检索结果-内蒙古大学图书馆

2022 International Conference on Mechatronics Engineering and Artificial Intelligence, MEAI 2022

作者： Hu, Xiaomei Zhang, Yunyou Chen, Yi Chai, Jianfei Wu, Jun Shanghai Key Laboratory of Intelligent Manufacturing and Robotics School of Mechatronic Engineering and Automation Shanghai University Shanghai200444 China Information Technology Office School of Mechatronic Engineering and Automation Shanghai University Shanghai200444 China

ISBN: (纸本)9781510663169

Pear recognition is one of the key technologies of pear picking robot, and the pear recognition algorithm based on convolutional neural network has high computing cost and large parameters, which is difficult to be deployed on pear picking robot with low computer resources. This paper presents a lightweight pear real-time detection method based on YOLOv5. This method designs a lightweight feature extraction network based on Ghost bottomleneck, and embeds the SE module into the designed network, which improves the ability of feature extraction while reducing the amount of network parameters. The experimental results show that compared with YOLOv5l, the parameters of the improved lightweight model are reduced by 48.17 %, mAP is increased by 0.9 %, and the recognition speed is increased by 36 %. The improved model is more suitable to be deployed on the picking robot with limited computing power and provides a solution for the vision system of pear picking robot. © 2023 SPIE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Submegahertz Nucleation of Plasmonic Vapor Microbubbles near a Solid Vertical Boundary

引用

Physical Review Letters 2024年第6期133卷 064001-064001页

作者： Fulong Wang (王福龙) Zhibin Hu Binglin Zeng Chenliang Xia Lihua Dong Huimin Wang Lijun Yang Yuliang Wang (王玉亮) Robotics Institute School of Mechanical Engineering and Automation National Center for Materials Service Safety School of Astronautics Ningbo Institute of Technology

Laser triggered and photothermally induced vapor bubbles have emerged as promising approaches to facilitate optomechanical energy conversion for numerous applications in microfluidics and nanofluidics. Here, we report an observation of spontaneously triggered periodic nucleation of plasmonic vapor bubbles near a rigid sidewall with readily tuned nucleation frequency from 0.8 kHz to over 200 kHz. The detailed collapsing process of the vapor bubbles was experimentally and numerically investigated. We find that the lateral migration of residual bubbles toward the sidewall refreshes the laser spot area, terminates the subsequent steady bubble growth, and leads to the repeatable bubble nucleation. A mathematic model regarding the Kelvin impulses was derived. It shows that the competition between the rigid boundary induced Bjerknes force and laser irradiation caused thermal Marangoni force on collapsing bubbles governs the process. The model also leads to a criterion of γζ<0.34 for repeatable bubble nucleation, where γ is the normalized distance and ζ thermal Marangoni coefficient. This study demonstrates nucleation of violent vapor bubbles at extreme high frequencies, providing an approach to remotely realize strong localized flows in microfluidics and nanofluidics.

关键词： Bubble dynamics Drop or bubble formation Drops & bubbles Laser-induced cavitation Lasers Metals Microfluidic devices Nanofluidic devices Nanoparticles Water

来源：评论

学校读者我要写书评

暂无评论

FDNet: Remaining Useful Life Prediction for Lithium-Ion Batteries Based on Fourier Series and DenseNet 5

FDNet: Remaining Useful Life Prediction for Lithium-Ion Batt...

引用

5th International Conference on Machine Learning and Computer Application, ICMLCA 2024

作者： Chen, Siwen Zheng, Xiujuan Shanghai United Imaging Healthcare Co. Ltd. Shanghai China Institute of Robotics and Intelligent Systems Wuhan University of Science and Technology Engineering Research Center for Metallurgical Automation and Measurement Technology Ministry of Education Wuhan China

ISBN: (纸本)9798331530334

To enhance the prediction accuracy of the remaining useful life (RUL) of lithium-ion batteries, this study proposes a novel RUL prediction model, termed FDNet, which integrates Discrete Fourier Series (DFS) and Densely Connected Convolutional Networks (DenseNet). In contrast to traditional methods that rely on one-dimensional (1D) numerical representations of time-series data, this model utilizes a two-dimensional (2D) visual representation for direct RUL prediction. First, the DFS is employed to convert 1D time-series signals into a 2D time-frequency domain, enabling the extraction of high-dimensional features from the original data. Then, these 2D images are subsequently input into DenseNet, which learns the mapping between the image features and the RUL targets. Finally, the proposed model is validated using the NASA lithium-ion battery aging dataset, and the results indicate that FDNet achieves superior prediction accuracy and exhibits notable robustness. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

DORM: Distance-based opportunistic routing and medium access protocol for multi-AUV monitoring system 23

DORM: Distance-based opportunistic routing and medium access...

引用

2nd International Conference on Networks, Communications and Information technology, CNCIT 2023

作者： Qiu, Tianyou Li, Yiping Feng, Xisheng School of Information Science and Technology University of Science and Technology of China Anhui230026 China 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 Province Shenyang110169 China

ISBN: (纸本)9798400700620

In a multi-AUV (autonomous underwater vehicle) monitoring system, each vehicle uploads sensor data to the surface central control platform through underwater acoustic communication, and the control platform sends commands or task files to AUVs. For a multi-AUV system with many vehicles and a large-scale underwater network, it is a challenge to design protocols to achieve reliable, low-latency, and energy-efficient communication due to the unique characteristics of underwater acoustic channels. We propose a distance-based opportunistic routing-MAC protocol (DORM), which combines opportunistic routing and CSMA, using distance and hop counts information to determine backoff time and forwarding priority. We conducted simulation experiments to analyze the performance of DORM and compared it with P-AUV and Probabilistic Broadcast (PB). The results show that DORM ensures reliable transmission and has apparent advantages in latency and energy efficiency. © 2023 Owner/Author.

关键词： Routing protocols

来源：评论

学校读者我要写书评

暂无评论

A Robotic Manipulator with Conveyor System for Visual Sorting of Work Pieces

A Robotic Manipulator with Conveyor System for Visual Sortin...

引用

E-mobility, Power Control and Smart Systems (ICEMPS), International Conference on

作者： Adarsh V S Jedin Jebi Mathew Joseph Mathew Thuruthiyil Sidharth Sunil Georgina Binoy Joseph Robotics and Automation Toc H institute of Science and Technology Ernakulum Kerala India

ISBN: (数字)9798350394399

ISBN: (纸本)9798350394405

The proposed system for sorting work pieces integrates a four-degree-of-freedom robotic manipulator with computer vision and conveyor transportation capabilities for automated object handling and sorting. Utilizing a conveyor system and inverse kinematics, the robotic arm ensures efficient movements. Real-time images of work pieces are captured and processed using computer vision techniques, allowing for size and color-based sorting. The integration of machine learning with robotic control can ensure dynamic and accurate sorting. The integrated system reduces labor costs, minimizes errors, and finds applications in manufacturing, logistics, and assembly lines improving productivity and product quality.

关键词： Productivity Computer vision Visualization Power control Transportation Real-time systems Product design

来源：评论

学校读者我要写书评

暂无评论

Visible-Infrared Cross-Modal Person Re-Identification Based on Modality Alignment and Fine-Grained Mining 14

Visible-Infrared Cross-Modal Person Re-Identification Based ...

引用

14th IEEE International Conference on Cyber technology in automation, Control, and Intelligent Systems, CYBER 2024

作者： Zhao, Yingchang Yu, Hang Cheng, Zhuxuan Fan, Huijie Lin, Sen School of Automation and Electrical Engineering Shenyang Ligong University Shenyang110159 China Shenyang Institute of Automation Chinese Academy of Sciences State Key Laboratory of Robotics Shenyang110016 China School of Information Engineering Shenyang University of Chemical Technology Shenyang110142 China

ISBN: (纸本)9798331506056

In the current field of computer vision, visible-infrared cross-modal person re-identification has become a research topic of great interest. This task aims to identify and match images of the same pedestrian from different modalities and is widely applied in scenarios like night-time surveillance and multi-camera tracking. However, due to significant visual differences between modalities, this task faces many challenges. To overcome these challenges, in this paper we propose a cross-modal person re-identification method based on modality alignment and fine-grained local feature mining. First, we introduce the Modality Alignment Module, which aims to reduce visual differences between modalities, thereby providing a more consistent foundation for feature extraction and matching. Then, through the Fine-grained Mining Module, we delve into the local details in pedestrian images to enhance the distinctiveness of features and the accuracy of identification. Moreover, by incorporating advanced deep learning architectures and optimization algorithms, our method shows exceptional results on both SYSU-MM01 and RegDB datasets. © 2024 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Brain-Conditional Multimodal Synthesis: A Survey and Taxonomy

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第5期6卷 1080-1099页

作者： Mai, Weijian Zhang, Jian Fang, Pengfei Zhang, Zhijun South China University of Technology School of Automation Science and Engineering Guangzhou510640 China Southeast University School of Computer Science and Engineering Nanjing210096 China South China University of Technology Key Library of Autonomous Systems and Network Control Ministry of Education The School of Automation Science and Engineering Guangzhou510640 China Institute for Super Robotics Huangpu Guangzhou510555 China Nanchang University Jiangxi Thousand Talents Plan Nanchang330031 China Jishou University College of Computer Science and Engineering Jishou416000 China Guangdong Artificial Intelligence and Digital Economy Laboratory Pazhou Lab Guangzhou510335 China Shaanxi University of Technology Shaanxi Provincial Key Laboratory of Industrial Automation School of Mechanical Engineering Hanzhong723001 China Changsha Normal University School of Information Science and Engineering Changsha410100 China Guangdong University of Petrochemical Technology School of Automation Science and Engineering Institute of Artificial Intelligence and Automation Maoming525000 China

In the era of artificial intelligence generated content (AIGC), conditional multimodal synthesis technologies (e.g., text-to-image) are dynamically reshaping the natural content. Brain signals, serving as potential reflections of how the brain interprets external information, exhibit a distinctive one-to-many correspondence with various external modalities. This correspondence makes brain signals emerge as a promising guiding condition for multimodal synthesis (e.g., image, text, and audio), which is crucial for developing practical brain–computer interface systems and unraveling complex mechanisms underlying human perception. This survey comprehensively examines the emerging field of brain-conditional multimodal synthesis, termed AIGC-brain, to delineate the current landscape and future directions. To begin, related neuroimaging datasets and generative models are introduced as the foundation of AIGC-brain decoding and analysis. Next, we present a comprehensive taxonomy according to AIGC-brain methodologies, followed by task-specific representative work and implementation details to facilitate in-depth comparison and analysis. Quality assessments are then introduced for both qualitative and quantitative evaluation. Finally, this survey explores insights gained, outlining current challenges and prospects of AIGC-brain. As a pioneering survey, this article paves the way for future advances in AIGC-brain research. © 2020 IEEE.

关键词： Taxonomies

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Golden Jackal Optimization Algorithm for Mobile Robotic Path Planning

An Adaptive Golden Jackal Optimization Algorithm for Mobile ...

引用

2024 International Conference on Mechatronics and Intelligent Control, ICMIC 2024

作者： Chen, Siwen Zheng, Xiujuan Shanghai United Imaging Healthcare Co. Ltd. Shanghai China Engineering Research Center for Metallurgical Automation and Measurement Technology of Ministry of Education Wuhan University of Science and Technology Wuhan China Institute of Robotics and Intelligent Systems Wuhan University of Science and Technology Wuhan China

ISBN: (数字)9781510686847

ISBN: (纸本)9781510686830

Given the shortcomings of the traditional Golden Jackal Optimization (GJO) algorithm, including limited accuracy and slow convergence speed in solving mobile robot path planning problems, an improved adaptive Golden Jackal Optimization (IAGJO) method is proposed. Firstly, a nonlinear adaptive energy strategy is presented to adjust the energy decay pattern, balancing global and local search. Secondly, an enhanced position update mechanism based on Cauchy and Gaussian mutation increases population diversity and guide the search based on optimal individuals, thereby facilitating efficient exploration of unknown regions and avoiding local optima. Finally, the IAGJO algorithm is applied to mobile robot path planning (MRPP), demonstrating that the IAGJO achieves shorter path lengths and higher search efficiency, exhibiting significant advantages over existing methods. © 2025 SPIE.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Prototype of an intelligent textile based robot skin to expand potential applications for cobot's 8

Prototype of an intelligent textile based robot skin to expa...

引用

8th International Conference on Mechanical Engineering and robotics Research, ICMERR 2023

作者： Niquet, Kirubagaran Patel, Nikunjkumar Schrodel, Frank Jahn, Matthias Varelmann, Sven Schmalkalden University of Applied Sciences Mechatronics and Robotics Thuringia Germany Schmalkalden University of Applied Sciences Automation Technology and Robotics Thuringia Germany ITP GmbH Engineers for Smart Textiles Germany B and R Industrie-Elektronik GmbH Germany

ISBN: (纸本)9798350330519

Human Robot Collaboration (HRC) already dates couple of decades back. However, as Industry 4.0 and 5.0 demands smart human-centered production technologies, more concerns has been raised in the recent years regarding optimization and adaption of collaborative robots (Cobots). The core idea of HRC focuses on sharing the same workspace and performing a joint task, by both robot and humans. This paper focuses mainly on the development of a textile-based cover for industrial robots, integrated by several sensor arrays, resulting in enabling the sense of the human in the vicinity of the robot. This information is further utilized to manipulate the standard robot control algorithm to facilitate a safe collaboration by adaptive speed control based on the distance of human and robot. Additionally, the cover material is based on textile, which in terms of passive safety, facilitates cushioning effect when collision is occurred. In terms of active safety, it provides a wide area of sensing with several proximity sensors integrated over the skin. © 2023 IEEE.

关键词： Intelligent robots

来源：评论

学校读者我要写书评

暂无评论

Advancement in Smart Cane technology: Enhancing Mobility for the Visually Impaired Using ROS and LiDAR 6

Advancement in Smart Cane Technology: Enhancing Mobility for...

引用

6th International Conference on robotics and automation in Industry, ICRAI 2024

作者： Zafar, Saqib Maqbool, Hafiz Farhan Ahmad, Naveed Ali, Arham Moeizz, Abdul Ali, Faizan Taborri, Juri Rossi, Stefano University of Tuscia Department of Economics Engineering Society and Business Organization VT Viterbo01100 Italy University of Engineering and Technology Lahore Department of Mechanical Mechatronics and Manufacturing Engineering Faisalabad Campus Lahore38000 Pakistan National Center of Robotics and Automation Human-Centred Robotics Lab Pakistan

ISBN: (纸本)9798350355703

Visual impairment affects the ability to navigate independently in an unknown environment due to reliance on human/dog assistance, potential miscommunication, and discomfort during mobility. To make the visually impaired (VI) individuals self-reliant and confident in their mobility the proposed system has been developed that contains a light detection and ranging (LiDAR) sensor for obstacle detection and two omni-wheels coupled with the DC gear encoder motors for precise movement in any direction without lifting the cane. Hector Simultaneous Localization and Mapping (SLAM), A, and steering wheel algorithms have been implemented in the robot operating system (ROS) for real-time environment mapping, efficient path planning, and navigating in an unknown indoor static environment, respectively. The Raspberry Pi 3B+ and Arduino Mega 2560 are used in the master-slave configuration for decision-making on path planning and controlling the maneuverability of the system in real-time. The proposed system in the paper is successfully tested on one subject in two indoor environments. The results demonstrate that the system serves as an assistive mobile robot, helping the VI individual to navigate confidently in an unknown environment and reach the destination without assistance. © 2024 IEEE.

关键词： Motion planning

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：