检索结果-内蒙古大学图书馆

IEEE Instrumentation and Measurement Technology Conference

作者： Robert Milijaš Juraj Oršulić Stjepan Bogdan Laboratory for Robotics and Intelligent Control Systems Faculty of Electrical Engineering and Computing University of Zagreb Zagreb Croatia

ISBN: (数字)9781728144603

ISBN: (纸本)9781728144610

In this paper we use the underlying pose graph structure of graph SLAM to allow the user to inspect and intervene into the Simultaneous Localization and Mapping (SLAM) process. With post-processing the map by inserting custom constraints into the optimization problem, the user can improve the quality of the map obtained as the final SLAM result. We refer to this inspection and intervention process as interactive SLAM. The mathematical background, which allows such interventions, is laid out, and a software implementation is used to improve the quality of a map created at the Faculty of Electrical Engineering and Computing, University of Zagreb.

关键词： SLAM robotics Interactive SLAM supersonic low altitude missile robotics maps software implementation ELECTRICAL ENGINEERING odometry

来源：评论

学校读者我要写书评

暂无评论

Decoding split-frequency representation for cross-scale tracking

引用

Neural Networks 2025年 189卷 107587页

作者： Zhang, Yuanming Sun, Hao State Key Laboratory of Robotics and Systems Harbin Institute of Technology Harbin150001 China Research Institute of Intelligent Control and Systems Harbin Institute of Technology Harbin150001 China Bio-Computing Research Center Harbin Institute of Technology Shenzhen Shenzhen518055 China

Learning tailored target representations for tracking is a promising direction in visual object tracking. Most state-of-the-art methods utilize autoencoders to generate representations by reconstructing the target's appearance. However, these reconstructions are often augmented to mimic scale jitter and alteration, neglecting physical scale observations such as those in aerial videos. This article addresses the challenge of representation learning for cross-scale tracking in generalized scenarios. Specifically, we incorporate target scale directly into the positional encoding, indicating scale through relative pixel density rather than the conventional metric of image resolution. This scale-aware encoding is then integrated into the proposed asymptotic hierarchy of decoders, designed to reconstruct representations by emphasizing the restoration of high- and low-frequency features at large and tiny scales. The reconstruction process is guided by supervised learning using split losses, enabling the generation of robust cross-scale representations for generic objects. Extensive experiments on six benchmarks — GOT-10k, LaSOT, TrackingNet, DTB70, UAV123, and TNL2K — validate the superior performance of our method. Additionally, our tracker achieves a remarkable speed of 123 frames per second on a Graphics Processing Unit, surpassing the previous best autoencoder-based tracker. The code and raw results will be made publicly available at: https://***/pellab/DSC. © 2025 Elsevier Ltd

关键词： Aircraft detection

来源：评论

学校读者我要写书评

暂无评论

Improved Cascade Mask RCNN Single Character Detection Algorithm for Cast Pipe

Improved Cascade Mask RCNN Single Character Detection Algori...

引用

Big Data & Artificial Intelligence & Software Engineering (ICBASE), International Conference on

作者： Fuli Xu Yu Wang Yan Jiang Huaizhen Wang Yong Cui Ye Tao Yisheng Wang Qi Zhang School of Software Shenyang University of Technology Shenyang China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang China Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China Shanghai Ballsnow Intelligent Technology Co. Ltd Shanghai China Shenyang Zhongke Microcyber Technology Co. Ltd Shenyang China

Due to the interference of blurry background, character occlusion, and low background contrast in the Cast Pipe character images, the detection accuracy and real-time performance cannot meet the requirements of industrial scenes. To address these issues, this paper presents an improvement based on the Cascade Mask RCNN. Firstly, the Channel Attention Mechanism Module (Squeeze-and-Excitation, SE) is embedded into the ResNet structure. By constructing a bottleneck structure with two fully connected layers, the normalized weights are applied to each channel feature to enhance the network representation ability. Secondly, a bottom-up structure is introduced after the Feature Pyramid Networks (FPN) to transmit the strong localization information from lower-level features to higher-level semantic features. Thirdly, an adaptive pooling layer is added to allocate the candidate regions generated by the Region Proposal Network (RPN) to different scale feature maps. Additionally, skip connections are introduced between the bottom-level features and the highest-level features of each stage to reduce model parameters while retaining global representation capabilities. The improved algorithm is tested on a cast pipe dataset, achieving an average detection accuracy (mAP) of 98.7%, which is 2.7% higher than that of Cascade Mask RCNN. The accuracy indicates that the improved performance is superior to the original algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Application of Complementary Sliding Mode control with State Observer in Servo System of Voice Coil Motor

Application of Complementary Sliding Mode Control with State...

引用

第34届中国控制与决策会议

作者： Yang Liu Danping Jia Bingjie Zhao Tao Zhang Hualiang Zhang Hongyu Yan Xu Lu School of Artificial Intelligence Shenyang University of Technology School of Information Science and Engineering Shenyang University of Technology Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang Institute of Automation Chinese Academy of Sciences Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences School of Electrica l Engineering Dalian University of Technology

ISBN: (纸本)9781665478977

Due to the vulnerability of the voice coil motor(VCM) servo system to uncertain elements such as external disturbance,nonlinear friction,and inherent end impact,a dynamic model of the linear servo motor motion system with uncertainty is *** complementary sliding mode variable structure controller(CSMC) is built on the basis of the standard sliding mode control by merging the generalized sliding mode surface with the complimentary sliding mode *** study demonstrates that this controller can ensure the system's tracking error converges,suppresses uncertain factors,increases the system's transient reaction speed,and successfully reduces tracking ***,the saturation function is chosen as the switching function,which mitigates the sliding mode control chattering *** total interference is defined as the unmeasured and unknown interference in the mathematical model of the *** system's position and total disturbance are estimated using the nonlinear extended state observer(ESO).The estimated total disturbance is then feed-forward corrected to the control *** a result,a nonlinear extended state observer-based closed-loop complementary sliding mode position control technique is ***,the system experiment demonstrates the effectiveness and feasibility of the suggested control *** complimentary sliding mode control system with state observer offers a high degree of tracking accuracy and robustness,which considerably minimizes the system's tracking error.

关键词： Voice coil motor Complementary sliding mode control Extended state observer Servo system

来源：评论

学校读者我要写书评

暂无评论

Analytic Compact Model of Short-channel Cylindrical ballistic GAA MOSFET Including SDT effect 3

Analytic Compact Model of Short-channel Cylindrical ballisti...

引用

2020 3rd International Conference on Advanced Algorithms and control Engineering, ICAACE 2020

作者： Cheng, He Zhang, Chao Liu, Tiefeng Yang, Zhijia Zhang, Zhipeng Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang110016 China Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110169 China

We have proposed an analytic compact model describing the drain current characteristics valid in all operating regions, for ultra-short channel cylindrical gate-all-around metal-oxide-semiconductor field-effect transistors considering source-to-drain tunnelling effect. The drain-induced barrier lowering had been incorporated from one two-dimensional analysis in our previous compact model. In this study, to represent the energy level profile along the device channel direction into the Wentzel-Kramers-Brillouin approximation by substituting a parabolic function, we can analytically derive the expressions of the transmission coefficients for source-to-drain tunneling. In the subthreshold region, the source-to-drain tunneling current then can be evaluated using the Landauer formula. Finally, a fully analytic compact model is proposed for representing the drain current in all operating regions. The results compared with non-equilibrium Green's function transport simulations can be obtained in a good agreement. © Published under licence by IOP Publishing Ltd.

关键词： Drain current

来源：评论

学校读者我要写书评

暂无评论

Research on the method of path planning for slag-removing on the surface of zinc pot

Research on the method of path planning for slag-removing on...

引用

第33届中国控制与决策会议

作者： Kebo LI Ling XIONG Zhenzhou ZHANG Gang CHEN Engineering Research Center for Metallurgical Automation and Measurement Technology of Ministry of Education Institute of Robotics and Intelligent Systems Wuhan University of Science and Technology Key Laboratory of Metallurgical Equipment and Control Technology Wuhan University of Science and Technology

During the production process of cold-rolled hot-dip galvanizing,the slag on the surface of the zinc pot will affect the quality of the *** zinc slag is mostly collected manually or by robots at *** effect of manual salvage is unstable and the operation is *** robot cannot identify the location of the zinc slag and can only salvage it according to a fixed rule,resulting in low *** response to the above problems,a zinc pot slag path planning method based on the greedy algorithm is proposed in this *** zinc pot area is divided,the image processing method is used to identify and locate the zinc slag to be *** the priority of the zinc pot,the obstacle avoidance problem and the restriction of the weight limit of the slag-removing tool are proposed in combination with the process *** three salvage strategies based on the greedy algorithm,the shortest distance,the maximum weight,and the minimum weight are proposed *** results show that the greedy algorithm strategy based on the shortest distance performs best,consumes the least energy,and the algorithm runs for a shorter *** can significantly improve the efficiency of zinc pot slag removal,realize intelligent control of slag removal technology,and can be applied to the actual production of zinc pot slag removal.

关键词： Slag from zinc pot Intelligent control Greedy algorithm Path planning Shortest distance strategy

来源：评论

学校读者我要写书评

暂无评论

Research on Intelligent Protection Technology for Distribution Network with Distributed Generation

Research on Intelligent Protection Technology for Distributi...

引用

IEEE Advanced Information Technology, Electronic and Automation control Conference (IAEAC)

作者： Shijie Cui Peng Zeng Zhongfeng Wang Chunhe Song State Key Laboratory of Robotics Chinese Academy of Sciences Shenyang China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China University of Chinese Academy of Sciences Beijing China Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China

ISBN: (数字)9781728180281

ISBN: (纸本)9781728180298

Connecting large-scale distributed generation to a distribution network is complex as it is difficult to set the current protection limit within a traditional distribution network. This paper proposes a distributed protection and control scheme based on reinforcement learning for a distribution network connected to a distributed generation system. This research introduces the idea of transforming this distribution network protection problem into a multi-agent reinforcement learning problem. The concrete construction method of the reinforcement learning environment and deep Q-learning network is described. The algorithm training process is presented and the algorithm training and verification environment is built.

关键词： Training Uncertainty Power supplies Distribution networks Reinforcement learning Power system stability Distributed power generation

来源：评论

学校读者我要写书评

暂无评论

Position Sensorless control of Permanent Magnet Synchronous Motor Based on Adaptive Sliding Mode Observer

Position Sensorless Control of Permanent Magnet Synchronous ...

引用

2021 China Automation Congress, CAC 2021

作者： Zhang, Tao Xiong, Yingjie Wang, Bolun Yan, Hongyu Chen, Xiyou School of Electrical Engineering Dalian University of Technology Dalian China Shenyang Institute of Automation Chinese Academy of Sciences 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 College Of Information Science and Engineering Northeastern University Shenyang China School of Artificial Intelligence Shenyang University of Technology Shenyang China

ISBN: (纸本)9781665426473

Permanent magnet synchronous motors(PMSM) are popular in AC motor applications due to their small size, high efficiency. They have appeared widely in various areas of life. Due to the high-frequency chattering problem caused by sliding mode observer sensorless control of PMSM, an SMO with piecewise control function is designed in this *** the same time, based on the back EMF output of the SMO, the gain of the SMO is adapted to reduce the system bucket vibration problem caused by the conventional SMO. Finally, a simulation experiment was carried out in MATLAB/SIMULINK and compared with the conventional SMO. The results show that the improved SMO has achieved a better control effect. © 2021 IEEE

关键词： Sensorless control

来源：评论

学校读者我要写书评

暂无评论

control of Smart Buildings and Utility-Scale Batteries Enabling 24/7 Carbon-Free Energy*

Control of Smart Buildings and Utility-Scale Batteries Enabl...

引用

European control Conference (ECC)

作者： Faran A. Qureshi Jeff S. Shamma Robotics Intelligent Systems and Control (RISC) Laboratory Computer Electrical and Mathematical Sciences and Engineering (CEMSE) Division King Abdullah University of Science and Technology (KAUST) Thuwal Saudi Arabia University of Illinois at Urbana-Champaign USA

Wind power is a clean and sustainable source of electricity, but its intermittent nature creates challenges for its grid integration. Utility-scale batteries are a popular and effective solution to make wind power dispatchable, however, batteries are expensive and increase the overall cost of operation. In this paper, we propose utilizing the flexibility in the consumption of smart buildings to reduce the size of the utility-scale batteries needed for the dispatchability of wind energy. A method based on stochastic optimization is proposed to compute the dispatch plan required to participate in the day-ahead energy market. A stochastic model predictive controller is proposed for the control of the buildings and batteries to track the dispatch plan in real-time. Simulations are carried out with realistic building models and real weather, wind power production, and forecast data. Results demonstrate that utilizing the flexibility of building thermodynamics can significantly reduce the size (and usage) of the required battery for making the wind power production dispatchable.

关键词： Smart buildings Computational modeling Stochastic processes Production Wind power generation Predictive models Data models

来源：评论

学校读者我要写书评

暂无评论

Catch Planner: Catching High-Speed Targets in the Flight

arXiv

引用

arXiv 2023年

作者： Yu, Huan Wang, Pengqin Wang, Jin Ji, Jialin Zheng, Zhi Tu, Jie Lu, Guodong Meng, Jun Zhu, Meixin Shen, Shaojie Gao, Fei The State Key Laboratory of Fluid Power and Mechatronic Systems School of Mechanical Engineering Zhejiang University Hangzhou310027 China The Engineering Research Center for Design Engineering and Digital Twin of Zhejiang Province School of Mechanical Engineering Zhejiang University Hangzhou310027 China Robotics Institute of Zhejiang University Hangzhou310027 China Hong Kong The State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University Hangzhou310027 China Huzhou Institute of Zhejiang University Huzhou313000 China School of Electrical Engineering Zhejiang University Hangzhou310027 China The Hong Kong University of Science and Technology Guangzhou China

Catching high-speed targets in the flight is a complex and typical highly dynamic task. However, existing methods require manual setting of catching height or time, resulting in lacks of adaptability and flexibility and cannot deal with multiple targets. To bridge this gap, we propose a planning-with-decision scheme called Catch Planner. For sequential decision making, a lightweight policy search method based on deep reinforcement learning is proposed. It is jointly trained with the motion planning and decoupled from physics to speed up training. For motion planning, we propose a trajectory optimization method that jointly optimizes the highly coupled catching time and terminal state. The core is the flexible-terminal constraint transcription. It converts the three unique constraints of catching into differentiable metrics, including equality constraints for terminal position and time, and inequality constraints that enable reasonable terminal position offset and attitude relaxation. In addition, sparse parameterization based on MINCO class considers both dynamic feasibility and collision avoidance constraints. As a result, a generally constrained quadrotor planning problem is transformed into an unconstrained optimization that can be solved reliably and efficiently. We also propose an online iterative optimization method for predicting differentiable trajectories of targets. Catch Planner provides a new paradigm for the combination of learning and planning, where all algorithms can be run in real time onboard at 100hz. Extensive experiments are carried out in real-world and simulated scenes to verify the robustness and expansibility when facing a variety of high-speed flying targets. Copyright © 2023, The Authors. All rights reserved.

关键词： Decision making

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：