检索结果-内蒙古大学图书馆

A trajectory-level robot skill learning method based on fuzzy systems

Science China(Information Sciences) 2025年第5期68卷 38-52页

作者： Chao ZENG Zhen DENG Boyang TI Yongsheng GAO Department of Computer Science University of Liverpool School of Mechanical Engineering and Automation Fuzhou University State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences State Key Laboratory of Robotics and System Harbin Institute of Technology

Learning from demonstration(LfD) allows for the effective transfer of human manipulation skills to a robot by building a model that represents these skills based on a limited number of demonstrated ***,a skilllearning model that can comprehensively satisfy multiple requirements,such as computational complexity,modeling accuracy,trajectory smoothness,and robustness,is still ***,this work aims to provide such a model by employing fuzzy ***,we introduce an LfD model named Takagi-Sugeno-Kang fuzzy system-based movement primitives(TSKFMPs),which exploits the advantages of the fuzzy theory for effective robotic imitation learning of human *** work formulates the TSK fuzzy system and gradient descent(GD) as imitation learning models,leveraging recent advancements in GD-based optimization for fuzzy *** study takes a two-step strategy.(ⅰ) The input-output relationships of the model are established using TSK fuzzy systems based on demonstration *** this way,the skill is encoded by the model parameter in the latent space.(ⅱ) GD is used to optimize the model parameter to increase the modeling accuracy and trajectory *** further explain how learned trajectories are adapted to new task scenarios through local *** conduct multiple tests using an open dataset to validate our method,and the results demonstrate performance comparable with those of other ***,we implement it in a real-world case study.

关键词： robot skill learning movement primitives TSK fuzzy systems gradient descent robotics

来源：评论

学校读者我要写书评

暂无评论

Automated Seeding in Hydroponic Greenhouse With a Dual-Arm Robotic System

引用

IEEE Access 2025年 13卷 30745-30761页

作者： Rodriguez-Nieto, Daniel Navas, Eduardo Fernandez, Roemi Madrid28500 Spain Polytechnic University of Madrid Centre for Automation and Robotics Madrid28006 Spain

automation in agriculture, often referred to as Agriculture 4.0, has attracted significant interest in recent decades. The integration of technologies like artificial intelligence, robotic manipulation, and autonomous navigation, commonly used in industrial automation, also shows great potential in the agricultural sector. While these technologies are being extensively applied to automate tasks such as fruit harvesting, there is a notable lack of research focused on their application to other essential tasks, such as seeding. In this context, this article introduces an autonomous bi-manipulator robot designed to automate the seeding process in a hydroponic greenhouse. The dual-arm robotic system is capable of perceiving the environment to accurately identify the location of growing cubes within planters, securely position the cubes without causing collisions within the hydroponic system, collect seeds, and deposit them directly into the small holes of the growing cubes. Several perception and manipulation strategies are proposed and experimentally evaluated to enhance the overall process. The results demonstrate that automating this task with a dual-arm mobile robot is both feasible and efficient, achieving an average seeding time of 75 s per rock-wool cube with the most efficient strategy, including cube positioning and verification of proper seed placement. © 2025 The Authors.

关键词： Hydroponics

来源：评论

学校读者我要写书评

暂无评论

An improved YOLOv3 model for detection of invasive Saccharomyces Cerevisiae infections

引用

Multimedia Tools and Applications 2025年第15期84卷 14605-14622页

作者： Li, Gongxin Li, Shuai Fang, Xing Luan, Xiaoli Liu, Fei Institute of Automation Jiangnan University Wuxi214122 China State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China

Saccharomyces Cerevisiae (S. cerevisiae) is a fermenting strain that commonly used in the baking and brewing industries and also used as a probiotic for the prevention and treatment of various diarrhea and related diseases. However, cases of invasive S. cerevisiae infection due to the ingestion of S. cerevisiae have been increasing over the last two decades, especially in elderly, immunocompromised and critically ill patients. In addition, the currently methods used in clinical for the diagnosis of invasive S. cerevisiae infections are time-consuming and easily miss the optimal time for diagnosis and early prevention. Here, we propose an improved YOLOv3 model-based deep learning method to detect S. cerevisiae with higher efficient. The improved YOLOv3 model is derived from the YOLOv3 model by re-constructing its’ model structure with a lightweight network (GhostNet) and other related functions to improve the detection precision and efficiency, and the improved performances were experimentally validated on blood samples. Furthermore, the detection performance by the method was also experimentally compared with that by other several typical deep learning methods. The experimental results showed that the average precision and average detection time on a single image of the improved YOLOv3 model is 97.83% and 0.021 s, respectively, and the both indexes significantly outperform the other methods. The study provides a novel and potential method to detect invasive S. cerevisiae infection with higher precision and faster rate, and also offers a new approach for timely diagnosis and early prevention of the related diseases reduced by microorganism. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Yeast

来源：评论

学校读者我要写书评

暂无评论

Neural Network Algorithm Based on LVQ for Myocardial Infarction Detection and Localization Using Multi-Lead ECG Data

引用

Computers, Materials & Continua 2025年第3期82卷 5257-5284页

作者： Kassymbek Ozhikenov Zhadyra Alimbayeva Chingiz Alimbayev Aiman Ozhikenova Yeldos Altay Department of Robotics and Engineering Tools of Automation Satbayev UniversityAlmaty050010Kazakhstan Joldasbekov Institute of Mechanics and Engineering Almaty050010Kazakhstan

Myocardial infarction(MI)is one of the leading causes of death globally among cardiovascular diseases,necessitating modern and accurate diagnostics for cardiac patient *** the available functional diagnostic methods,electrocardiography(ECG)is particularly well-known for its ability to detect ***,confirming its accuracy—particularly in identifying the localization of myocardial damage—often presents challenges in *** study,therefore,proposes a new approach based on machine learning models for the analysis of 12-lead ECG data to accurately identify the localization of *** particular,the learning vector quantization(LVQ)algorithm was applied,considering the contribution of each ECG lead in the 12-channel system,which obtained an accuracy of 87%in localizing damaged *** developed model was tested on verified data from the PTB database,including 445 ECG recordings from both healthy individuals and MI-diagnosed *** results demonstrated that the 12-lead ECG system allows for a comprehensive understanding of cardiac activities in myocardial infarction patients,serving as an essential tool for the diagnosis of myocardial conditions and localizing their damage.A comprehensive comparison was performed,including CNN,SVM,and Logistic Regression,to evaluate the proposed LVQ *** results demonstrate that the LVQ model achieves competitive performance in diagnostic tasks while maintaining computational efficiency,making it suitable for resource-constrained *** study also applies a carefully designed data pre-processing flow,including class balancing and noise removal,which improves the reliability and reproducibility of the *** aspects highlight the potential application of the LVQ model in cardiac diagnostics,opening up prospects for its use along with more complex neural network architectures.

关键词： Electrocardiography 12-lead electrocardiogram myocardial infarction heart disease learning vector quantization algorithm machine learning

来源：评论

学校读者我要写书评

暂无评论

Theoretical Model Construction and Static Performance Analysis of Multi-Leaf Journal Foil Bearings

引用

Journal of Tribology 2025年第7期147卷 074101页

作者： Hu, Yang Ding, Pengjing School of Mechatronic Engineering and Automation Shanghai Key Laboratory of Intelligent Manufacturing and Robotics Shanghai University Shanghai200072 China

Multi-leaf journal foil bearing (MLJFB) structures are complex, making performance prediction challenging, and the accurate prediction of gas film thickness and pressure distributions is crucial. In this study, comsol finite-element software was used to establish an initial foil assembly and structural deformation simulation model for an MLJFB with bump foils. Using matlab, a compressible gas lubrication model was established and solved using the finite volume method. Real-time data transfer between comsol and matlab enabled a fully coupled fluid-structure interaction simulation. This model meticulously accounts for the pre-tension force in the multi-leaf bearing assembly, contact friction between adjacent foils, and the interaction between the top foil and gas film pressure. The effects of journal movement distance, direction, and top foil overlapping ratio on the bearing capacity as well as the effects of different external load directions on the journal equilibrium position were analyzed based on this model. The results indicate that increasing the top foil overlapping ratio enhances the bearing capacity of the MLJFB. Furthermore, compared to the direction of the top foil overlap position, external loads applied in the direction of the top foil midpoint are more beneficial for bearing operational stability. Copyright © 2024 by ASME.

关键词： MATLAB

来源：评论

学校读者我要写书评

暂无评论

Information-Theoretic Improvement of Model Predictive Control 9

Information-Theoretic Improvement of Model Predictive Contro...

引用

9th International Conference on Mechanical Engineering and robotics Research, ICMERR 2025

作者： Bania, Piotr AGH University of Krakow Department of Automation and Robotics Krakow Poland

ISBN: (纸本)9798331509262

An information-theoretic improvement of the stochastic Model Predictive Control has been proposed and examined. First, it was observed that optimal feedback must, if possible, actively generate information about the system state. Since standard MPC algorithm does not do this, it was hypothesized that adding a penalty for information deficit to the standard MPC cost function can generate a control strategy closer to the optimal one. An exact formula for the cost has been derived for a class of linear systems with control-dependent matrices. Then, it was shown on the basis of simple, two dimensional, example that the proposed modification generates significantly better strategy, for which the cost functional is more than five times smaller compared to the standard MPC algorithm. © 2025 IEEE.

关键词： Predictive control systems

来源：评论

学校读者我要写书评

暂无评论

Hybrid Topological Map Fusion Based on Memory Sphere

引用

Journal of Shanghai Jiaotong University (Science) 2025年 1-13页

作者： Peng, Chengyu Chen, Baifan Li, Siyu Jin, Yuxuan Wan, Jiadong Fu, Yuesi School of Automation Central South University Changsha410083 China School of Robotics Hunan University Changsha410082 China

A topological map with the spatial relationship is an inescapable object in the research of map fusion, as it is a priori knowledge for planning path. However, there are some difficulties in topological map fusion in a dynamic environment. Therefore, this paper proposes a fusion method for the hybrid topological map based on the memory sphere. A hybrid topological map is composed of occupancy grid maps and the topological structure. The hybrid map fusion can rely on rich features in occupancy grid maps. By analyzing the process of recalling scene, a memory sphere is designed to store the features and the semantic label extracted from occupancy grid maps. Then the core is the matching of the memory sphere, which is divided into two parts, fast retrieval and fine matching. We verify the effectiveness of our method in simulation and real environments, demonstrating that our method has a great performance in the dynamic environment. (Figure presented.) © Shanghai Jiao Tong University 2025.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Joint Probabilistic Scheduling and Resource Allocation for Wireless Networked Control Systems

引用

IEEE/CAA Journal of Automatica Sinica 2025年第1期12卷 258-260页

作者： Meng Zheng Lei Zhang Wei Liang IEEE the State Key Laboratory of Robotics and the Key Laboratory of Networked Control Systems Shenyang Institute of Automation Chinese Academy of Sciences the University of Chinese Academy of Sciences

Dear Editor,This letter presents a joint probabilistic scheduling and resource allocation method(PSRA) for 5G-based wireless networked control systems(WNCSs). As a control-aware optimization method, PSRA minimizes the linear quadratic Gaussian(LQG) control cost of WNCSs by optimizing the activation probability of subsystems, the number of uplink repetitions, and the durations of uplink and downlink phases. Simulation results show that PSRA achieves smaller LQG control costs than existing works.

关键词： Networked control systems

来源：评论

学校读者我要写书评

暂无评论

Automated Force Curve Methods Based Micropipette Force Sensors

引用

IEEE Transactions on Nanotechnology 2025年 24卷 224-230页

作者： Shi, Huiyao Tang, Si Shi, Jialin Yu, Peng Yang, Tie Su, Chanmin Liu, Lianqing State Key Laboratory of Robotics Shenyang Institute of Automation Shenyang110016 China University of the Chinese Academy of Sciences Beijing100049 China

Force curve is the most important techniques for accurate measuring the stiffness, adhesion and energy dissipation. However, due to the challenges of probe-cell localization, this type of single-cell analysis tool has become a labor-intensive and time-consuming procedure. Here, we demonstrate an automatic positioning methods based on micropipette for force curves acquisition. The automation covers the detection of cells in label-free images, pre-positioning and automatic focusing of micropipette, as well as automated force curves. This new method discards silicon-based probes used in traditional AFM, and instead utilizing a transparent micropipette with an unobstructed tip as the sensor. This advancement enables accurate localization of the probe tip and cell under an optical microscope. Furthermore, during the probe positioning process, we have implemented a pre-localization method using focused laser projection. This allows for manual adjustment of the probe tip within a range of 70 micrometers, providing precise region of interests (ROI) for automatic tip focusing. Combining with the aforementioned techniques. We also demonstrate the high-precision localization and force curve acquisition of eight fixed cells on a single image. The measurement results indicate that the positioning error will not exceed 3.4 μm. Our work has effectively enhanced the efficiency of cellular mechanical measurements and holds the potential to achieve automated high-throughput single-cell analysis and drug screening. © 2002-2012 IEEE.

关键词： Probes

来源：评论

学校读者我要写书评

暂无评论

Model predictive control and replanning for magnetic microrobots in fluid environments

引用

Science China Technological Sciences 2025年第5期68卷 142-154页

作者： Junjian ZHOU Mengyue LI Na LI Huanyu ZHOU Xiaodong WANG Jingyi WANG Lianqing LIU Niandong JIAO State Key Laboratory of Robotics Shenyang Institute of AutomationChinese Academy of Sciences University of Chinese Academy of Sciences College of Information and Electrical Engineering Shenyang Agricultural University

Magnetic microrobots, given their unique characteristics, hold great potential in biomedical applications such as targeted therapy and microscale operations and are receiving widespread attention. Research on the autonomous navigation of magnetic microrobots is highly focused, as it is an essential prerequisite for achieving functions such as targeted delivery in medical settings. The success of autonomous navigation determines the level of intelligence and precision in the motion of magnetic microrobots. However, uncertainties stemming from environmental changes and time-varying disturbances in electromagnetic systems adversely affect the control accuracy of magnetic microrobots. Additionally, the random appearance of dynamic obstacles along expected trajectories challenges their autonomous navigation. In this study, we demonstrate a method for the exact autonomous navigation of magnetic microrobots in fluid environments, successfully avoiding dynamic obstacles that suddenly appear in predefined trajectories. Improved versions of the A*algorithm and dynamic window approach are integrated as path planners, that can generate smooth and collision-free trajectories that adhere to kinematic constraints in fluid environments with dynamic obstacles. A learning-based model predictive control strategy is employed, where radial basis function neural networks are used to effectively predict and compensate for fluid disturbances and inevitable errors introduced by electromagnetic system coupling, thereby ensuring the control accuracy of the magnetic microrobot in a flowing environment. Experiments in a constructed microfluidic environment validate the effectiveness of our navigation approach in motion control, autonomous navigation, and replanning, with an average error of less than 8% of the body length of the microrobot.

关键词： magnetic microrobot model predictive control path planning radial basis function neural network

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：