检索结果-内蒙古大学图书馆

Artificial Intelligence and Electromechanical Automation (AIEA), International Conference on

作者： Honghua Zhao Jian Zhao Yifei Lin Qifei Han Mianpeng Chen University of Jinan School of Mechanical Engineering Jinan China Shandong University School of Control Science and Engineering Jinan China Shandong Institute of Intelligent Robot & Applied Technology Jining China CNC System R&D Department GSK CNC Equipment Co. Ltd. Guangzhou China

ISBN: (数字)9781728182889

ISBN: (纸本)9781728182896

The accuracy of industrial robot kinematics parameters directly affects its absolute positioning accuracy. Based on Modify Denavit-Hartenberg (MD-H) kinematics theory, a more accurate calibration method for kinematic parameters of industrial robots is proposed in this paper. It takes the kinematics parameters, deceleration ratio and coupling coefficient of the robot as error parameters to establish the error model. The calibration experiment and accuracy verification experiment are designed by laser tracker. After the introduction of the reduction ratio and the coupling coefficient calibration, the absolute positioning error of the robot in all directions has been greatly improved, and the overall average accuracy of the robot is increased by 91.42% compared with the uncalibrated, and is increased by 81.02% compared with the without introducing the deceleration ratio and coupling coefficient.

关键词： component industrial robot Denavit-Hartenberg kinematics error model calibration experiment accuracy verification experiment industrial robots error model CALIBRATION METHODS robot kinematics deceleration rate absolute location laser trackers

来源：评论

学校读者我要写书评

暂无评论

LimeSoDa: A Dataset Collection for Benchmarking of Machine Learning Regressors in Digital Soil Mapping

arXiv

引用

arXiv 2025年

作者： Schmidinger, Jonas Vogel, Sebastian Barkov, Viacheslav Pham, Anh-Duy Gebbers, Robin Tavakoli, Hamed Correa, Jose Tavares, Tiago R. Filippi, Patrick Jones, Edward J. Lukas, Vojtech Boenecke, Eric Ruehlmann, Joerg Schroeter, Ingmar Kramer, Eckart Paetzold, Stefan Kodaira, Masakazu Wadoux, Alexandre M.J.-C. Bragazza, Luca Metzger, Konrad Huang, Jingyi Valente, Domingos S.M. Safanelli, Jose L. Bottega, Eduardo L. Dalmolin, Ricardo S.D. Farkas, Csilla Steiger, Alexander Horst, Taciara Z. Ramirez-Lopez, Leonardo Scholten, Thomas Stumpf, Felix Rosso, Pablo Costa, Marcelo M. Zandonadi, Rodrigo S. Wetterlind, Johanna Atzmueller, Martin Osnabrück University Joint Lab Artificial Intelligence and Data Science Osnabrück Germany Department of Agromechatronics Potsdam Germany Piracicaba Brazil The University of Sydney Sydney Institute of Agriculture Sydney Australia Mendel University in Brno Department of Agrosystems and Bioclimatology Brno Czech Republic Leibniz Institute of Vegetable and Ornamental Crops Next Generation Horticultural Systems Grossbeeren Germany Eberswalde University for Sustainable Development Landscape Management and Nature Conservation Eberswalde Germany Soil Science and Soil Ecology Bonn Germany Tokyo University of Agriculture and Technology Institute of Agriculture Tokyo Japan LISAH Univ. Montpellier AgroParisTech INRAE IRD L'Institut Agro Montpellier France Agroscope Field-Crop Systems and Plant Nutrition Nyon Switzerland University of Wisconsin-Madison Department of Soil Science Madison United States Federal University of Viçosa Department of Agricultural Engineering Viçosa Brazil Woodwell Climate Research Center Falmouth United States Academic Coordination Santa Maria Brazil Soil Department Santa Maria Brazil Division of Environment and Natural Resources Aas Norway University of Rostock Chair of Geodesy and Geoinformatics Rostock Germany Federal Technological University of Paraná Dois Vizinhos Brazil BÜCHI Labortechnik AG Data Science Department Flawil Switzerland Imperial College London Imperial College Business School London United Kingdom University of Tübingen Department of Geosciences Tübingen Germany University of Tübingen DFG Cluster of Excellence Machine Learning for Science’ Germany Bern University of Applied Sciences Competence Center for Soils Zollikofen Switzerland Simulation and Data Science Müncheberg Germany Federal University of Jataí Institute of Agricultural Sciences Jatai Brazil Federal University of Mato Grosso Instute of Agricultural and Environmental Scinces Sinop Brazil Department of Soil and Environment Skara

Digital soil mapping (DSM) relies on a broad pool of statistical methods, yet determining the optimal method for a given context remains challenging and contentious. Benchmarking studies on multiple datasets are needed to reveal strengths and limitations of commonly used methods. Existing DSM studies usually rely on a single dataset with restricted access, leading to incomplete and potentially misleading conclusions. To address these issues, we introduce an open-access dataset collection called Precision Liming Soil Datasets (LimeSoDa). LimeSoDa consists of 31 field- and farm-scale datasets from various countries. Each dataset has three target soil properties: (1) soil organic matter or soil organic carbon, (2) clay content and (3) pH, alongside a set of features. Features are dataset-specific and were obtained by optical spectroscopy, proximal- and remote soil sensing. All datasets were aligned to a tabular format and are ready-to-use for modeling. We demonstrated the use of LimeSoDa for benchmarking by comparing the predictive performance of four learning algorithms across all datasets. This comparison included multiple linear regression (MLR), support vector regression (SVR), categorical boosting (CatBoost) and random forest (RF). The results showed that although no single algorithm was universally superior, certain algorithms performed better in specific contexts. MLR and SVR performed better on high-dimensional spectral datasets, likely due to better compatibility with principal components. In contrast, CatBoost and RF exhibited considerably better performances when applied to datasets with a moderate number ( © 2025, CC BY-SA.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Fast ORB-SLAM without Keypoint Descriptors

arXiv

引用

arXiv 2020年

作者： Fu, Qiang Yu, Hongshan Wang, Xiaolong Yang, Zhengeng He, Yong Zhang, Hong Mian, Ajmal The National Engineering Laboratory for Robot Visual Perception and Control Technology College of Electrical and Information Engineering Hunan University China The Department of Computing Science University of Alberta Canada Quanzhou Institute of Industrial Design and Machine Intelligence Innovation Hunan University China The Southern University of Science and Technology Shenzhen China The School of Mathematics and Information Science Shaanxi Normal University China The Department of Computer Science The University of Western Australia WA6009 Australia

Indirect methods for visual SLAM are gaining popularity due to their robustness to environmental variations. ORB-SLAM2 [1] is a benchmark method in this domain, however, it consumes significant time for computing descriptors that never get reused unless a frame is selected as a keyframe. To overcome these problems, we present FastORB-SLAM which is light-weight and efficient as it tracks keypoints between adjacent frames without computing descriptors. To achieve this, a two stage descriptor-independent keypoint matching method is proposed based on sparse optical flow. In the first stage, we predict initial keypoint correspondences via a simple but effective motion model and then robustly establish the correspondences via pyramid-based sparse optical flow tracking. In the second stage, we leverage the constraints of the motion smoothness and epipolar geometry to refine the correspondences. In particular, our method computes descriptors only for keyframes. We test FastORB-SLAM on TUM and ICL-NUIM RGB-D datasets and compare its accuracy and efficiency to nine existing RGB-D SLAM methods. Qualitative and quantitative results show that our method achieves state-of-the-art accuracy and is about twice as fast as the ORB-SLAM2. Copyright © 2020, The Authors. All rights reserved.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

LimeSoDa: A dataset collection for benchmarking of machine learning regressors in digital soil mapping

引用

Geoderma 2025年 459卷

作者： Schmidinger, Jonas Vogel, Sebastian Barkov, Viacheslav Pham, Anh-Duy Gebbers, Robin Tavakoli, Hamed Correa, Jose Tavares, Tiago R. Filippi, Patrick Jones, Edward J. Lukas, Vojtech Boenecke, Eric Ruehlmann, Joerg Schroeter, Ingmar Kramer, Eckart Paetzold, Stefan Kodaira, Masakazu Wadoux, Alexandre M.J.-C. Bragazza, Luca Metzger, Konrad Huang, Jingyi Valente, Domingos S.M. Safanelli, Jose L. Bottega, Eduardo L. Dalmolin, Ricardo S.D. Farkas, Csilla Steiger, Alexander Horst, Taciara Z. Ramirez-Lopez, Leonardo Scholten, Thomas Stumpf, Felix Rosso, Pablo Costa, Marcelo M. Zandonadi, Rodrigo S. Wetterlind, Johanna Atzmueller, Martin Osnabrück University Joint Lab Artificial Intelligence and Data Science Osnabrück Germany Department of Agromechatronics Potsdam Germany Piracicaba Brazil The University of Sydney Sydney Institute of Agriculture Sydney Australia Mendel University in Brno Department of Agrosystems and Bioclimatology Brno Czech Republic Leibniz Institute of Vegetable and Ornamental Crops Next Generation Horticultural Systems Grossbeeren Germany Eberswalde University for Sustainable Development Landscape Management and Nature Conservation Eberswalde Germany —Soil Science and Soil Ecology Bonn Germany Tokyo University of Agriculture and Technology Institute of Agriculture Tokyo Japan LISAH Univ. Montpellier AgroParisTech INRAE IRD L'Institut Agro Montpellier France Agroscope Field-Crop Systems and Plant Nutrition Nyon Switzerland University of Wisconsin-Madison Department of Soil Science Madison United States Federal University of Viçosa Department of Agricultural Engineering Viçosa Brazil Woodwell Climate Research Center Falmouth United States Academic Coordination Santa Maria Brazil Soil Department Santa Maria Brazil Division of Environment and Natural Resources Aas Norway University of Rostock Chair of Geodesy and Geoinformatics Rostock Germany Federal Technological University of Paraná Dois Vizinhos Brazil BÜCHI Labortechnik AG Data Science Department Flawil Switzerland Imperial College London Imperial College Business School London United Kingdom University of Tübingen Department of Geosciences Tübingen Germany University of Tübingen DFG Cluster of Excellence ‘Machine Learning for Science’ Germany Bern University of Applied Sciences Competence Center for Soils Zollikofen Switzerland Simulation and Data Science Müncheberg Germany Federal University of Jataí Institute of Agricultural Sciences Jatai Brazil Federal University of Mato Grosso Instute of Agricultural and Environmental Scinces Sinop Brazil Department of Soil and Environment Skara S

关键词： Random forests

来源：评论

学校读者我要写书评

暂无评论

Real time backbone for semantic segmentation

arXiv

引用

arXiv 2019年

作者： Yang, Zhengeng Yu, Hongshan Fu, Qiang Sun, Wei Jia, Wenyan Sun, Mingui Mao, Zhi-Hong National Engineering Laboratory for Robot Visual Perception and Control Technology College of Electrical and Information Engineering Hunan University Lushan South Rd. Yuelu Dist. Changsha410082 China University of Pittsburgh University of Pittsburgh PittsburghPA United States Department of Electrical and Computer Engineering Department of Neurosurgery

The rapid development of autonomous driving in recent years presents lots of challenges for scene understanding. As an essential step towards scene understanding, semantic segmentation thus received lots of attention in past few years. Although deep learning based state-of-the-arts have achieved great success in improving the segmentation accuracy, most of them suffer from an inefficiency problem and can hardly applied to practical applications. In this paper, we systematically analyze the computation cost of Convolutional Neural Network(CNN) and found that the inefficiency of CNN is mainly caused by its wide structure rather than the deep structure. In addition, the success of pruning based model compression methods proved that there are many redundant channels in CNN. Thus, we designed a very narrow while deep backbone network to improve the efficiency of semantic segmentation. By casting our network to FCN32 segmentation architecture, the basic structure of most segmentation methods, we achieved 60.6% mIoU on Cityscape val dataset with 54 frame per seconds(FPS) on 1024 × 2048 inputs, which already outperforms one of the earliest real time deep learning based segmentation methods: ENet. Copyright © 2019, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Remote control library and GUI development for Russian crawler robot Servosila Engineer 13

Remote control library and GUI development for Russian crawl...

引用

13th International Conference on Electromechanics and robotics "Zavalishin's Readings", ER(ZR) 2018

作者： Mavrin, Ilya Lavrenov, Roman Svinin, Mikhail Sorokin, Sergey Magid, Evgeni Intelligent Robotics Department Higher School of Information Technology and Information Systems Kazan Federal University Russia Robot Dynamics and Control Laboratory College of Information Science and Engineering Ritsumeikan University Japan Mechanical Engineering Department Chuvash State University Russia

Recently a large variety of robots are available on the global market for a reasonable price. Often it turns out that even though a robot has a high-quality hardware and architecture, an original software of the robot may have a number of drawbacks or lacks some important features, which are required for a particular application of the robot. In such cases a user may decide to implement new libraries and functionalities using a provided by a manufacturer application programming interfaces as in most cases code of a commercial robot system is not an open-source. A number of our ongoing research projects concentrate on applications of various robots in urban search and rescue operations, and in most of these projects utilize Russian crawler robot Servosila Engineer. This paper describes the development of a new ROS-based control software and graphical user interface for Servosila Engineer robot. © The Authors, published by EDP Sciences.

关键词： Graphical user interfaces

来源：评论

学校读者我要写书评

暂无评论

System Design and Experiment of a Laryngeal Surgical robotic System 15

System Design and Experiment of a Laryngeal Surgical Robotic...

引用

15th International Conference on Ubiquitous robots, UR 2018

作者： Kim, Sang-Hwa Seo, Jong-Tae Woo, Jae Hong Yoon, Hyun-Soo Tae, Kyung Yi, Byung-Ju Division of Electrical Engineering Hanyang University Ansan Korea Republic of Department of Intelligent Robot Engineering Hanyang University Ansan Korea Republic of Department of Electronic Electrical Control and Instrumentation Engineering Hanyang University Ansan Korea Republic of Department of Otolaryngology-Head Hanyang University Neck Surgery College of Medicine Seoul Korea Republic of

ISBN: (纸本)9781538663349

A laryngeal surgical robotic system equipped with high quality 3-dimensional images and robot arms is developed to help the surgeon treat general diseases located at head and neck area. This paper is to describe a system configuration and demonstrate effectiveness of the laryngeal surgical robotic system. A mechanical construction of this system is based on a novel stackable parallel mechanism architecture. The EtherCAT communication protocol is used for real-time control. In order to confirm the effectiveness of the laryngeal surgical robotic system, experiments using phantom and cadaver were performed. © 2018 IEEE.

关键词： Real time control

来源：评论

学校读者我要写书评

暂无评论

Fast 3D detection of vehicles using density image of lidar

引用

Journal of Institute of control, robotics and Systems 2018年第12期24卷 1161-1169页

作者： Kim, Tae-Hyeong Park, Tae-Hyeong Department of Control and Robot Engineering Chungbuk National University Korea Republic of School of Electronics Engineering Chungbuk National University Korea Republic of

The deep-learning-based method is a costly method that requires the addition of a lot of learning data and hardware. This paper proposes a 3D vehicle detection method using only 3D lidar in autonomous vehicles. The proposed method generates density image and height image using point clouds. Candidates of the vehicle are detected from the complex image, and images for extracting features are generated from each candidate. In addition, we use the SVM (Support Vector Machine) instead of deep-learning, a low-cost learning method, to classify HOG (Histogram of Oriented Gradient) feature vectors. The proposed method can reduce the amount of computation as well as the execution time. The vehicle can be detected and the distance to the vehicle can be measured. Experimental results show the performance of the proposed method. © ICROS 2018.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

A VR-based upper limb rehabilitation hand robotic training system 15

A VR-based upper limb rehabilitation hand robotic training s...

引用

15th IEEE International Conference on Mechatronics and Automation, ICMA 2018

作者： Guo, Jian Li, Nan Guo, Shuxiang Tianjin Key Laboratory for Control Theory and Application in Complicated Systems and Biomedical Robot Laboratory Tianjin University of Technology Binshui Xidao 391 Tianjin China Intelligent Mechanical Systems Engineering Department Faculty of Engineering Kagawa University Takamatsu Kagawa Japan

ISBN: (纸本)9781538660720

With the development of science and technology, virtual reality technology has been applied to various fields. Virtual reality technology is proposed into rehabilitation medical treatment, which can avoid dull rehabilitation training, improve the initiative of patients' rehabilitation and improve the overall effect of rehabilitation training. In order to help patients with hand grab function training, we proposed a virtual reality-based upper limb rehabilitation hand training system. In this paper, we can obtain the bending angle data of fingers and force feedback through the upper limb rehabilitation hand robot with CyberGlove. We established the high precise 3D model, set up the mapping relationship between CyberGlove and the virtual hand to realize the human-computer interaction. Based on the previous work, a VR-based upper limb rehabilitation hand robotic training system is proposed and has collision detection and force feedback, which makes users feel more realistic when interacting with objects in the virtual environment. The relevant verification experiment confirmed that virtual hand and upper limb rehabilitation robot interact well, which increases the interest of training. © 2018 IEEE.

关键词： Patient treatment

来源：评论

学校读者我要写书评

暂无评论

Design of the speech control system for a upper limb rehabilitation robot based on wavelet de-noising 15

Design of the speech control system for a upper limb rehabil...

引用

15th IEEE International Conference on Mechatronics and Automation, ICMA 2018

作者： Guo, Shuxiang Wang, Zhi Guo, Jian Fu, Qiang Li, Nan Tianjin Key Laboratory for Control Theory and Applications in Complicated Systems and Biomedical Robot Laboratory Tianjin University of Technology Binshui Xidao Extension 391 Tianjin300384 China Intelligent Mechanical Systems Engineering Department Faculty of Engineering Kagawa University Takamatsu Kagawa Japan

ISBN: (纸本)9781538660720

In order to help stroke patients to go on rehabilitation training, a new type of exoskeleton upper limb rehabilitation robot based on biomechanics has been designed in this paper, and speech control has been implemented. The speech control is suitable for patients who can speak. Doctors or family members can also assist patients in training. The system can help patients with hemiplegia to recover the upper limbs and fingers movement function, at the same time, it has the characteristics of small size, more portable and convenient operation. It can also effectively solve the shortage of traditional doctors and patients' one to one rehabilitation training. It is convenient for patients to use in the family. Anybody can help patients with rehabilitation training and has a broad application prospect in the field of rehabilitation. Finally, the speech control system was tested and the master-slave control experiment was implemented. In order to better perform speech recognition and further reduce the noise in the environment, the original speech signals have been de-noised with wavelet transform . The experimental results showed that the success rate of post-noise speech control system rehabilitation training is higher, and the average correct recognition rate of speech control is 94%, thus the feasibility of the speech control system is verified. © 2018 IEEE.

关键词： control systems

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：