检索结果-内蒙古大学图书馆

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

作者： Li, Liang Li, Yiping Jiang, Zhibin Wang, Hailin State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110169 China Key Laboratory of Marine Robotics Liaoning Shenyang110169 China University of Chinese Academy of Sciences Beijing100049 China

ISBN: (纸本)9789819964796

Cleaning up surface floating garbage is of great significance to improve the ecological environment of the waters, of which the detection of surface floating garbage is a crucial step. It is difficult to distinguish the background and garbage and solve the problem of small targets of the existing target detection methods. Therefore, an improved YOLOv7 network is proposed to achieve efficient and high-precision detection of surface floating garbage. The newly proposed DS method is applied to original YOLOv7 network for multi-scale feature fusion. Meanwhile, CBAM attention mechanism module is applied to network backbone to improve detection precision. The public data set FLOW is used to validate the method in this paper. The simulation test results show that the proposed method significantly improves the detection precision without reducing too much detection speed, which proves the effectiveness of the proposed method. Finally, the proposed method is deployed to an NVIDIA Jetson device and applied to real-time surface floating garbage detection, which proves its practicability. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2023.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Query Attack by Multi-Identity Surrogates

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第2期5卷 684-697页

作者： Chen, Sizhe Huang, Zhehao Tao, Qinghua Huang, Xiaolin Department of Automation and Institute of Medical Robotics Shanghai Jiao Tong University Shanghai200240 China MOE Key Laboratory of System Control and Information Processing Shanghai Jiao Tong University Shanghai200240 China ESAT-STADIUS Katholieke Universiteit Leuven Leuven3000 Belgium

Deep neural networks (DNNs) are acknowledged as vulnerable to adversarial attacks while the existing black-box attacks require extensive queries on the victim DNN to achieve high success rates. For query-efficiency, surrogate models of the victim are used to generate transferable adversarial examples (AEs) because of their gradient similarity (GS), i.e., surrogates' attack gradients are similar to the victim's ones. However, it is generally neglected to exploit their similarity on outputs, namely the prediction similarity (PS), to filter out inefficient queries by surrogates without querying the victim. To jointly utilize and also optimize surrogates' GS and PS, we develop QueryNet, a unified attack framework that can significantly reduce queries. QueryNet creatively attacks by multi-identity surrogates, i.e., crafts several AEs for one sample by different surrogates and also uses surrogates to decide on the most promising AE for the query. After that, the victim's query feedback is accumulated to optimize not only surrogates' parameters but also their architectures, enhancing both the GS and the PS. Although QueryNet has no access to pretrained surrogates' prior, it reduces queries by averagely about an order of magnitude compared to alternatives within an acceptable time, according to our comprehensive experiments: 11 victims (including two commercial models) on MNIST/CIFAR10/ImageNet, allowing only 8-b image queries, and no access to the victim's training data. The code is available at https://***/Sizhe-Chen/QueryNet. © 2023 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Design and Performance Analysis of Fe-Based Nanocrystalline Materials for Underwater Wireless Power Transfer systems 3

Design and Performance Analysis of Fe-Based Nanocrystalline ...

引用

3rd Asia Power and Electrical Technology Conference, APET 2024

作者： Xu, Han Zheng, Rong Ning, Wei Shenyang Institute of Automation Chinese Academy of Sciences State Key Laboratory of Robotics Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110169 China University of Chinese Academy of Sciences Beijing100049 China

ISBN: (纸本)9798350367690

Underwater wireless power transfer (UWPT) technology provides an efficient energy supply solution for autonomous underwater vehicle (AUV), where the magnetic core of the magnetic coupling mechanism plays a critical role in system performance. Considering the application constraints of MnZn ferrite in high-power rapid charging and arc-shaped magnetic coupling mechanisms in UWPT systems, Fe-based nanocrystals are employed in this work as novel core materials because of their high saturation magnetic flux density and superior flexibility. However, their low resistivity results in greater eddy current losses, requiring optimization through specialized processing techniques. The performance parameters affecting system efficiency were analysed and designed through finite element simulation to guide the processing techniques. Finally, a UWPT experimental platform was constructed to conduct comparative performance experiments between the processed Fe-based nanocrystalline core and the Mn-Zn ferrite core. The results indicate that the coupling coefficients of the two cores are similar, with the total system efficiency of the Fe-based nanocrystalline core being slightly lower than that of the Mn-Zn ferrite core by 2.05%. However, its weight is reduced by 59.8%, which significantly enhances the lightweight design potential of AUV. © 2024 IEEE.

关键词： Inductive power transmission

来源：评论

学校读者我要写书评

暂无评论

Dielectric Elastomer-Based Biomimetic Twin-Tailed Robotic Fish with Fast and Flexible Swimming 14

Dielectric Elastomer-Based Biomimetic Twin-Tailed Robotic Fi...

引用

14th IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent systems, CYBER 2024

作者： Zhang, Yiwei Zhang, Chuang Wang, Ruiqian Qin, Hengshen Yang, Lianchao Liu, Lianqing Shenyang Institute of Automation Chinese Academy of Sciences State Key Laboratory of Robotics Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110169 China University of Chinese Academy of Sciences Beijing100049 China

ISBN: (纸本)9798331506056

Soft underwater robots, due to their flexible materials, low driving noise, and outstanding human-machine interaction capabilities, have enormous potential applications in underwater rescue, underwater sample collection, marine resource exploration, and other fields, arousing widespread research interest. However, current soft underwater robots based on smart materials have several shortcomings, such as slow swimming speeds, poor flexibility, weak driving force, and poor load capacity, making them difficult to apply in real task environments. Here, we designed a soft twin-tailed robotic fish driven by cylindrical dielectric elastomer actuators that can achieve fast and flexible swimming and efficient transportation. The designed dielectric elastomer actuators can realize large bending angles (84°) and high output force (53 mN), enabling the soft robot to swim quickly. The twin-tailed robotic fish is driven by two-degree-of-freedom actuators, realizing an average swimming speed of 0.35 BL/s and a maximum instantaneous swimming speed of 14.5 cm/s (0.85 BL/s). Furthermore, to demonstrate its application potential, robotic fish can transport goods to the desired location through two modes of movement (straight line movement and turning). This work not only lays the foundation for the development and application of soft swimming robots but also provides a reference for research on high-performance soft actuators applied to underwater robots. © 2024 IEEE.

关键词： Human robot interaction

来源：评论

学校读者我要写书评

暂无评论

Pressure Pain Recognition for Lower Limb Exoskeleton Robot with Physiological Signals 1

引用

2nd International Conference on Cognitive Computation and systems, ICCCS 2023

作者： Ma, Yue Wu, Xinyu Wang, Xiangyang Li, Jinke Qin, Pengjie Yin, Meng Cao, Wujing Yi, Zhengkun Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Shenzhen China SIAT-CUHK Joint Laboratory of Robotics and Intelligent Systems Guangdong Shenzhen China Shandong Institute of Advanced Technology Chinese Academy of Sciences Shandong Jining China

ISBN: (数字)9789819708857

ISBN: (纸本)9789819708840

Pain is a feedback mechanism the body uses to protect itself. The perception of human pain is still missing in lower limb exoskeleton robots, such as the pain caused by the pressure between the knee joint and the baffle when the lower limb exoskeleton stands up, or the pain caused by the mismatch between the gait and the body function of the wearer when walking. Aiming at the pain perception problem of the exoskeleton robot, this study designed a pressure pain data acquisition paradigm combined first considering the movement mode of the exoskeleton robot, and collected facial electromyography and electrocardiography signals, as well as five levels of pain. Then a deep learning neural Network based on Temporal Convolutional Network and Long Short-Term Memory is designed. The composite Loss of Center Loss, InfoNEC Loss and Softmax Loss is designed. The designed deep neural network model was evaluated using the thermal pain dataset BioVid, and the average recognition rate using only electrocardiography signals reached 86.44%. By Using the fusion signals of electrocardiography, electrocardiogram and electromyogram signals, the average recognition accuracy can reach 87.16%, which is superior to other similar methods, and verifies the effectiveness of the proposed method. The proposed network is also used to verify the collected pressure pain dataset, and the recognition accuracy can reach 87.5%, which proves the validity of the collected data set. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Electrocardiography

来源：评论

学校读者我要写书评

暂无评论

Review of Underwater Visual Navigation and Docking: Advances and Challenges 6

Review of Underwater Visual Navigation and Docking: Advances...

引用

6th Conference on Frontiers in Optical Imaging and Technology: Imaging Detection and Target Recognition

作者： Li, Yiyang Sun, Kai State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Science Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110169 China University of Chinese Academy of Sciences Beijing100049 China

ISBN: (数字)9781510679733

ISBN: (纸本)9781510679726

The widespread utilization of autonomous underwater vehicles in marine science and engineering has underscored the paramount importance of precise underwater navigation and docking capabilities for underwater robots. Underwater vision navigation systems serve as a pivotal technology, encompassing various domains such as computer vision, image processing, and machine learning. Nevertheless, they confront a series of challenges. This review aims to consolidate the most recent research advancements in underwater vision navigation systems, with a particular focus on critical aspects such as beacon design, monocular and binocular vision, and detection algorithms. At present, underwater beacons can be categorized into active and passive types, with the flexibility to choose between them contingent upon the specific task and environment. On the other hand, relative to the prevalent use of monocular vision, binocular vision systems offer the potential to furnish more accurate depth information, and the seamless integration of monocular and binocular vision systems enhances the precision and stability of navigation tasks. Concerning detection algorithms, traditional feature extraction methods and deep learning approaches each exhibit their merits and drawbacks, but deep learning methods demonstrate immense potential in complex underwater environments. By summarizing and analyzing the above research results, the application of each key technology of underwater vision navigation and docking is sorted out, and its further development direction is foreseen. © 2024 SPIE. All rights reserved.

关键词： Autonomous underwater vehicles

来源：评论

学校读者我要写书评

暂无评论

Simulation of magnetization process and Faraday effect of magnetic bilayer films

引用

Chinese Physics B 2024年第9期33卷 590-597页

作者： Sheng Gao An Du Lei Zhang Tian-Guang Li Da-Cheng Ma Department of Basic and General Studies Shenyang Institute of Science and TechnologyShenyang 110167China College of Science Northeastern UniversityShenyang 110819China National Frontiers Science Center for Industrial Intelligence and Systems Optimization Northeastern UniversityShenyang 110819China Office of Academic Research Shenyang Institute of Science and TechnologyShenyang 110167China State Key Laboratory of Robotics Shenyang Institute of AutomationChinese Academy ofSciencesShenyang 110016China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of SciencesShenyang110016China

We described ferromagnetic film and bilayer films composed of two ferromagnetic layers coupled through antiferromagnetic interfacial interaction by classical Heisenberg model and simulated their magnetization state,magnetic permeability,and Faraday effect at zero and finite temperature by using the Landau–Lifshitz–Gilbert(LLG)*** results indicate that in a microwave field with positive circular polarization,the ferromagnetic film has one resonance peak while the bilayer film has two resonance ***,the resonance peak disappears in ferromagnetic film,and only one resonance peak emerges in bilayer film in the negative circularly polarized microwave *** the microwave field’s frequency exceeds the film’s resonance frequency,the Faraday rotation angle of the ferromagnetic film is the greatest,and it decreases when the thickness of the two halves of the bilayer is *** the microwave field’s frequency remains constant,the Faraday rotation angle fluctuates with temperature in the same manner as spontaneous magnetization *** a DC magnetic field is applied in the direction of the anisotropic axis of the film,the Faraday rotation angle varies with the DC magnetic field and shows a similar shape of the hysteresis loop.

关键词： magnetic bilayer films magnetic permeability hysteresis loop Faraday effect Landau-Lifshitz-Gilbert(LLG)equation

来源：评论

学校读者我要写书评

暂无评论

EMG Based Rehabilitation Gesture Recognition Using DAE-CNN-LSTM Hybrid Model

EMG Based Rehabilitation Gesture Recognition Using DAE-CNN-L...

引用

2024 International Convention on Rehabilitation Engineering and Assistive Technology and World Rehabilitation Robot Convention, i-CREATE and WRRC 2024

作者： Cao, Wujing Guo, Xinqiang Zou, Yupeng Zhang, Shuo Luo, Mingxiang Kobsiriphat, Worawarit Wu, Xinyu Yin, Meng Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen518005 China SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society SIAT-CUHK Joint Laboratory of Robotics and Intelligent Systems China School of Mechanical Engineering China University of Petroleum China National Metal and Materials Technology Center Thailand

ISBN: (纸本)9798350355123

Stroke, as one of the leading causes of long-term disability globally, often results in motor impairments, particularly in the hands, significantly affecting patients' daily activities and causing profound psychological trauma. Rehabilitation gesture recognition, as one of the key means of active rehabilitation medicine, holds significant potential in stroke rehabilitation, providing real-time feedback on patient progress and enabling personalized interventions to meet individual needs. Traditional gesture recognition methods face numerous challenges when dealing with stroke patient data, such as noise, motion blur, and individual differences. To address these challenges, this paper proposes a novel approach for stroke patient gesture recognition using deep learning models. We adopt a strategy combining denoising autoencoder (DAE), convolutional neural network (CNN), and long short-term memory (LSTM) to enhance the accurate recognition of hand movements in stroke patients. Specifically, DAE is utilized for denoising EMG signals, extracting features, and reducing noise to improve the signal's noise resistance. CNN is employed for spatial feature extraction, while LSTM captures temporal dependencies in gesture sequences. By integrating these three deep learning models, our aim is to enhance the accuracy and robustness of rehabilitation gesture recognition. We validate the proposed method's effectiveness on an EMG dataset from seven subjects through experiments and compare it with traditional machine learning and individual CNN and LSTM algorithms. Experimental results demonstrate significant performance improvements of our hybrid model in rehabilitation gesture recognition tasks, indicating promising application prospects and practical significance. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

RA Loss: Relation-Aware Loss for Robust Person Re-identification 16th

RA Loss: Relation-Aware Loss for Robust Person Re-identific...

引用

16th Asian Conference on Computer Vision, ACCV 2022

作者： Wang, Kan Hu, Shuping Cheng, Jun Cheng, Jun Pang, Jianxin Tan, Huan Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China Guangdong Provincial Key Laboratory of Robot Localization and Navigation Technology UBTech Robotics Corp Ltd. Shenzhen China Institute for Infocomm Research A*STAR Singapore Singapore

ISBN: (纸本)9783031262838

Previous relation-based losses in person re-identification (ReID) typically comprise two sequential steps: they firstly sample both positive pair and negative pair and then deploy constraints to simultaneously improve intra-identity compactness and inter-identity separability. However, existing relation-based losses usually place emphasis on exploring the relation between images and therefore consider only several pairs during each optimization. This inevitably leads to different convergence status for pairs of the same kind and brings about the intra-pair variance problem. Accordingly, we propose a novel Relation-Aware (RA) loss to address the intra-pair variance via exploring the informative relation across pairs. In brief, we introduce a macro-constraint and a micro-constraint. The macro-constraint encourages the separation of positive pair and negative pair via pushing far apart the two "centers" of the positive pair and the negative pair. The "center" of each kind of pair are obtained via averaging all the pairs of the same kind. The micro-constraint further enhances the compactness by minimizing the discrepancies among pairs of the same kind. The two constraints work cooperatively to relieve the intra-pair variance and improve the quality of pedestriansąŕ representation. Results of extensive experiments on three widely used ReID benchmarks, i.e., Market-1501, DukeMTMC-ReID and CUHK03, demonstrate that the RA loss brings improvements over existing relation-based losses. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Design and manufacturing of micro/nanorobots

引用

International Journal of Extreme Manufacturing 2024年第6期6卷 169-202页

作者： Junmin Liu Rencheng Zhuang Dekai Zhou Xiaocong Chang Longqiu Li State Key Laboratory of Robotics and System Harbin Institute of TechnologyHarbinPeople's Republic of China Key Laboratory of Micro-systems and Micro-structures Manufacturing HarbinPeople's Republic of China Zhengzhou Research Institute of Harbin Institute of Technology ZhengzhouPeople's Republic of China

Micro/nanorobots(MNRs)capable of performing tasks at the micro-and nanoscale hold great promise for applications in cutting-edge fields such as biomedical engineering,environmental engineering,and *** cope with the intricate and dynamic environments encountered in practical applications,the development of high performance MNRs is *** have evolved from single-material,single-function,and simple structure to multi-material,multi-function,and complex ***,the design and manufacturing of high performance MNRs with complex multi-material three-dimensional structures at the micro-and nanoscale pose significant challenges that cannot be addressed by conventional serial design strategies and single-process manufacturing *** material-interface-structure-function/performance coupled design methods and the additive/formative/subtractive composite manufacturing methods offer the opportunity to design and manufacture MNRs with multimaterials and complex structures under multi-factor coupling,thus paving the way for the development of high performance *** this paper,we take the three core capabilities of MNRs—mobility,controllability,and load capability—as the focal point,emphasizing the coupled design methods oriented towards their function/performance and the composite manufacturing methods for their functional *** limitations of current investigation are also discussed,and our envisioned future directions for design and manufacture of MNRs are *** hope that this review will provide a framework template for the design and manufacture of high performance MNRs,serving as a roadmap for researchers interested in this area.

关键词： micro/nanorobots functional structure design manufacturing

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：