检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Wang, Guojun Tian, Bin Zhang, Yachen Chen, Long Cao, Dongpu Wu, Jian State Key Laboratory of Automotive Simulation and Control Jilin University Changchun130022 China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100190 China School of Data and Computer Science Sun Yat-Sen University Guangzhou510275 China Lab University of Waterloo Canada College of Automotive Engineering Jilin University China

3D object detection based on LiDAR-camera fusion is becoming an emerging research theme for autonomous driving. However, it has been surprisingly difficult to effectively fuse both modalities without information loss and interference. To solve this issue, we propose a single-stage multi-view fusion framework that takes LiDAR Birds-Eye View, LiDAR Range View and Camera View images as inputs for 3D object detection. To effectively fuse multi-view features, we propose an Attentive Pointwise Fusion (APF) module to estimate the importance of the three sources with attention mechanisms which can achieve adaptive fusion of multi-view features in a pointwise manner. Besides, an Attentive Pointwise Weighting (APW) module is designed to help the network learn structure information and point feature importance with two extra tasks: foreground classification and center regression, and the predicted foreground probability will be used to reweight the point features. We design an end-to-end learnable network named MVAF-Net to integrate these two components. Our evaluations conducted on the KITTI 3D object detection datasets demonstrate that the proposed APF and APW module offer significant performance gain and that the proposed MVAF-Net achieves state-of-the-art performance in the KITTI benchmark. Copyright © 2020, The Authors. All rights reserved.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Primitives generation policy learning without catastrophic forgetting for robotic manipulation 19

Primitives generation policy learning without catastrophic f...

引用

19th IEEE International Conference on Data Mining Workshops, ICDMW 2019

作者： Xiong, Fangzhou Liu, Zhiyong Huang, Kaizhu Yang, Xu Hussain, Amir State Key Lab of Management and Control for Complex Systems Institute of Automation Chinese Academy of Science China China CAS Centre for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences China Department of EEE Xi'an Jiaotong-Liverpool University China School of Computing Edinburgh Napier University United Kingdom

ISBN: (纸本)9781728146034

Catastrophic forgetting is a tough challenge when agent attempts to address different tasks sequentially without storing previous information, which gradually hinders the development of continual learning. Except for image classification tasks in continual learning, however, there are little reviews related to robotic manipulation. In this paper, we present a novel hierarchical architecture called Primitives Generation Policy Learning to enable continual learning. More specifically, a generative method by Variational Autoencoder is employed to generate state primitives from task space, then separate policy learning component is designed to learn torque control commands for different tasks sequentially. Furthermore, different task policies could be identified automatically by comparing reconstruction loss in the autoencoder. Experiment on robotic manipulation task shows that the proposed method exhibits substantially improved performance over some other continual learning methods. © 2019 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

A NOVEL TENSOR-BASED FEATURE EXTRACTION METHOD FOR POLSAR IMAGE CLASSIFICATION

A NOVEL TENSOR-BASED FEATURE EXTRACTION METHOD FOR POLSAR IM...

引用

IEEE International Geoscience and Remote Sensing Symposium

作者： Xiayuan Huang Xiangli Nie Hong Qiao Bo Zhang State Key Lab of Management and Control for Complex Systems Chinese Academy of Sciences Beijing China State Key Lab of Scientific and Engineering Computing and Institute of Applied Mathematics AMSS Chinese Academy of Sciences Beijing China

Spatial information helps improve the performance of polarimetric synthetic aperture radar (PolSAR) image classification. Some existing methods have combined the spatial information and polarimetric features by the third-order tensor representation for feature extraction. They describe a pixel with the patch centered on this pixel. But they neglect the spatial heterogeneity, which may influence the classification performance. Therefore, we firstly seek k nearest samples based on the polarimetric feature similarity for each pixel to construct the second-order tensor, whose first order denotes the nearest samples and the second order denotes the polarimetric features. Moreover, k nearest samples are searched in a spatial local region rather than the full image, which can exploit the spatial information and reduce the computational burden. Then we employ tensor principal component analysis (TPCA) to extract low-dimensional features. Experimental results demonstrate that the proposed method can improve the classification performance compared with other methods.

关键词： Feature extraction Principal component analysis Visualization Euclidean distance Eigenvalues and eigenfunctions Roads

来源：评论

学校读者我要写书评

暂无评论

Effect of compliant passive joint on swimming performance for a multi-joint robotic fish

Effect of compliant passive joint on swimming performance fo...

引用

2019 IEEE International Conference on Robotics and Biomimetics, ROBIO 2019

作者： Chen, Di Wu, Zhengxing Yu, Junzhi Institute of Automation CAS State Key Lab Management and Control for Complex Systems Beijing100190 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China Dept. Mech. Eng. Sci. BIC-ESAT College of Engineering Peking University Beijing100871 China

ISBN: (纸本)9781728163215

In this paper, a novel compliant passive joint with two torsion springs is designed for a multi-joint robotic fish to improve propulsive performance. The motion of the multi-joint robotic fish is governed by the central pattern generator (CPG) control method. Using this multi-joint robotic fish as a testbed, the effect of compliant passive joint on swimming speed with changes in spring constant and CPG parameters such as oscillation frequency and phase difference is explored. As for the multi-joint robotic fish with a compliant passive joint, the swimming speed increases directly with the increase of oscillation frequency and the swimming speed achieved at maximum oscillation frequency increases with the decrease of phase difference. In addition, the comparison of swimming performance between robotic fish with a compliant passive joint and a fixed passive joint is made. Remarkably, the maximum swimming speed after improvement increases approximately 9.43 cm/s, corresponding to 0.17 BL/s. Experimental results reveal that adding an extra compliant passive joint can not always bring an improvement in swimming performance. Appropriate stiffness of passive joint and control parameters are needed to achieve better swimming performance. © 2019 IEEE.

关键词： Robotics

来源：评论

学校读者我要写书评

暂无评论

3-D Motion Analysis and Implementation of a Developed Gliding Robotic Dolphin

3-D Motion Analysis and Implementation of a Developed Glidin...

引用

IEEE International Conference on Robotics and Biomimetics

作者： Jian Wang Zhengxing Wu Jincun Liu Min Tan Junzhi Yu State Key Lab Management and Control for Complex Systems Institute of Automation CAS Beijing China Dept. Mech. Eng. Sci. Peking University Beijing China

This paper investigates the three-dimensional (3-D) maneuverability of a gliding robotic dolphin through analyzing the horizontal and vertical motions. Concretely, in order to improve the performance in the horizontal plane, the gliding robotic dolphin is developed with a rudder installed on its belly, and the 3-D full-state dynamic model is derived briefly. By setting two typical body and/or caudal fin (BCF)-based and three typical median and/or paired fin (MPF)-based turning patterns, the turning performances are revealed and analyzed. With regard to the vertical plane, a novel finite state machine framework is proposed to realize the vertical downward action. Finally, extensive experiments involving the turning and vertical motions are conducted to illustrate and analyze the 3-D maneuverability, which provides valuable guidance for the real-world applications of the gliding robotic dolphin.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An efficient 3D pedestrian detector with calibrated RGB camera and 3D LiDAR

An efficient 3D pedestrian detector with calibrated RGB came...

引用

2019 IEEE International Conference on Robotics and Biomimetics, ROBIO 2019

作者： Pang, Lei Cao, Zhiqiang Yu, Junzhi Liang, Shuang Chen, Xuechao Zhang, Weimin State Key Lab Management and Control for Complex Systems Institute of Automation CAS Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China Dept. Mech. Eng. Sci. BIC-ESAT College of Engineering Peking University Beijing100871 China BAICIRS Beijing100081 China Intell. Robot. Inst. Beijing Inst. Technol. Beijing100081 China

ISBN: (纸本)9781728163215

Pedestrian detection plays an important role in the environmental perception and autonomous navigation for robotics, which provides critical information for the safe operation in complex environments. In this paper, a 3D pedestrian detector with calibrated LiDAR and RGB Camera is proposed, which takes full advantage of the precise range information of 3D LiDAR scanner and semantic information acquired from RGB image. The proposed approach integrates the segmented object clusters of point cloud and 2D bounding boxes generated by a visual object detector. The point cloud is segmented by a three-step segmentation approach, which can segment point cloud with both high precision and high efficiency. By fusion multi-sensor information in the image domain, the proposed approach provides 3D information of pedestrians in both LiDAR and camera coordinate systems. Experiments was conducted to evaluate the performance of the proposed approach. © 2019 IEEE.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of Faults in a Photovoltaic Array Based on V-I and V-P Characteristic Curve

Performance Evaluation of Faults in a Photovoltaic Array Bas...

引用

International Conference on Measuring Technology and Mechatronics Automation, ICMTMA

作者： Ehtisham Lodhi Wang Lina Yang Pu M. Yaqoob Javed Zeeshan Lodhi Jiao Zhijie Usman Javed School of Automation Science and Electrical Engineering Beihang University Beijing China The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Department of Electrical and Computer Engineering COMSATS University Islamabad Lahore Pakistan Department of Electrical and Computer Engineering COMSATS University Islamabad Abbottabad Pakistan The Guo China-US photonics Lab Changchun Institute of Optics Fine Mechanics and Physics Chinese Academy of Sciences Changchun China

ISBN: (数字)9781728170817

ISBN: (纸本)9781728170824

The prediction and forecasting of faults occurring in photovoltaic (PV) system is one of the important aspect to escalate the reliability, output power generation, proficiency, lifetime and effectiveness of overall system. In this article, the behavior of PV array is studied under various faulty circumstances and new approach has offered for the better performance assessment of PV array. This approach is established on the analysis of peculiarities displayed by voltage power (V-P) and voltage-current (V-I) characteristics curves of PV array under different faulty conditions. The proposed technique can be used to identify and classify the five common faults in PV system. These progressive faults (includes open circuit, line-to-line, partial shading, degradation and bridging faults) have been occurred at the basic components of PV cell and at the connection point between PV modules. The characteristic curves under normal and faulty conditions have been compared by utilizing Matlab.Simulink environment. Hence, the suggested method can be utilized to determine the important fact about the health PV array.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Bibliometric Analysis of Blockchain Research

A Bibliometric Analysis of Blockchain Research

引用

2018 IEEE Intelligent Vehicles Symposium, IV 2018

作者： Zeng, Shuai Ni, Xiaochun Yuan, Yong Wang, Fei-Yue State Key Lab for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China Qingdao Academy of Intelligent Industries Shandong266000 China Research Center of Military Computational Experiments and Parallel System National University of Defense China

ISBN: (纸本)9781538644522

Taking Ei Compendex (EI) and China National Knowledge Infrastructure (CNKI) databases as the literature sources, this paper presented a bibliographic analysis of the blockchain-related literature between January 2011 and September 2017. For each literature source, we built a separate dataset. Authors' productivity and collab.ration, affiliation of authors and collab.ration amongst institutions were analyzed using techniques of social networks analysis on both datasets. According to the results, the CNKI authors/institutes raised their productivity and outperformed the EI authors/institutes since 2016. However, the EI authors/institutes show a higher level than the CNKI authors/institutes in collab.ration. We also summarized the hot topics on the EI dataset using textual analysis and discovered researchers have shifted their attention from Bitcoin itself to the blockchain technology underlying it. © 2018 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Compare Variation of User’s EEG Owing to Parallax Cue

Compare Variation of User’s EEG Owing to Parallax Cue

引用

International Conference on Display Technology, ICDT 2018

作者： Hu, Haichen Wang, Danli Yue, Kang Yang, Xinpan Chiu, Steve C. The State Key Laboratory of Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Beijing Key Lab of Human-Computer Interaction Institute of Software Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China College of Science and Engineering Idaho State University Pocatello United States

ISBN: (纸本)9781510867659

3D display has become increasingly popular in many fields. It can provide incredible immersion compared with 2D display. There are many researches referring to the change of user about no matter subjective experience or objective physiology signal while watching 3D content. Similarly, in this paper, we study the variation of user’s EEG when the user watched 3D content. However, we only focus on parallax cue and avoid other cues of 3D content by using Random Dot Stereogram(RDS) as visual stimulus. We designed an experiment which asked the subject to watch RDS with nine kinds of parallaxes(0,±0.5,±1.1,±1.3,±1.7). The users watched one RDS for 1 minute and then closed eyes and rest for 1 minute every time. During watching, EEG signal with 30-channel was recorded. The result suggests that significant variation of the user’s EEG data occurred in the Alpha(8-13Hz) and Beta(14-30Hz) frequency band by different parallax’s comparison. And we found not only parallax but also electrode position can impact the user’s EEG data significantly. Accurately, the EEG data has a significant change in six electrodes position in both frequency bands including CZ 、 PZ 、 OZ 、 O2 in international 10-20 system. It means those electrode positions we detect can be regarded as typical positions where we record EEG signal. It will simplify the process of EEG signal acquisition when we need to study the relationship between parallax cue of 3D display and the user further. © 2018 SID.

关键词： Three dimensional displays

来源：评论

学校读者我要写书评

暂无评论

Primitives Generation Policy Learning without Catastrophic Forgetting for Robotic Manipulation

Primitives Generation Policy Learning without Catastrophic F...

引用

IEEE International Conference on Data Mining Workshops (ICDM Workshops)

作者： Fangzhou Xiong Zhiyong Liu Kaizhu Huang Xu Yang Amir Hussain State Key Lab of Management and Control for Complex Systems Institute of Automation Chinese Academy of Science China School of Computer and Control University of Chinese Academy of Sciences (UCAS) China CAS Centre for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences China Department of EEE Xi’an Jiaotong-Liverpool University China School of Computing Edinburgh Napier University U.K.

关键词： Task analysis Robots Neural networks Learning systems Trajectory Decoding Aerospace electronics

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：