检索结果-内蒙古大学图书馆

IEEE Access 2024年 12卷 i-xi页

作者： Derek Abbott Sonia Aissa Anuradha Annaswamy Nirwan Ansari Jun Cai Kun-Shan Chen Yixin Chen J.-C. Chiao Ayman El-Baz Shaikh Fattah Hoay Gooi Maya Gokhale Chih-Lin Ⅰ Giuseppe Iannaccone Yumi Iwashita Bruce Jacob Abbas Jamalipour Bahram Javidi Weihua Jiang Okyay Kaynak Hulya Kirkici Germano Lambert-Torres Shengtao Li Michal Mrozowski Michele Nappi Dalma Novak Hugo Proença Yi Qian Zhihua Qu Susanto Rahardja Mehrdad Saif Ali Serpengüzel Peter H. Siegel Ashitey Trebi-Ollennu Daniela Tuninetti Ge Wang Keith A. Wear Andreas Weisshaar C. Patrick Yue Enrico Zio School of Electrical and Electronic Engineering University of Adelaide Adelaide SA Australia Institut National de la Recherche Scientifique (INRS) Québec City Canada Department of Mechanical Engineering Massachusetts Institute of Technology Cambridge MA USA Department of Electrical and Computer Engineering New Jersey Institute of Technology Newark NJ USA Concordia University Montreal Canada Guilin University of Technology Guilin China Washington University St. Louis MO USA Southern Methodist University Dallas TX USA University of Louisville/Bioengineering Department Louisville KY USA Department of Electrical and Electronic Engineering Bangladesh University of Engineering and Technology Dhaka Bangladesh Nanyang Technological University Jurong West Singapore Lawrence Livermore National Laboratory Livermore CA USA China Mobile Research Institute Beijing China University of Pisa Pisa Italy NASA-JPL California Institute of Technology Pasadena CA USA Florida Polytechnic University Lakeland FL USA The University of Sydney Sydney NSW Australia University of Connecticut Storrs CT USA Nagaoka University of Technology Nagaoka Niigata Japan Department of Electrical and Electronic Engineering Boğaziçi University Istanbul Turkey University of South Alabama Mobile AL USA Gnarus Institute Itajuba Brazil Xi’an Jiaotong University Xi’an China Gdansk University of Technology Gdansk Poland University of Salerno Fisciano Italy Octane Wireless Hanover MD USA University of Beira Interior Covilhã Portugal Department of Electrical and Computer Engineering University of NebraskaLincoln Lincoln NE USA University of Central Florida Orlando Florida USA Singapore Institute of Technology 10 Dover Dr Singapore Infocomm Technology Cluster 10 Dover Dr Singapore University of Windsor Windsor Canada Department of Physics Koç University Istanbul Turkey California Institute of Technology (CalTech) Pasadena California USA NASA-JPL Mobility and Robotics Systems S

来源：评论

学校读者我要写书评

暂无评论

From multi-modal property dataset to robot-centric conceptual knowledge about household objects

arXiv

引用

arXiv 2019年

作者： Thosar, Madhura Mueller, Christian A. Jaeger, Georg Schleiss, Johannes Pulugu, Narender Chennaboina, Ravi Mallikarjun Jeevangekar, Sai Vivek Birk, Andreas Pfingsthorn, Max Zug, Sebastian Institute for Intelligent Cooperating Systems Faculty of Computer Science Otto-von-Guericke University Magdeburg Germany Robotics Computer Science & Electrical Engineering Department Jacobs University Bremen Germany Institute for Computer Science Technische Universität Bergakademie Freiberg Germany OFFIS Institute for Information Technology Oldenburg Germany

Tool-use applications in robotics require conceptual knowledge about objects for informed decision making and object interactions. State-of-the-art methods employ hand-crafted symbolic knowledge which is defined from a human perspective and grounded into sensory data afterwards. However, due to different sensing and acting capabilities of robots, their conceptual understanding of objects must be generated from a robot's perspective entirely, which asks for robot-centric conceptual knowledge about objects. With this goal in mind, this article motivates that such knowledge should be based on physical and functional properties of objects. Consequently, a selection of ten properties is defined and corresponding extraction methods are proposed. This multi-modal property extraction forms the basis on which our second contribution, a robot-centric knowledge generation is build on. It employs unsupervised clustering methods to transform numerical property data into symbols, and Bivariate Joint Frequency Distributions and Sample Proportion to generate conceptual knowledge about objects using the robot-centric symbols. A preliminary implementation of the proposed framework is employed to acquire a dataset comprising physical and functional property data of 110 houshold objects. This Robot-Centric dataSet (RoCS) is used to evaluate the framework regarding the property extraction methods, the semantics of the considered properties within the dataset and its usefulness in real-world applications such as tool substitution. Copyright © 2019, 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

Port-Hamiltonian Approach to Neural Network Training

Port-Hamiltonian Approach to Neural Network Training

引用

IEEE Annual Conference on Decision and Control

作者： Stefano Massaroli Michael Poli Federico Califano Angela Faragasso Jinkyoo Park Atsushi Yamashita Hajime Asama Department of Precision Engineering The University of Tokyo Tokyo Japan Department of Industrial and Systems Engineering Korea Advanced Institute of Science and Technology (KAIST) Daejeon South Korea Faculty of Electrical Engineering Mathematics & Computer Science (EWI) Robotics and Mechatronics (RAM) University of Twente Enschede The Netherlands

ISBN: (数字)9781728113982

ISBN: (纸本)9781728113999

Neural networks are discrete entities: subdivided into discrete layers and parametrized by weights which are iteratively optimized via difference equations. Recent work proposes networks with layer outputs which are no longer quantized but are solutions of an ordinary differential equation (ODE);however, these networks are still optimized via discrete methods (e.g. gradient descent). In this paper, we explore a different direction: namely, we propose a novel framework for learning in which the parameters themselves are solutions of ODEs. By viewing the optimization process as the evolution of a port-Hamiltonian system, we can ensure convergence to a minimum of the objective function. Numerical experiments have been performed to show the validity and effectiveness of the proposed methods.

关键词： Training Biological neural networks Convergence Mathematical model Optimization Linear programming

来源：评论

学校读者我要写书评

暂无评论

CNN-LIDAR pedestrian classification: combining range and reflectance data

CNN-LIDAR pedestrian classification: combining range and ref...

引用

IEEE International Conference on Vehicular Electronics and Safety (ICVES)

作者： Gledson Melotti Alireza Asvadi Cristiano Premebida Department of Electrical and Computer Engineering Institute of Systems and Robotics University of Coimbra Portugal

The use of multiple sensors in perception systems is becoming a consensus in the automotive and robotics industries. Camera is the most popular technology, however, radar and LIDAR are increasingly being adopted more often in protection and safety systems for object/obstacle detection. In this paper, we particularly explore the LIDAR sensor as an inter-modality technology which provides two types of data, range (distance) and reflectance (intensity return), and study the influence of high-resolution distance/depth (DM) and reflectance maps (RM) on pedestrian classification using a deep Convolutional Neural Network (CNN). Pedestrian protection is critical for advanced driver assistance system (ADAS) and autonomous driving, and it has regained particular attention recently for known reasons. In this work, CNN-LIDAR based pedestrian classification is studied in three distinct cases: (i) having a single modality as input in the CNN, (ii) by combining distance and reflectance measurements at the CNN input-level (early fusion), and (iii) combining outputs scores from two single-modal CNNs (late fusion). Distance and intensity (reflectance) raw data from LIDAR are transformed to high-resolution (dense) maps which allow a direct implementation on CNNs both as single or multi-channel inputs (early fusion approach). In terms of late-fusion, the outputs from individual CNNs are combined by means of non-learning rules, such as: minimum, maximum, average, product. Pedestrian classification is evaluated on a `binary classification' dataset created from the KITTI Vision Benchmark Suite, and results are shown for the three cases.

关键词： Laser radar Feature extraction Cameras Sensors Three-dimensional displays Safety Automotive engineering

来源：评论

学校读者我要写书评

暂无评论

Primal-dual optimization methods for large-scale and distributed data analytics

arXiv

引用

arXiv 2019年

作者： Jakovetić, Dušan Bajović, Dragana Xavier, João Moura, José M.F. Faculty of Sciences University of Novi Sad Novi Sad Serbia Faculty of Technical Sciences University of Novi Sad Novi Sad Serbia Instituto Superior Tećnico Universidade de Lisboa Institute for Systems and Robotics Laboratory for Robotics and Engineering Systems Lisbon Portugal Department of Electrical and Computer Engineering Carnegie Mellon University PittsburghPA United States

The augmented Lagrangian method (ALM) is a classical optimization tool that solves a given "difficult" (constrained) problem via finding solutions of a sequence of "easier" (often unconstrained) sub-problems with respect to the original (primal) variable, wherein constraints satisfaction is controlled via the so-called dual variables. ALM is highly flexible with respect to how primal sub-problems can be solved, giving rise to a plethora of different primal-dual methods. The powerful ALM mechanism has recently proved to be very successful in various large scale and distributed applications. In addition, several significant advances have appeared, primarily on precise complexity results with respect to computational and communication costs in the presence of inexact updates and design and analysis of novel optimal methods for distributed consensus optimization. We provide a tutorial-style introduction to ALM and its analysis via control-theoretic tools, survey recent results, and provide novel insights in the context of two emerging applications: federated learning and distributed energy trading. Copyright © 2019, The Authors. All rights reserved.

关键词： Constrained optimization

来源：评论

学校读者我要写书评

暂无评论

Metrics Reloaded: Recommendations for image analysis validation

arXiv

引用

arXiv 2022年

作者： Maier-Hein, Lena Reinke, Annika Godau, Patrick Tizabi, Minu D. Buettner, Florian Christodoulou, Evangelia Glocker, Ben Isensee, Fabian Kleesiek, Jens Kozubek, Michal Reyes, Mauricio Riegler, Michael A. Wiesenfarth, Manuel Emre Kavur, A. Sudre, Carole H. Baumgartner, Michael Eisenmann, Matthias Heckmann-Nötzel, Doreen Rädsch, Tim Acion, Laura Antonelli, Michela Arbel, Tal Bakas, Spyridon Benis, Arriel Blaschko, Matthew B. Jorge Cardoso, M. Cheplygina, Veronika Cimini, Beth A. Collins, Gary S. Farahani, Keyvan Ferrer, Luciana Galdran, Adrian Ginneken, Bram Van Haase, Robert Hashimoto, Daniel A. Hoffman, Michael M. Huisman, Merel Jannin, Pierre Kahn, Charles E. Kainmueller, Dagmar Kainz, Bernhard Karargyris, Alexandros Karthikesalingam, Alan Kenngott, Hannes Kofler, Florian Kopp-Schneider, Annette Kreshuk, Anna Kurc, Tahsin Landman, Bennett A. Litjens, Geert Madani, Amin Maier-Hein, Klaus Martel, Anne L. Mattson, Peter Meijering, Erik Menze, Bjoern Moons, Karel G.M. Müller, Henning Nichyporuk, Brennan Nickel, Felix Petersen, Jens Rajpoot, Nasir Rieke, Nicola Saez-Rodriguez, Julio Sánchez, Clara I. Shetty, Shravya Smeden, Maarten Van Summers, Ronald M. Taha, Abdel A. Tiulpin, Aleksei Tsaftaris, Sotirios A. Calster, Ben Van Varoquaux, Gaël Jäger, Paul F. Heidelberg Division of Intelligent Medical Systems and HI Helmholtz Imaging Germany Faculty of Mathematics and Computer Science and Medical Faculty Heidelberg University Heidelberg Germany NCT Heidelberg a partnership between DKFZ University Medical Center Heidelberg Germany Faculty of Mathematics and Computer Science Heidelberg University Heidelberg Germany Heidelberg Division of Intelligent Medical Systems Germany partner site Frankfurt/Mainz a partnership between DKFZ and UCT Frankfurt-Marburg Germany Heidelberg Goethe University Frankfurt Germany Department of Medicine Goethe University Frankfurt Germany Department of Informatics Frankfurt Cancer Insititute Germany Department of Computing Imperial College London London United Kingdom Heidelberg Division of Medical Image Computing and HI Applied Computer Vision Lab Germany Institute for AI in Medicine University Medicine Essen Essen Germany Centre for Biomedical Image Analysis Faculty of Informatics Masaryk University Brno Czech Republic ARTORG Center for Biomedical Engineering Research University of Bern Bern Switzerland Department of Radiation Oncology University Hospital Bern University of Bern Bern Switzerland Simula Metropolitan Center for Digital Engineering Oslo Norway UiT The Arctic University of Norway Romsø Norway Heidelberg Division of Biostatistics Germany Heidelberg Division of Intelligent Medical Systems Division of Medical Image Computing HI Applied Computer Vision Lab Germany MRC Unit for Lifelong Health and Ageing UCL Centre for Medical Image Computing Department of Computer Science University College London London United Kingdom School of Biomedical Engineering and Imaging Science King’s College London London United Kingdom Heidelberg Division of Medical Image Computing Germany Instituto de Cálculo CONICET – Universidad de Buenos Aires Buenos Aires Argentina Centre for Medical Image Computing University College London London United Kingdom McGill University Montréal

Increasing evidence shows that flaws in machine learning (ML) algorithm validation are an underestimated global problem. Particularly in automatic biomedical image analysis, chosen performance metrics often do not reflect the domain interest, thus failing to adequately measure scientific progress and hindering translation of ML techniques into practice. To overcome this, we created Metrics Reloaded, a comprehensive framework guiding researchers in the problem-aware selection of metrics. It was developed by a large international consortium in a multi-stage Delphi process and is based on the novel concept of a problem fingerprint – a structured representation of the given problem that captures all aspects that are relevant for metric selection, from the domain interest to the properties of the target structure(s), data set and algorithm output. Based on the problem fingerprint, users are guided through the process of choosing and applying appropriate validation metrics while being made aware of potential pitfalls. Metrics Reloaded targets image analysis problems that can be interpreted as a classification task at image, object or pixel level, namely image-level classification, object detection, semantic segmentation, and instance segmentation tasks. To improve the user experience, we implemented the framework in the Metrics Reloaded online tool. Following the convergence of ML methodology across application domains, Metrics Reloaded fosters the convergence of validation methodology. Its applicability is demonstrated for various biomedical use cases. © 2022, CC BY.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Robot Force Control on a Beating Heart (22, pg 1736, 2017)

引用

IEEE-ASME TRANSACTIONS ON MECHATRONICS 2017年第6期22卷 2802-2802页

作者： Cortesao, Rui Dominici, Michel Department of Electrical and Computer Engineering Institute of Systems and Robotics University of Coimbra Coimbra Portugal Institute of Systems and Robotics University of Coimbra Coimbra Portugal

Cardiac interventions have to deal with several difficulties, where heart motion is a major one. This paper addresses the heart motion compensation problem under contact, relying on robot force control techniques. A double active observer (AOB) architecture is proposed to tackle precise force control in the presence of heart motion. One AOB controls the desired interaction force, and the other one is responsible for compensating heart motion autonomously. Three-degrees of freedom (DOF) force tracking on top of a beating heart is presented, showing that with the proposed control architecture, it is possible to have force controlled interventions with root mean square errors below 0.56 N (based on raw data). The 4-DOF whole arm manipulator (WAM) from Barrett Technologies is the medical arm, while another 3-DOF robot carrying an ex vivo heart generates heart motion based on recorded biosignals.

关键词： Heart Force Force control Robot sensing systems computer architecture Motion compensation

来源：评论

学校读者我要写书评

暂无评论

Energetic electron precipitation driven by electromagnetic ion cyclotron waves from ELFIN’s low altitude perspective

arXiv

引用

arXiv 2022年

作者： Angelopoulos, V. Zhang, X.-J. Artemyev, A.V. Mourenas, D. Tsai, E. Wilkins, C. Runov, A. Liu, J. Turner, D.L. Li, W. Khurana, K. Wirz, R.E. Sergeev, V.A. Meng, X. Wu, J. Hartinger, M.D. Raita, T. Shen, Y. An, X. Shi, X. Bashir, M.F. Shen, X. Gan, L. Qin, M. Capannolo, L. Ma, Q. Russell, C.L. Masongsong, E.V. Caron, R. He, I. Iglesias, L. Jha, S. King, J. Kumar, S. Le, K. Mao, J. McDermott, A. Nguyen, K. Norris, A. Palla, A. Roosnovo Tam, J. Xie, E. Yap, R.C. Ye, S. Young, C. Adair, L.A. Shaffer, C. Chung, M. Cruce, P. Lawson, M. Leneman, D. Allen, M. Anderson, M. Arreola-Zamora, M. Artinger, J. Asher, J. Branchevsky, D. Cliffe, M. Colton, K. Costello, C. Depe, D. Domae, B.W. Eldin, S. Fitzgibbon, L. Flemming, A. Frederick, D.M. Gilbert, A. Hesford, B. Krieger, R. Lian, K. McKinney, E. Miller, J.P. Pedersen, C. Qu, Z. Rozario, R. Rubly, M. Seaton, R. Subramanian, A. Sundin, S.R. Tan, A. Thomlinson, D. Turner, W. Wing, G. Wong, C. Zarifian, A. Earth Planetary and Space Sciences Department Institute of Geophysics and Planetary Physics University of California Los Angeles Los AngelesCA90095 United States University of Texas at Dallas RichardsonTX75080 United States CEA DAM DIF Arpajon France Atmospheric and Oceanic Sciences Departments University of California Los AngelesCA United States Johns Hopkins University Applied Physics Laboratory LaurelMD United States Department of Astronomy Center for Space Physics Boston University BostonMA United States Mechanical and Aerospace Engineering Department Henry Samueli School of Engineering University of California Los AngelesCA90095 United States School of Mechanical Industrial Manufacturing Engineering Oregon State University CorvallisOR97331 United States University of St. Petersburg St. Petersburg Russia Jet Propulsion Laboratory California Institute of Technology PasadenaCA91109 United States Space Science Institute BoulderCO80301 United States Sodankylä Geophysical Observatory University of Oulu Sodankylä Finland Materials Science and Engineering Department Henry Samueli School of Engineering University of California Los AngelesCA90095 United States Deloitte Consulting New YorkNY10112 United States Computer Science Department Henry Samueli School of Engineering University of California Los AngelesCA90095 United States Microsoft RedmondWA98052 United States Physics and Astronomy Department University of California Los AngelesCA90095 United States Department of Astronomy and Astrophysics The University of Chicago ChicagoIL60637 United States Raybeam Inc. Mountain ViewCA94041 United States SpaceX HawthorneCA90250 United States Reliable Robotics Corporation Mountain ViewCA94043 United States Los Alamos National Laboratory Los AlamosNM87545 United States Mathematics Department University of California Los AngelesCA90095 United States Planet Labs PBC San FranciscoCA94107 United States KSAT Inc. De

We review comprehensive observations of electromagnetic ion cyclotron (EMIC) wave-driven energetic electron precipitation using data from the energetic electron detector on the Electron Losses and Fields InvestigatioN (ELFIN) mission, two polar-orbiting low-altitude spinning CubeSats, measuring 50-5000 keV electrons with good pitch-angle and energy resolution. EMIC wave-driven precipitation exhibits a distinct signature in energy-spectrograms of the precipitating-to-trapped flux ratio: peaks at >0.5 MeV which are abrupt (bursty) (lasting ∼17s, or ∆L ∼ 0.56) with significant substructure (occasionally down to sub-second timescale). We attribute the bursty nature of the precipitation to the spatial extent and structuredness of the wave field at the equator. Multiple ELFIN passes over the same MLT sector allow us to study the spatial and temporal evolution of the EMIC wave - electron interaction region. Case studies employing conjugate ground-based or equatorial observations of the EMIC waves reveal that the energy of moderate and strong precipitation at ELFIN approximately agrees with theoretical expectations for cyclotron resonant interactions in a cold plasma. Using 2 years of ELFIN data uniformly distributed in local time, we assemble a statistical database of ∼50 events of strong EMIC wave-driven precipitation. Most reside at L ∼ 5 − 7 at dusk, while a smaller subset exists at L ∼ 8 − 12 at post-midnight. The energies of the peak-precipitation ratio and of the half-peak precipitation ratio (our proxy for the minimum resonance energy) exhibit an L-shell dependence in good agreement with theoretical estimates based on prior statistical observations of EMIC wave power spectra. The precipitation ratio’s spectral shape for the most intense events has an exponential falloff away from the peak (i.e., on either side of ∼ 1.45 MeV). It too agrees well with quasi-linear diffusion theory based on prior statistics of wave spectra. It should be noted though that this diffusive

关键词： Radiation belts

来源：评论

学校读者我要写书评

暂无评论

Perceived Stiffness Estimation for Robot Force Control

Perceived Stiffness Estimation for Robot Force Control

引用

IEEE International Conference on robotics and Automation

作者： Luis Santos Rui Cortesao Institute of Systems and Robotics University of Coimbra Portugal Electrical and Computer Engineering Department University of Coimbra Portugal

Typical robot force control architectures have a positive force feedback loop to decouple robot dynamics from contact dynamics. Due to the noisy profile of force measurements, it is common to filter force signals by low pass filters. This paper shows that, when force feedback is filtered, robot and environment dynamics are no longer decoupled, affecting force control performance. Additionally, the perceived stiffness from the force control perspective, is correlated with the robot effective mass. To cope with this issue, a force based stiffness estimation strategy that also includes the inertial properties (effective mass) in the estimation algorithm is proposed, allowing to adapt control gains based on the robot effective mass. In this way, the perceived stiffness can be seen as a control optimization parameter, rather than a well defined physical property. Simulation and experimental results with a 1-DoF robot and 7-DoF manipulator, respectively, validate the estimation strategy, showing better force control results with the perceived stiffness in the control loop, as compared to the real environment stiffness.

关键词： Robots Force Estimation Dynamics Force control Effective mass Adaptation models

来源：评论

学校读者我要写书评

暂无评论

Adaptive leader-follower formation control and obstacle avoidance via deep reinforcement learning

arXiv

引用

arXiv 2019年

作者： Zhou, Yanlin Lu, Fan Pu, George Ma, Xiyao Sun, Runhan Chen, Hsi-Yuan Li, Xiaolin Wu, Dapeng National Science Foundation Center for Big Learning Large-scale Intelligent Systems Laboratory Department of Electrical and Computer Engineering University of Florida GainesvilleFL United States Department of Mechanical and Aerospace Engineering University of Florida GainesvilleFL United States Amazon Robotics North Reading AI Institute Tongdun Technology

We propose a deep reinforcement learning (DRL) methodology for the tracking, obstacle avoidance, and formation control of nonholonomic robots. By separating vision-based control into a perception module and a controller module, we can train a DRL agent without sophisticated physics or 3D modeling. In addition, the modular framework averts daunting retrains of an image-to-action end-to-end neural network, and provides flexibility in transferring the controller to different robots. First, we train a convolutional neural network (CNN) to accurately localize in an indoor setting with dynamic foreground/background. Then, we design a new DRL algorithm named Momentum Policy Gradient (MPG) for continuous control tasks and prove its convergence. We also show that MPG is robust at tracking varying leader movements and can naturally be extended to problems of formation control. Leveraging reward shaping, features such as collision and obstacle avoidance can be easily integrated into a DRL controller. Copyright © 2019, The Authors. All rights reserved.

关键词： Deep learning

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：