检索结果-内蒙古大学图书馆

CrowdMove: Autonomous mapless navigation in crowded scenarios

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Fan, Tingxiang Cheng, Xinjing Pan, Jia Manocha, Dinesh Yang, Ruigang Researcher of Robotics and Auto-driving Lab Baidu Research Baidu Inc. Department of Mechanical Biomedical Engineering City University of Hong Kong Hong Kong Hong Kong Department of Computer Science University of Maryland College Park United States

Navigation is an essential capability for mobile robots. In this paper, we propose a generalized yet effective 3M (i.e., multi-robot, multi-scenario, and multi-stage) training framework. We optimize a mapless navigation policy with a robust policy gradient algorithm. Our method enables different types of mobile platforms to navigate safely in complex and highly dynamic environments, such as pedestrian crowds. To demonstrate the superiority of our method, we test our methods with four kinds of mobile platforms in four scenarios. Videos are available at http://***/view/crowdmove. Copyright © 2018, The Authors. All rights reserved.

关键词： Navigation

Webizing interactive CAD review system using super multiview autostereoscopic displays 1

学校读者我要写书评

暂无评论

19th International Conference on Human-computer Interaction, HCI International 2017

作者： Seo, Daeil Lee, Yongjae Yoo, Byounghyun Center for Imaging Media Research Korea Institute of Science and Technology Seoul Korea Republic of Department of Computer Science and Engineering Seoul National University of Science and Technology Seoul Korea Republic of Department of HCI and Robotics University of Science and Technology Daejeon Korea Republic of

ISBN: (数字)9783319587530

ISBN: (纸本)9783319587523

A glasses-free super multi-view display has emerged alongside the development of optical technologies. However, the display is not yet widely used because its content remains in the early stages of only image or video without user interaction. Expanding the display market would require content that can take advantage of the display. In this paper, we propose a webized interactive CAD review system that uses super multi-view autostereoscopic displays with an application facilitating the popularization of super multi-view displays. The content for the display is described by web technologies such as HTML5, CSS, and JavaScript. The proposed system renders the content through a web browser and handles user interactions via JavaScript. A user can view autostereoscopic images with a sense of depth through motion parallax using the display and control the content remotely using gesture interaction devices. We present an example of content using a prototype implementation to verify our approach’s usefulness. © Springer International Publishing AG 2017.

关键词： Display devices

Webizing virtual reality-based interactive interior design system 1

学校读者我要写书评

暂无评论

19th International Conference on Human-computer Interaction, HCI International 2017

作者： Seo, Daeil Lee, Jongho Yoo, Byounghyun Center for Imaging Media Research Korea Institute of Science and Technology Seoul Korea Republic of Department of Computer Science and Engineering Seoul National University of Science and Technology Seoul Korea Republic of Department of HCI and Robotics University of Science and Technology Daejeon Korea Republic of

ISBN: (数字)9783319587530

ISBN: (纸本)9783319587523

The virtual reality (VR)-based interior design systems have the advantage of cost reductions and can support multiple users without spatial or temporal constraints. Recently, various head-mounted display (HMD) applications for VR using smartphones have become popular, and WebVR technology has been introduced to implement VR applications on the web. However, WebVR is still its early stages for use in the development of VR applications. Interaction methods for WebVR are limited compared to traditional VR development environments. In this paper, we propose an interactive VR system for interior design based on web technologies with a system that supports 3D and VR views with various interaction methods on the web. © Springer International Publishing AG 2017.

关键词： Virtual reality

Advances in Industrial Control

学校读者我要写书评

暂无评论

Introduction

Advances in Industrial Control 2018年第9783319610207期 1-18页

作者： Orsag, Matko Korpela, Christopher Oh, Paul Bogdan, Stjepan Laboratory for Robotics and Intelligent Control Systems Faculty of Electrical Engineering and Computing University of Zagreb Zagreb Croatia Department of Electrical Engineering and Computer Science United States Military Academy West PointNY United States Department of Mechanical Engineering University of Nevada Las Vegas Las VegasNV United States

Aerial robotics has reached significant maturity in the last few years. Thus, the number of new unmanned aerial vehicles (UAV) and unmanned aerial systems (UAS), applications, and companies producing them has increased in a very important way. The number of publications and presentations in conferences has also experienced a large increase. Moreover, almost every day we can find articles, videos, and news in the general media related to drones. © Springer International Publishing AG 2018.

关键词： Antennas

Re-scheduling of AGVs Steady State Flow

学校读者我要写书评

暂无评论

IFAC-PapersOnLine 2017年第1期50卷 3493-3498页

作者： Bocewicz G. Banaszak Z. Nielsen I. Muszyński W. Department of Electronics and Computer Science Koszalin University of Technology Sniadeckich 2 Koszalin 75-453 Poland Department of Mechanical and Manufacturing Engineering Aalborg University Aalborg East Denmark Department of Cybernetics and Robotics Wrocław University of Technology Poland

The paper's objective concerns assessing a mesh-like supply network of periodically acting local transportation modes from the perspective of possible re-scheduling the multimodal flows of jobs assigned to certain technological routes passing through common shared workstations. The considered reference model of a Material Transportation Network (MTN), where several heterogeneous means of material handling, e.g. AGVs, hoists, lifts, etc., interact with each other via common shared workstations, enables the formulation of scheduling and re-scheduling tasks in the context of a Periodic Vehicle Routing Problem. The main problem is in essence to identify conditions guaranteeing transient period free re-scheduling of cyclic steady state flows of multimodal processes and local transportation processes supporting their execution. Such sufficient conditions allows one to replace the exhaustive search for the admissible flows control by design of regular structure material handling system, i.e. to solve the considered class of re-scheduling problems online. The proposed methodology behind re-scheduling cyclic steady state production flows executed in regular-structure MTNs is clarified through multiple illustrative examples. © 2017

关键词： cyclic scheduling declarative modelling fleet of AGVs multimodal process Periodic Vehicle Routing Problem re-scheduling

Magnetic-visual sensor fusion-based dense 3D reconstruction and localization for endoscopic capsule robots

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Turan, Mehmet Almalioglu, Yasin Ornek, Evin Pinar Araujo, Helder Yanik, Mehmet Fatih Sitti, Metin Physical Intelligence Department Max Planck Institute for Intelligent Systems Germany Computer Science Department University of Oxford Oxford United Kingdom Informatics Department Technical University of Muenich Germany Institute for Systems and Robotics University of Coimbra Portugal Department of Information Technology and Electrical Engineering Zurich Switzerland

Reliable and real-time 3D reconstruction and localization functionality is a crucial prerequisite for the navigation of actively controlled capsule endoscopic robots as an emerging, minimally invasive diagnostic and therapeutic technology for use in the gastrointestinal (GI) tract. In this study, we propose a fully dense, non-rigidly deformable, strictly realtime, intraoperative map fusion approach for actively controlled endoscopic capsule robot applications which combines magnetic and vision-based localization, with non-rigid deformations based frame-to-model map fusion. The performance of the proposed method is demonstrated using four different ex-vivo porcine stomach models. Across different trajectories of varying speed and complexity, and four different endoscopic cameras, the root mean square surface reconstruction errors 1.58 to 2.17 cm. Copyright © 2018, The Authors. All rights reserved.

关键词： Robot applications

PID2018 benchmark challenge: Learning feedforward control

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Zhao, Yang Dehghan, Sina Ates, Abdullah School of Control Science and Engineering Center for Robotics Shandong University Jinan Shandong250061 China University of California Merced MercedCA95340 United States School of Automation Southeast University Nanjing210096 China Engineering Faculty Computer Engineering Department Inonu University Malatya44280 Turkey

The design and application of learning feedforward controllers (LFFC) for the one-staged refrigeration cycle model described in the PID2018 Benchmark Challenge is presented, and its effectiveness is evaluated. The control system consists of two components: 1) a preset PID component and 2) a learning feedforward component which is a function approximator that is adapted on the basis of the feedback signal. A B-spline network based LFFC and a low-pass filter based LFFC are designed to track the desired outlet temperature of evaporator secondary flux and the superheating degree of refrigerant at evaporator outlet. Encouraging simulation results are included. Qualitative and quantitative comparison results evaluations show that, with little effort, a high-performance control system can be obtained with this approach. Our initial simple attempt of low-pass filter based LFFC and B-spline network based LFFC give J=0.4902 and J=0.6536 relative to the decentralized PID controller, respectively. Besides, the initial attempt of a combination controller of our optimized PI controller and low-pass filter LFFC gives J=0.6947 relative to the multi-variable PID controller. Copyright © 2018, The Authors. All rights reserved.

关键词： Feedforward control

Standardized Assessment of Automatic Segmentation of White Matter Hyperintensities and Results of the WMH Segmentation Challenge

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Kuijf, Hugo J. Biesbroek, J. Matthijs Bresser, Jeroen de Heinen, Rutger Andermatt, Simon Bento, Mariana Berseth, Matt Belyaev, Mikhail Cardoso, M. Jorge Casamitjana, Adrià Collins, D. Louis Dadar, Mahsa Georgiou, Achilleas Ghafoorian, Mohsen Jin, Dakai Khademi, April Knight, Jesse Li, Hongwei Lladó, Xavier Luna, Miguel Mahmood, Qaiser McKinley, Richard Mehrtash, Alireza Ourselin, Sébastien Park, Bo-yong Park, Hyunjin Park, Sang Hyun Pezold, Simon Puybareau, Elodie Rittner, Leticia Sudre, Carole H. Valverde, Sergi Vilaplana, Verónica Wiest, Roland Xu, Yongchao Xu, Ziyue Zeng, Guodong Zhang, Jianguo Zheng, Guoyan Chen, Christopher Flier, Wiesje van der Barkhof, Frederik Viergever, Max A. Biessels, Geert Jan Image Sciences Institute UMC Utrecht Utrecht University Netherlands Brain Center Rudolf Magnus UMC Utrecht Utrecht University Netherlands Department of Radiology UMC Utrecht Department of Radiology LUMC Leiden Netherlands Department of Biomedical Engineering University of Basel Allschwil Switzerland Radiology and Clinical Neuroscience Hotchkiss Brain Institute University of Calgary AB Canada NLP Logix Skolkovo Institute of Science and Technology School of Biomedical Engineering and Imaging Sciences King’s College London Centre for Medical Image Computing University College London Signal Theory and Communications Department Universitat Politècnica de Catalunya BarcelonaTech Barcelona Spain McGill University Canada Computational Statistics and Machine Learning MSc University College London TomTom Amsterdam Netherlands Department of Radiology and Imaging Science National Institutes of Health United States Ryerson University Canada University of Guelph Canada Sun Yat-sen University University of Dundee Technical University of Munich Research institute of Computer Vision and Robotics University of Girona Spain Department of Robotics Engineering Daegu Gyeongbuk Institute of Science and Technology Daegu Korea Republic of Pakistan Institute of Nuclear Science and Technology Support Center for Advanced Neuroimaging Institute for Diagnostic and Interventional Neuroradiology Inselspital University of Bern Switzerland Electrical and Computer Engineering Department University of British Columbia Vancouver Department of Radiology Brigham and Women’s Hospital Harvard Medical School Boston School of Biomedical Engineering and Imaging Sciences King’s College London Suwon Korea Republic of School of Electronic and Electrical Engineering Sungkyunkwan University Suwon Korea Republic of France School of Electrical and Computer Engineering University of Campinas SP Brazil School of Biomedical Engineering and Imaging Sciences King’s College London Centre for Medical I

Quantification of cerebral white matter hyperintensities (WMH) of presumed vascular origin is of key importance in many neurological research studies. Currently, measurements are often still obtained from manual segmentations on brain MR images, which is a laborious procedure. Automatic WMH segmentation methods exist, but a standardized comparison of the performance of such methods is lacking. We organized a scientific challenge, in which developers could evaluate their method on a standardized multi-center/-scanner image dataset, giving an objective comparison: the WMH Segmentation Challenge (https://***/).Sixty T1+FLAIR images from three MR scanners were released with manual WMH segmentations for training. A test set of 110 images from five MR scanners was used for evaluation. Segmentation methods had to be containerized and submitted to the challenge organizers. Five evaluation metrics were used to rank the methods: (1) Dice similarity coefficient, (2) modified Hausdorff distance (95th percentile), (3) absolute log-transformed volume difference, (4) sensitivity for detecting individual lesions, and (5) F1-score for individual lesions. Additionally, methods were ranked on their inter-scanner *** participants submitted their method for evaluation. This paper provides a detailed analysis of the results. In brief, there is a cluster of four methods that rank significantly better than the other methods, with one clear winner. The inter-scanner robustness ranking shows that not all methods generalize to unseen *** challenge remains open for future submissions and provides a public platform for method evaluation. Copyright © 2019, The Authors. All rights reserved.

关键词： Magnetic resonance imaging

Multicast Repair for Broadcast Flows to the Handheld Receivers

学校读者我要写书评

暂无评论

Multicast Repair for Broadcast Flows to the Handheld Receive...

IEEE Wireless Communications and Networking Conference

作者： Muhammad Moiz Anis Luis Suarez Johann Leithon Dushantha Nalin K. Jayakody School of Science and Engineering Habib University Karachi Pakistan Huawei Technologies Co Ltd Russian Research Center Moscow Russia Department of Signal Processing and Acoustics Aalto University Espoo Finland School of Computer Science and Robotics National Research Polytechnic University Tomsk Russia

Mobile TV receivers operate with a weaker link budget in the Digital Video Broadcast (DVB) network compared to the fixed rooftop mounted antenna receivers. Nevertheless, the cellular radio interface is an attractive alternative for broadcast services given its reliability. In this work, we use Long Term Evolution (LTE) 's evolved Multimedia Broadcast Multicast Service (eMBMS) to multicast overhead parity packets among the multicast groups of mobile TV receivers (e.g. smartphones suffering from DVB packet erasures). The proposed multicast scheme recovers erased packets at each smartphone by Systematic RaptorQ Code (SRQC) decoding the directly received DVB transmission along with the overhead packets transmitted via eMBMS multicast. We analyze the load generated in the Cellular Radio Access Network due to this erasure-recovery multicast scheme and compare the gains of such a service over the LTE unicast retransmissions of the missing DVB packets.

关键词： Mobile TV EMBMS Block codes Multicast repair DVB-T2 LTE Real-time broadcast Multicast Linear combinations Erasure channel