magnetometer successfully operating in *** orbit,the CPTM has sensitivity of~10 pT/Hz^(1/2) and can automatically operate under complex magnetic field *** difference between the scalar fields obtained using the CPTM and CHAOS model has a mean deviation of -3.73 nT and a standard deviation of 26.11 nT(1σ),without on-orbit calibration or *** miniaturized AMRM has a sensitivity of~0.3 nT/Hz^(1/2) and maintains stable and reliable operation in *** low-power and miniaturized nano star tracker has a measurement uncertainty of 14.23″(1σ)in *** mission has realized the on-orbit technical verification of the integrated and synchronized detection of the vector magnetic field and attitude and fully validated the system’s performance,automation level,and reliability.

关键词： magnetic field measurement system coherent population trapping magnetometer anisotropic magnetoresistance magnetometer nano star tracker non-magnetic telescopic tubular mast satellite

来源：评论

学校读者我要写书评

暂无评论

Development and Optimization of a WebGL-Based Mechanical Model Simulation Platform 4th

Development and Optimization of a WebGL-Based Mechanical Mod...

引用

4th International Conference on Mechanical Design and Simulation, MDS 2024

作者： Wang, Xintong Tian, Hao Fang, Jingzhe Zhang, Hualiang Zhang, Tao Software College Shenyang University of Technology Liaoning Shenyang China Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China School of Electrical Engineering Shenyang University of Technology Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang China

ISBN: (纸本)9789819778867

The need for mechanical model simulation platforms is growing as a result of the ongoing advancements in digital technology and the mechanical manufacturing sector. The application scope and efficacy of simulation platforms are severely limited by the issue of sluggish rendering performance, which frequently arises when obtaining high-quality rendering. When drawing high demand mechanical models, a lot of processing power is frequently needed, which makes real-time rendering speed unsatisfactory for practical purposes. In order to achieve real-time rendering and simulation of 3D robots, this experiment built and implemented a WebGL-based 3D simulation platform. Additionally, the simulation platform can be optimized by increasing frame rate and rendering speed without sacrificing rendering effect by building a mixed bounding box. © The Author(s) 2025.

关键词： Digital elevation model

来源：评论

学校读者我要写书评

暂无评论

Asymptotic Trajectory Tracking of Stratospheric Airships Based on RISE Controllers Under External Uncertainties

引用

IEEE Transactions on Aerospace and Electronic systems 2025年

作者： Liu, Can Li, Baoquan Dai, Fengzhi Shi, Wuxi Zhang, Xuebo Tiangong University School of Control Science and Engineering Tianjin Key Laboratory of Autonomous Intelligence Technology and Systems Tianjin300387 China Tianjin University of Science and Technology College of Electronic Information and Automation Tianjin300222 China Nankai University Institute of Robotics and Automatic Information Systems Tianjin Key Laboratory of Intelligent Robotics Tianjin300071 China

For a stratospheric airship under internal and external uncertainties, controller strategies with robust integral sign of the error (RISE) are proposed for asymptotic trajectory tracking control. Specifically, a fully connected neural network (FCNN) is constructed with adaptive weight updating to estimate internal uncertainties of the airship system. Then, a self-tuning RISE controller is designed to track trajectories with compensating external disturbance, which enables gain adjustment in realtime according to system feedback. Based on Lyapunov technique and LaSalle-Yoshizawa corollary extension, system stability is strictly analyzed, and asymptotic convergence performance is obtained for trajectory tracking by the designed controller. Moreover, a RISE controller is designed with fixed gain matrices for the airship based on classic control strategies, and asymptotic tracking is also proved. Finally, numerical simulations are conducted with spiral and hovering control to verify performance of the proposed strategies. © 1965-2011 IEEE.

关键词： Lyapunov methods

来源：评论

学校读者我要写书评

暂无评论

Obstacle-Avoidance Motion Planning Method of Manipulator Based on Deep Reinforcement Learning

引用

Unmanned systems 2025年

作者： Liu, Yiyang Wu, Defan Fu, Yukai Bai, Hongfei Deng, Chao State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Key Laboratory of Networked Control Systems Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110169 China University of Chinese Academy of Sciences Beijing100049 China Institute of Advanced Technology Nanjing University of Posts and Telecommunications Nanjing210023 China

In recent years, driven by the rapid advancement of industrial automation and intelligent manufacturing, the demand for manipulators to perform tasks in complex environments has significantly increased. Traditional motion planning methods face challenges of computational complexity and lack of adaptability when handling robots with redundant degrees of freedom. To address these issues, this paper proposes a novel obstacle avoidance motion planning method for manipulators based on deep reinforcement learning (DRL), which is especially important when unmanned systems operate in a GPS-free environment. The primary contributions are twofold: (i) we propose an innovative algorithm, termed PPO-HER, which incorporates hindsight experience replay (HER) into proximal policy optimization (PPO) during training, effectively leveraging failed experiences to enhance policy learning efficiency;(ii) an adaptive action exploration strategy is designed to accelerate training convergence and avoid local optima. Experimental results demonstrate that the PPO-HER algorithm and the adaptive action exploration strategy perform exceptionally well across three environments of varying difficulty, significantly improving network training speed and success rates, shortening planned paths, and enhancing autonomous obstacle avoidance capabilities. These findings provide new ideas for target location and tracking of unmanned systems, and lay the foundation for future learning and data-driven approaches in complex environments. © World Scientific Publishing Company.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Machine Learning in Predicting the Impact of Filter Parameters on the Accuracy of Biosignal Measurement

Machine Learning in Predicting the Impact of Filter Paramete...

引用

Digital Signal Processing and its Applications (DSPA), International Conference on

作者： Yeldos A. Altay Raisa K. Uskenbayeva Abu-Alim E. Ayazbay Alexey V. Fedorov Department of Robotics and Technical Means of Automation Satbayev University Almaty Kazakhstan Institute of Automation and Information Technologies Vice-Rector Satbayev University Almaty Kazakhstan Electronic engineering Almaty University of Power Engineering and Telecomunications Almaty Kazakhstan Faculty of Control Systems and Robotics ITMO University Saint-Petersburg Russian Federation

ISBN: (数字)9798331518752

ISBN: (纸本)9798331518769

In this scientific article under consideration, a machine learning model has been developed that allows predicting the impact of filter parameters on the accuracy of measuring a biosignal - an ECG (electrocardiography) signal. For the first time, quantitative results have shown the degree of influence and the error introduced into the measured biosignal and described through dependence. The results of assessing the obtained relationship of indicators demonstrate an inverse correlation relationship that characterizes a decrease in the accuracy of measurement at the output of a high-order digital filtering system. The machine learning model is based on the linear regression method the dependence of which is approximated by the method based on least squares and visualized using a scattergram. The adequacy of the developed machine learning model was confirmed by calculating the coefficient of determination and checking its statistical significance. The developed model can be used to create new or improve existing biomedical data processing systems to increase the reliability of the results.

关键词： Accuracy Shape Filtering Biological system modeling Machine learning Biomedical measurement Electrocardiography Distortion Distortion measurement Digital filters

来源：评论

学校读者我要写书评

暂无评论

TOWARDS EFFICIENT AND GENERAL-PURPOSE FEW-SHOT MISCLASSIFICATION DETECTION FOR VISION-LANGUAGE MODELS

arXiv

引用

arXiv 2025年

作者： Zeng, Fanhu Cheng, Zhen Zhu, Fei Zhang, Xu-Yao State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation CAS China School of Artificial Intelligence UCAS United Kingdom Centre for Artificial Intelligence and Robotics HKISI-CAS Hong Kong

Reliable prediction by classifiers is crucial for their deployment in high security and dynamically changing situations. However, modern neural networks often exhibit overconfidence for misclassified predictions, highlighting the need for confidence estimation to detect errors. Despite the achievements obtained by existing methods on small-scale datasets, they all require training from scratch and there are no efficient and effective misclassification detection (MisD) methods, hindering practical application towards large-scale and ever-changing datasets. In this paper, we pave the way to exploit vision language model (VLM) leveraging text information to establish an efficient and general-purpose misclassification detection framework. By harnessing the power of VLM, we construct FSMisD, a Few-Shot prompt learning framework for MisD to refrain from training from scratch and therefore improve tuning efficiency. To enhance misclassification detection ability, we use adaptive pseudo sample generation and a novel negative loss to mitigate the issue of overconfidence by pushing category prompts away from pseudo features. We conduct comprehensive experiments with prompt learning methods and validate the generalization ability across various datasets with domain shift. Significant and consistent improvement demonstrates the effectiveness, efficiency and generalizability of our approach. Copyright © 2025, The Authors. All rights reserved.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Human-Robot Pose Tracking Based on CNN with Color and Geometry Aggregation 16th

Human-Robot Pose Tracking Based on CNN with Color and Geo...

引用

16th International Conference on Social robotics, ICSR + InnoBiz 2024

作者： Xu, Yue Zhang, Yinlong Liu, Shuai Liu, Yuanhao Liang, Wei He, Hongsheng Shenyang University of Technology Shenyang110020 China Guangzhou Institute of Industrial Intelligence Guangzhou511458 China State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang110016 China University of Chinese Academy of Sciences Beijing100049 China Department of Computer Science The University of Alabama TuscaloosaAL35487 United States

ISBN: (纸本)9789819611508

Accurately tracking the robotic arm and human joints is crucial to ensure safety during human-robot interaction. However, traditional pose tracking methods often exhibit insufficient performance and robustness in complex environments. The variations in the robotic arm’s environment and posture make it challenging for traditional methods to accurately capture the positions and posture of its joints. Specifically, when addressing challenges such as high similarity, occlusion, background complexity, and joint recognition failures, they often struggle to provide reliable and accurate results. To address these challenges, this paper proposes a human-robot pose tracking algorithm based on a new convolutional neural network model. To enhance detection accuracy, an improved color detection module is introduced to resolve joint misclassification. A geometric perception module is designed to accurately locate joints even under occlusion. Additionally, innovative iEMA and DBB modules are incorporated. The iEMA module employs edge detection technology to dynamically adjust thresholds for correct matching by improving the edge matching process. The DBB module refines the boundary box parameters for precise localization by introducing adaptive bounding box updates in real-time. This algorithm also integrates human pose recognition, enabling real-time pose recognition, thereby facilitating more intelligent and natural human-robot interaction. The algorithm has been rigorously evaluated on a custom-designed robotic arm platform. Experimental results validate the algorithm’s effectiveness and feasibility. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Robotic arms

来源：评论

学校读者我要写书评

暂无评论

Global Convergence of Continual Learning on Non-IID Data

arXiv

引用

arXiv 2025年

作者： Zhu, Fei Liu, Yujing Liu, Wenzhuo Zhang, Zhaoxiang Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science & Innovation CAS Hong Kong Key Laboratory of Systems and Control Academy of Mathematics and Systems Science CAS China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation CAS China School of Artificial Intelligence University of Chinese Academy of Sciences China

Continual learning, which aims to learn multiple tasks sequentially, has gained extensive attention. However, most existing work focuses on empirical studies, and the theoretical aspect remains under-explored. Recently, a few investigations have considered the theory of continual learning only for linear regressions, establishes the results based on the strict independent and identically distributed (i.i.d.) assumption and the persistent excitation on the feature data that may be difficult to verify or guarantee in practice. To overcome this fundamental limitation, in this paper, we provide a general and comprehensive theoretical analysis for continual learning of regression models. By utilizing the stochastic Lyapunov function and martingale estimation techniques, we establish the almost sure convergence results of continual learning under a general data condition for the first time. Additionally, without any excitation condition imposed on the data, the convergence rates for the forgetting and regret metrics are provided. Copyright © 2025, The Authors. All rights reserved.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Towards Fast Face Image Quality Assessment via Latent Diffusion Model 18th

Towards Fast Face Image Quality Assessment via Latent Diffu...

引用

18th Chinese Conference on Biometric Recognition, CCBR 2024

作者： Yan, Zheyu Zhao, Weisong Zhu, Xiangyu Gao, Li Zhang, Xiao-Yu Lei, Zhen State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China China Mobile Financial Technology Co. Ltd. Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science and Innovation Chinese Academy of Sciences Hong Kong Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9789819610679

Face recognition technology has gradually come into wide application in real life. However, in real-life unconstrained scenarios, low-quality images could be matched to unpredictable individuals, thereby affecting the stability of recognition and even causing security problems. Conducting quality assessment on face images before facial recognition can help alleviate these problems by rejecting low-quality samples. In this paper, we propose a Fast Diffusion-model-based Face Image Quality Assessment method (FDif-FIQA). It uses a diffusion model to perturb face images and measures image quality based on the similarity of features before and after the perturbation. The denoising process is transferred from the pixel space to the latent space, thereby reducing the computational cost. We evaluated the performance of this method with multiple mainstream face recognition models on various public datasets. Compared to state-of-the-art methods, our approach demonstrates highly competitive performance and significant improvements in computational efficiency. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Face recognition

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：