检索结果-内蒙古大学图书馆

Affine Formation Maneuver Control for Multiagent Systems Based on Unknown Input Reconstruction

IEEE Access 2025年 13卷 102311-102322页

作者： Liduo Hu Wei Zhang Chenhang Yan Yuhang Cai Hao Chen Zhi Hu Laboratory of Intelligent Control and Robotics Shanghai University of Engineering Science Shanghai China National Key Laboratory of Autonomous Intelligent Unmanned Systems School of Automation Beijing Institute of Technology Beijing China

Disturbances can significantly impact the dynamic performance and stability of a system, making them a key focus in stability analysis. However, direct measurement of disturbances is often challenging due to technological and cost limitations. These disturbances introduce uncertainties that complicate multi-agent coordination, particularly in formation control tasks. Consequently, designing effective control strategies for multi-agent systems becomes both challenging and crucial. This paper addresses the affine transformation formation control problem of multi-agent systems in the presence of unknown disturbances. We begin by using a state-space model to describe agent dynamics and employing an unknown input observer to estimate both the state and the unknown disturbances. Based on these estimates, we redesign the control law to ensure that tracking errors converge to an adjustable residual set. This distributed control approach allows agents to operate without global information, thereby reducing communication requirements. Finally, a simulation example demonstrates the feasibility and effectiveness of the proposed control law.

关键词： Formation control Observers Laplace equations Directed graphs Vectors Multi-agent systems Protocols Matrix decomposition Aerospace electronics Vehicle dynamics

来源：评论

学校读者我要写书评

暂无评论

Review of Research on Battery Defect Detection and Recovery 14th

Review of Research on Battery Defect Detection and Recovery

引用

14th International Workshop of Advanced Manufacturing and Automation, IWAMA 2024

作者： Huang, Peng Wang, Chen Yang, Shuai Zhou, Lin College of Mechanical Engineering Hubei University of Automotive Technology Shiyan442002 China China Academy of Engineering Science and Technology Shiyan Industrial Technology Research Institute Shiyan442000 China Shanghai Key Laboratory of Intelligent Manufacturing and Robotics Shanghai University Shanghai200072 China

ISBN: (纸本)9789819626243

Deep learning technology has injected new vitality into the defect detection and disassembly recycling of batteries. This paper describes the defect detection and disassembly recycling of batteries. Firstly, this paper outlines a protocol for detecting imperfections that relies on traditional machine vision procedures, encompassing both image domain analysis and transform domain analysis. Secondly, this paper describes the applications of deep learning in defect detection, including supervised training, unsupervised data mining, limitedly supervised learning, etc. Then, deep neural network applications in the disassembly and recycling of waste batteries is described. Finally, defect inspection relying on traditional machine vision methodologies, the approach for anomaly detection utilizing hierarchical learning, and the implementation of deep neural networks technology in the disassembly and recycling of waste batteries are all summarized herein. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Machine vision

来源：评论

学校读者我要写书评

暂无评论

Underwater Object Detection

Underwater Object Detection

引用

Frontiers technology of Information and Computer (ICFTIC), IEEE International Conference on

作者： Haibin Huang Jiale Xu Robotics and Intelligent Manufacturing Laboratory Xiamen Key Laboratory Xiamen University of Technology Xiamen Fujian China

ISBN: (数字)9798331541750

ISBN: (纸本)9798331541767

This paper addresses the challenges of underwater object detection in aquaculture and marine environmental protection, particularly the issues of small targets and low clarity. To overcome these hurdles, we propose the SwinMS algorithm, which integrates the strengths of Transformer and CNN architectures to enhance the Swin Transformer. key contributions include the introduction of a Deformable Block to improve local perception, resulting in significantly higher accuracy for underwater object detection, and the design of a Mixed-scale Block to enrich local features at each stage. Furthermore, we modify the existing activation function and enhance the detection head with the Shuffle Attention (SA) mechanism, both of which contribute to improved detection accuracy. Experimental results on the UPRC dataset demonstrate that the SwinMS algorithm achieves a mAP score of 88.6%, representing a 4.2% improvement over the DETR. These findings indicate that the proposed detection method is particularly suited for underwater object detection tasks.

关键词： Deformable models Accuracy Convolution Object detection Transformers Rendering (computer graphics) Feature extraction Sensors Neck Protection

来源：评论

学校读者我要写书评

暂无评论

A Review of Small-Sample Target Detection Research 14th

A Review of Small-Sample Target Detection Research

引用

14th International Workshop of Advanced Manufacturing and Automation, IWAMA 2024

作者： Zhou, Lin Wang, Chen Yang, Shuai Huang, Peng College of Mechanical Engineering Hubei University of Automotive Technology Shiyan442002 China China Academy of Engineering Science and Technology Shiyan Industrial Technology Research Institute Shiyan442000 China Shanghai Key Laboratory of Intelligent Manufacturing and Robotics Shanghai University Shanghai200072 China

ISBN: (纸本)9789819626243

Deep learning-based methods for detecting targets in images have advanced significantly in recent years and shown to have tremendous application potential across various domains. But in real-world applications, these methods are frequently constrained by the lack of labelled samples, particularly in situations with small sample sizes. As a result, it has become a crucial area of research to determine how to carry out target detection efficiently. This paper conducts a thorough analysis of image target detection technology under small sample conditions. It does this by methodically elaborating on the definition of the problem of small-sample image target detection and by thoroughly discussing a number of small-sample learning approaches, the most prominent of which are data enhancement-based, migration learning-based, and meta-learning-based. By discussing various algorithms and the fundamental idea behind the process, the benefits and drawbacks of the current approaches to small-sample detection are made evident. Sample identification issues. Lastly, the technological challenges of the current small sample target identification and the direction of future improvement are explored. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Estimation and Prediction of CoM With Terrain Feature Embedding During Walking

引用

IEEE Transactions on Automation Science and Engineering 2025年 22卷 16108-16120页

作者： Haolan Xian Jingfeng Xiong Yuanwen Zhang Xinxing Chen Chenglong Fu Yuquan Leng Key Laboratory of Biomimetic Robotics and Intelligent Systems Shenzhen China Guangdong Provincial Key Laboratory of Human-Augmentation and Rehabilitation Robotics in Universities Southern University of Science and Technology Shenzhen China School of Biomedical Engineering and the State Key Laboratory of Robotics and Systems Harbin Institute of Technology (Shenzhen) Shenzhen China Department of Mechanical and Energy Engineering Southern University of Science and Technology Shenzhen China

Wearable devices are currently being used to reduce metabolism and assist people with disabilities for daily walking. For the elderly and disabled people, improving the walking stability of wearable devices is a crucial and unsolved research. In particular, the center of mass (CoM) trajectory can reflect the walking state as well as the stability of a person. For this reason, realizing the prediction of CoM trajectory under daily walking is promising to improve the wearable devices. In this article, a method for estimation and prediction of CoM during daily walking was proposed. A visual-inertial-odometry algorithm was used to obtain history CoM trajectories during walking, and the depth information from camera data was extracted by sequential distance embedding method and encode the information into terrain vectors. The trajectory vectors were patched with the corresponding terrain vectors and then realized the fusion of multi-modal data, which were then fed into a well-trained temporal convolution network to output the prediction results. With data from two outdoor datasets, the method in this paper was verified to be able to be used for CoM trajectory prediction for a variety of walking tasks and consume low computational cost. This method has the potential to be extensible in improving the stability of wearable devices, such as exoskeleton, powered prosthetic, and so on. Note to Practitioners—It is necessary to obtain the future state of human center of mass (CoM) to improve the stability of user with wearable devices. However, current methods for CoM trajectory prediction, especially with multi-modal data fusion are difficult to apply to this prediction task due to the high computational cost. This article addressed the problem of estimation and prediction of CoM under daily walking conditions and proposed a method to solve the above problems, which enable to deploy on wearable robots with limited computation resources. In our study, a visual-inertial-odometry

关键词： Trajectory Legged locomotion History Cameras Vectors Wearable devices Feature extraction Estimation Wearable robots Sensors

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Model for Metal Gear Defect Detection 14th

Deep Learning Model for Metal Gear Defect Detection

引用

14th International Workshop of Advanced Manufacturing and Automation, IWAMA 2024

作者： Yang, Shuai Wang, Chen Zhou, Lin College of Mechanical Engineering Hubei University of Automotive Technology Shiyan442002 China China Academy of Engineering Science and Technology Shiyan Industrial Technology Research Institute Shiyan442000 China Shanghai Key Laboratory of Intelligent Manufacturing and Robotics Shanghai University Shanghai200072 China

ISBN: (纸本)9789819626243

The quality of the entire mechanical system is directly impacted by the quality of metal gears, an essential transmission component. As such, detecting defects on the end face of metal gears accurately holds significant practical importance with the advancement of industrial automation. Traditional methods for defect detection often involve manual visual inspection or basic image processing techniques, leading to inefficiencies and inaccuracies. In this study, we introduce a novel model for detecting defects on metal gear endfaces utilizing deep learning technology. Through comparison with current mainstream algorithms, our model demonstrated superior performance in terms of accuracy and efficiency, highlighting the vast potential of deep learning in enhancing metal gear endface defect detection. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Gear transmissions

来源：评论

学校读者我要写书评

暂无评论

Predict Hip Joint Moment Using CNN for Hip Exoskeleton Control 1

引用

16th International Conference on intelligent robotics and Applications, ICIRA 2023

作者： Zhang, Yuanwen Xiong, Jingfeng Qian, Yuepeng Chen, Xinxing Guo, Yixuan Fu, Chenglong Leng, Yuquan Shenzhen Key Laboratory of Biomimetic Robotics and Intelligent Systems Department of Mechanical and Energy Engineering Southern University of Science and Technology Shenzhen518055 China Guangdong Provincial Key Laboratory of Human-Augmentation and Rehabilitation Robotics in Universities Southern University of Science and Technology Shenzhen518055 China National University of Singapore Singapore117583 Singapore

ISBN: (数字)9789819964987

ISBN: (纸本)9789819964970

The assistance of the hip exoskeleton is closely related to hip joint moment, and the corresponding assistance can be generated by hip joint moment directly. However, it is difficult to obtain the hip joint moment directly from the sensor during walking. An effective method is to use deep learning models to predict hip joint moment using hip joint angle information. But there are still many challenges in applying this method to practical control systems. This study designs specific parameters to train a deep neural network for predicting hip joint moments and discusses the effects of the number of convolutional layers (N) and the length of sampling time (SL) on the prediction accuracy and the computation time in a real control system. Experiments show that for N ≤ 5, using angle information with SL ≤ 1.0 s achieves the highest prediction accuracy. However, for larger values of N (N > 5), the optimal SL becomes to be longer, where it increases to 2.0 s and the corresponding RMSE is 0.06260 Nm/kg and 0.05977 Nm/kg, respectively. These results indicate the importance of SL for prediction accuracy. Furthermore, a comparative analysis of the computation time with models using different N and SL is performed, and the relationship between computation time and prediction accuracy is discussed. This study provides specific model training parameters and detailed comparative analysis, which facilitates further application of deep learning models on hip exoskeletons. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2023.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Macro-Mini Manipulator Based on Multi-Force Sensors for Force Control Application 14

Macro-Mini Manipulator Based on Multi-Force Sensors for Forc...

引用

14th IEEE International Conference on Cyber technology in Automation, Control, and intelligent Systems, CYBER 2024

作者： Dai, Junjie Chen, Chin-Yin Chen, Han Yang, Guilin Zhejiang Key Laboratory of Robotics and Intelligent Manufacturing Equipment Technology Ningbo Institute of Materials Technology and Engineering Ningbo315201 China University of Chinese Academy of Sciences Beijing100049 China College of Mechanical Engineering Zhejiang University of Technology Hangzhou310023 China

ISBN: (纸本)9798331506056

In polishing, force-controlled performance is affected by manipulator dynamics, end-effector dynamics, and workpiece uncertainty. This paper proposes a new force-controlled method by utilizing multi-force sensors for robotic polishing applications. One of the force sensors is installed between the endpoint of the manipulator and the fixed platform of the end-effector to realize the dynamic decoupling. The other one is added at the back of the workpiece to realize force tracking. The experimental results indicate that the proposed method's contact force response speed and overshoot are both better than those of the conventional force-controlled method. © 2024 IEEE.

关键词： End effectors

来源：评论

学校读者我要写书评

暂无评论

High-compatibility Manipulation Method for Parallel In-situ Isolation of Microalgal Cells via Optoelectronic Tweezers

High-compatibility Manipulation Method for Parallel In-situ ...

引用

2024 IEEE International Conference on Real-Time Computing and robotics, RCAR 2024

作者： Qin, Shilong Liu, Jiaxin Chen, Yuxin Yang, Haotian Zhao, Ziyi Shi, Qing Huang, Qiang Wang, Huaping Beijing Institute of Technology Ministry of Education Key Laboratory of Biomimetic Robots and Systems Beijing100081 China Intelligent Robotics Institute School of Mechatronical Engineering Beijing Institute of Technology Beijing100081 China Beijing Institute of Technology School of Medical Technology Beijing100081 China

ISBN: (纸本)9798350372601

Isolating microalgae in in-situ liquid environment based on optoelectronic tweezers (OETs) enables providing specific species of microalgae in high-purity, thus has significant potential in environmental detection, aquaculture, bioenergy, and biomedicine development. However, the conventional OET method can only separate and extract one type of microalgae in a single-step operation and is challenging to utilize the opposite dielectrophoretic force when the cross frequency of microalgae is too high /low or even absent. In this study, a novel automated microalgae isolation method based on optoelectronic tweezers is proposed, which integrates two strategies: cluster manipulation and discretized synchronous manipulation. Firstly, an optoelectronic tweezer robot platform was built, the dielectrophoretic forces on microalgae and the factors affecting the dielectrophoretic forces were analyzed. Secondly, a cluster manipulation strategy based on light patterns dynamic locomotion structure scheme was designed to simultaneously separate microalgae subject to dielectrophoretic forces of different attributes and the same attribute. Finally, a discretized synchronous manipulation strategy based on visual feedback and PID controller was designed to realize the precise isolation of microalgae subjected to the same dielectrophoretic force and different dielectrophoretic forces. Experimental results demonstrated that the aforementioned method provides a feasible microalgae isolating method based on optoelectronic tweezers within 10 minutes, which has potential applications in the in-situ water contamination detection and treatment. © 2024 IEEE.

关键词： Microorganisms

来源：评论

学校读者我要写书评

暂无评论

TGCN-P: A TCN-GCN Network With Weighted Graph Constructed by Pearson Correlation Coefficient for Human Motion Tracking

TGCN-P: A TCN-GCN Network With Weighted Graph Constructed by...

引用

2023 IEEE International Conference on Real-Time Computing and robotics, RCAR 2023

作者： Li, Xiaoyu Wang, Jingnan Huang, Binhua Liu, Chengliang Liu, Yiwen Zhang, Yupo Yi, Zhengkun Wu, Xinyu Chinese Academy of Sciences Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen Institute of Advanced Technology Shenzhen518055 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Siat Branch Shenzhen518055 China

ISBN: (纸本)9798350327182

Neural networks based on graph convolution are simple and effective network structures that have better performance in some fields compared to traditional convolutional networks. However, when graph convolution networks (GCN) are applied to other fields, how to transform data or features into graph edges is a challenge needed to be studied. In previous studies of non-Euclidean spatial data such as relationship studies, people achieve graph construction by indicating the connection or not of nodes with binary values. However, when graph network is applied to some multi-sensor data scenarios, especially human motion tracking tasks, binarization is obviously not the best solution for the weights of edges. In addition, relying on manual graph construction may ignore some cross-space sensor relationships, which makes the update information of nodes far away slower or unavailable. Therefore, we try to use Pearson correlation coefficient (PCC) as the estimation of node correlation, and construct a complete graph to enhance the connectivity of nodes, which achieve faster signal transmission at remote nodes. After combining it with the temporal convolutional network (TCN), we propose a new network structure TGCN-P. Experimentally, this approach is more effective compared to other baseline models. © 2023 IEEE.

关键词： Convolution

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：