检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Wang, Guangming Chen, Muyao Liu, Hanwen Yang, Yehui Liu, Zhe Wang, Hesheng The Department of Automation Institute of Medical Robotics Key Laboratory of System Control and Information Processing Ministry of Education Key Laboratory of Marine Intelligent Equipment System of Ministry of Education Shanghai Jiao Tong University Shanghai200240 China Beijing Advanced Innovation Center for Intelligent Robots and Systems Beijing Institute of Technology China The Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai200240 China The Department of Computer Science and Technology University of Cambridge

With the rapid development of measurwement technology, LiDAR and depth cameras are widely used in the perception of the 3D environment. Recent learning based methods for robot perception most focus on the image or video, but deep learning methods for dynamic 3D point cloud sequences are underexplored. Therefore, developing efficient and accurate perception method compatible with these advanced instruments is pivotal to autonomous driving and service robots. An Anchor-based Spatio-Temporal Attention 3D Convolution operation (ASTA3DConv) is proposed in this paper to process dynamic 3D point cloud sequences. The proposed convolution operation builds a regular receptive field around each point by setting several virtual anchors around each point. The features of neighborhood points are firstly aggregated to each anchor based on the spatio-temporal attention mechanism. Then, anchor-based 3D convolution is adopted to aggregate these anchors' features to the core points. The proposed method makes better use of the structured information within the local region and learns spatio-temporal embedding features from dynamic 3D point cloud sequences. Anchor-based Spatio-Temporal Attention 3D Convolutional Neural Networks (ASTA3DCNNs) are built for classification and segmentation tasks based on the proposed ASTA3DConv and evaluated on action recognition and semantic segmentation tasks. The experiments and ablation studies on MSRAction3D and Synthia datasets demonstrate the superior performance and effectiveness of our method for dynamic 3D point cloud sequences. Our method achieves the state-of-the-art performance among the methods with dynamic 3D point cloud sequences as input on MSRAction3D and Synthia datasets. Copyright © 2020, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

A Bus-Based Battery Equalization via Modified Isolated Cuk Converter Governed by Adaptive control

A Bus-Based Battery Equalization via Modified Isolated Cuk C...

引用

Chinese automation Congress (CAC)

作者： Hao Zhong Jianwei Li Ya-Xiong Wang Key Laboratory of Industrial Automation Control Technology and Information Processing (Fuzhou University) Fujian Province University National Engineering Laboratory for Electric Vehicles Beijing Institute of Technology Beijing P. R. China School of Mechanical Engineering and Automation Fuzhou University Fuzhou P. R. China

Active equalization systems require balancing current regulation to further improve balancing efficiency and battery cycle life. This paper focuses on an adaptive control strategy for a battery equalization system based on modified isolated Cuk converter. Firstly, the analysis and modeling of the modified isolated Cuk-based equalizer are presented, and then the development of the adaptive sliding-mode control (SMC) scheme is proposed. The designed controller is verified through testing transient response, reference current variation and load change under continuous conduction mode. Compared with a traditional SMC, the proposed adaptive control has strongly ability to cope with the external disturbance and system parameters variation. A bus-based battery equalization system for five cells in series with an unbalanced state-of-charge (SOC) 0.75, 0.90, 0.45, 0.80 and 0.67 is performed to test the proposed control method. The simulation results indicate that the battery pack reaches to a balanced state in 712 sec.

关键词： Batteries Adaptive control Equalizers Capacitors Inductors Current control Stability analysis

来源：评论

学校读者我要写书评

暂无评论

Learning of long-horizon sparse-reward robotic manipulator tasks with base controllers

arXiv

引用

arXiv 2020年

作者： Wang, Guangming Xin, Minjian Wu, Wenhua Liu, Zhe Wang, Hesheng Department of Automation Key Laboratory of System Control and Information Processing of Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Shanghai200240 China Department of Computer Science and Engineering University of California San Diego La Jolla CA92093 United States Department of Computer Science and Technology University of Cambridge CambridgeCB2 1TN United Kingdom

Deep Reinforcement Learning (DRL) enables robots to perform some intelligent tasks end-to-end. However, there are still many challenges for long-horizon sparse-reward robotic manipulator tasks. On the one hand, a sparse-reward setting causes exploration inefficient. On the other hand, exploration using physical robots is of high cost and unsafe. In this paper, we propose a method of learning long-horizon sparse-reward tasks utilizing one or more existing traditional controllers named base controllers in this paper. Built upon Deep Deterministic Policy Gradients (DDPG), our algorithm incorporates the existing base controllers into stages of exploration, value learning, and policy update. Furthermore, we present a straightforward way of synthesizing different base controllers to integrate their strengths. Through experiments ranging from stacking blocks to cups, it is demonstrated that the learned state-based or image-based policies steadily outperform base controllers. Compared to previous works of learning from demonstrations, our method improves sample efficiency by orders of magnitude and improves the performance. Overall, our method bears the potential of leveraging existing industrial robot manipulation systems to build more flexible and intelligent controllers. Copyright © 2020, 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

Direction-of-Arrival Estimation Using Atomic Norm Methods: Affects of Multiple Snapshots and Coherent Sources

Direction-of-Arrival Estimation Using Atomic Norm Methods: A...

引用

2018 IEEE International Conference on Computational Electromagnetics, ICCEM 2018

作者： Yang, Zai Nanjing University of Science and Technology School of Automation Nanjing210094 China Key Laboratory of System Control and Information Processing Ministry of Education Shanghai200240 China

ISBN: (纸本)9781538612415

Multiple snapshots and coherent sources are two of the core concepts in direction-of-arrival (DOA) estimation. While multiple snapshots are acquired to improve the estimation accuracy, the presence of coherent sources may cause performance degradation and deterioration for a specific method. In this paper, we discuss their affects on the recently proposed atomic norm methods and present rigorous theoretical results in the noiseless case. In a nutshell, atomic norm methods are robust to coherent sources, and in the case of noncoherent sources, their performance increases as the number of snapshots increases in terms of reduced number of antennas required for exact DOA estimation. © 2018 IEEE.

关键词： Atoms

来源：评论

学校读者我要写书评

暂无评论

EEG-Based Brain-Computer Interfaces Are Vulnerable to Backdoor Attacks

arXiv

引用

arXiv 2020年

作者： Meng, Lubin Huang, Jian Zeng, Zhigang Jiang, Xue Yu, Shan Jung, Tzyy-Ping Lin, Chin-Teng Chavarriaga, Ricardo Wu, Dongrui Ministry of Education Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Brainnetome Center National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing China La Jolla CA United States Center for Advanced Neurological Engineering Institute of Engineering in Medicine Ucsd La Jolla CA United States Centre of Artificial Intelligence Faculty of Engineering and Information Technology University of Technology Sydney Australia Zhaw DataLab Zürich University of Applied Sciences Winterthur8401 Switzerland

Research and development of electroencephalogram (EEG) based brain-computer interfaces (BCIs) have advanced rapidly, partly due to deeper understanding of the brain and wide adoption of sophisticated machine learning approaches for decoding the EEG signals. However, recent studies have shown that machine learning algorithms are vulnerable to adversarial attacks. This article proposes to use narrow period pulse for poisoning attack of EEG-based BCIs, which is implementable in practice and has never been considered before. One can create dangerous backdoors in the machine learning model by injecting poisoning samples into the training set. Test samples with the backdoor key will then be classified into the target class specified by the attacker. What most distinguishes our approach from previous ones is that the backdoor key does not need to be synchronized with the EEG trials, making it very easy to implement. The effectiveness and robustness of the backdoor attack approach is demonstrated, highlighting a critical security concern for EEG-based BCIs and calling for urgent attention to address it. Copyright © 2020, The Authors. All rights reserved.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Robust Semi-Global Leaderless Consensus and Containment control of Identical Linear Systems with Imperfect Actuators

引用

Journal of Systems Science & Complexity 2018年第1期31卷 69-86页

作者： SHI Liangren ZHAO Zhiyun LIN Zongli Department of Automation Shanghai Jiao Tong University and Key Laboratory of System Control and Information Processing of Ministry of Education Shanghai 200240 China Key Laboratory of Advanced Control and Optimization for Chemical Processes (East China University of Science and Technology) Ministry of Education Shanghai 200237 China Charles L. Brown Department of Electrical and Computer Engineering University of Virginia P.O. Box 400743 Charlottesville VA 22904-4743 USA

This paper investigates both the robust semi-global leaderless consensus problem and the robust semi-global containment control problem for a group of identical linear systems with imperfect actuators. The imperfect actuators are characterized by nonlinearities such as saturation and dead zone and there input output relationships are not precisely known. The dynamics of follower agents are also affected by the input additive disturbances. Low-and-high gain feedback consensus protocols are constructed to solve these problems. More specifically, it is shown that robust semi-global leaderless consensus can be achieved over a connected undirected graph and robust semi-global containment control can be achieved when each follower agent has access to the information of at least one leader agent. Numerical simulation illustrates the theoretical results.

关键词： Consensus containment control dead zone leaderless consensus multi-agent systems saturation

来源：评论

学校读者我要写书评

暂无评论

Low-latency federated learning over wireless channels with differential privacy

arXiv

引用

arXiv 2021年

作者： Wei, Kang Li, Jun Ma, Chuan Ding, Ming Chen, Cailian Jin, Shi Han, Zhu Poor, H. Vincent School of Electrical and Optical Engineering Nanjing University of Science and Technology Nanjing210094 China Data61 CSIRO SydneyNSW2015 Australia The Department of Automation Shanghai Jiao Tong University Shanghai200240 China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China The National Mobile Communications Research Laboratory Southeast University Nanjing210096 China The Department of Electrical and Computer Engineering The University of Houston HoustonTX77004 United States The Department of Computer Science and Engineering Kyung Hee University Seoul Korea Republic of The Department of Electrical and Computer Engineering Princeton University PrincetonNJ08544 United States

In federated learning (FL), model training is distributed over clients and local models are aggregated by a central server. The performance of uploaded models in such situations can vary widely due to imbalanced data distributions, potential demands on privacy protections, and quality of transmissions. In this paper, we aim to minimize FL training delay over wireless channels, constrained by overall training performance as well as each client's differential privacy (DP) requirement. We solve this problem in the framework of multi-agent multiarmed bandit (MAMAB) to deal with the situation where there are multiple clients confornting different unknown transmission environments, e.g., channel fading and interferences. Specifically, we first transform the long-term constraints on both training performance and each client's DP into a virtual queue based on the Lyapunov drift technique. Then, we convert the MAMAB to a max-min bipartite matching problem at each communication round, by estimating rewards with the upper confidence bound (UCB) approach. More importantly, we propose two efficient solutions to this matching problem, i.e., modified Hungarian algorithm and greedy matching with a better alternative (GMBA), in which the first one can achieve the optimal solution with a high complexity while the second one approaches a better tradeoff by enabling a verified low-complexity with little performance loss. In addition, we develop an upper bound on the expected regret of this MAMAB based FL framework, which shows a linear growth over the logarithm of communication rounds, justifying its theoretical feasibility. Extensive experimental results are conducted to validate the effectiveness of our proposed algorithms, and the impacts of various parameters on the FL performance over wireless edge networks are also discussed. Copyright © 2021, The Authors. All rights reserved.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

End-to-end learning for high-precision lane keeping via multi-state model

引用

CAAI Transactions on Intelligence technology 2018年第4期3卷 185-190页

作者： Wei Yuan Ming Yang Hao Li Chunxiang Wang Bing Wang Department of Automation Key Laboratory of System Control and Information ProcessingShanghai Jiao Tong UniversityMinistry of Education of ChinaShanghai 200240People’s Republic of China Department of Automation & SJTU-ParisTech Elite Institute of Technology Shanghai Jiao Tong UniversityShanghai 200240People’s Republic of China

High-precision lane keeping is essential for the future autonomous ***,due to the imbalanced and inaccurate datasets collected by human drivers,current end-to-end driving models have poor lane keeping the *** improve the precision of lane keeping,this study presents a novel multi-state model-based end-to-end lane keeping ***,three driving states will be defined:going straight,turning right and turning ***,the finite-state machine(FSM)table as well as three kinds of training datasets will be generated based on the three driving *** of collecting the dataset by human drivers,the accurate dataset will be collected by the high-performance path following ***,three sets of parameters based on 3DCNN-LSTM model will be trained for going straight,turning left and turning right,which will be combined with FSM table to form a multi-state *** study evaluates the multi-state model by testing it on five tracks and recording the lane keeping *** result shows the multi-state model-based end-to-end method performs the higher precision of lane keeping than the traditional single end-to-end model.

关键词： High-precision lane keeping

来源：评论

学校读者我要写书评

暂无评论

Robotic Trajectory Planning for Non-Destructive Testing Based on Surface 3D Point Cloud Data

引用

Journal of Physics: Conference Series 2021年第1期1965卷

作者： Zhen Zhang Hualiang Zhang Xiaolong Yu Yongsheng Deng Zheng Chen School of mechanical engineering and automation Northeastern University Shenyang China Key laboratory of industrial control network and system Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Hangzhou innovation institute Beihang University Hangzhou China School of information engineering Shenyang University of Chemical Technology Shenyang China

Robotics has been widely used in the field of non-destructive testing in recent years. However, for complex surfaces, manual teaching or offline programming is time-consuming and difficult to ensure high precision for non-destructive testing robot trajectory planning. Therefore, this work proposes a new method to generate non-destructive testing trajectory of the robot based on the pre-processed point cloud data. The workpiece surface is measured by 3D sensor to obtain the point cloud data. The trajectory line on workpiece surface is obtained by slicing pre-processed point cloud data. The dense trajectory points are obtained by isometric discretizing trajectory lines, and then they are compressed by Douglas-Peucker algorithm. The Principal Component Analysis (PCA) method is used to estimate the normal vector of the optimized trajectory points and unify their orientation. The pose of non-destructive testing robot can be obtained by biasing the trajectory points along their normal vectors finally.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Velocity Coordination of Multi-vehicle Systems via Distributed Neighbor Selection

Velocity Coordination of Multi-vehicle Systems via Distribut...

引用

International Conference on Intelligent Transportation

作者： Haibin Shao Lulu Pan Yugeng Xi Dewei Li Shu Lin Department of Automation and the Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Jiao Tong University China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781538670255

In this paper, we examine a data-driven control approach to coordination of multi-vehicle systems based on the distributed neighbor selection. The core of the proposed approach is to utilize a recently developed metric called relative tempo for distributed coordination which is computable from local measurable data for each vehicle in the network. The relative tempo between each agent and its neighbors is shown to be closely related to the directed spanning tree of the underlying network in a quantitative manner. Based on this fact, a local neighbor selection protocol is subsequently provided to construct the global refined communication structure which can both maintain the connectivity and increase the efficiency of the multi-vehicle coordination. The numerical study is finally provided to demonstrate the effectiveness of our approach.

关键词： Protocols Vehicle dynamics control systems Topology Intelligent transportation systems Measurement Heuristic algorithms

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：