检索结果-内蒙古大学图书馆

A registration-aided domain adaptation network for 3D Point cloud based place recognition

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Qiao, Zhijian Hu, Hanjiang Shi, Weiang Chen, Siyuan Liu, Zhe Wang, Hesheng Department of Automation Insititue of Medical Robotics 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 Jiao Tong University Shanghai200240 China Beijing Advanced Innovation Center for Intelligent Robots and Systems Beijing Institute of Technology China Department of Mechanical Engineering Carnegie Mellon University United States Department of Computer Science and Technology University of Cambridge United Kingdom

In the field of large-scale SLAM for autonomous driving and mobile robotics, 3D point cloud based place recognition has aroused significant research interest due to its robustness to changing environments with drastic daytime and weather variance. However, it is time-consuming and effort-costly to obtain high-quality point cloud data for place recognition model training and ground truth for registration in the real world. To this end, a novel registration-aided 3D domain adaptation network for point cloud based place recognition is proposed. A structure-aware registration network is introduced to help to learn features with geometric information and a 6-DoFs pose between two point clouds with partial overlap can be estimated. The model is trained through a synthetic virtual LiDAR dataset through GTA-V with diverse weather and daytime conditions and domain adaptation is implemented to the real-world domain by aligning the global features. Our results outperform state-of-the-art 3D place recognition baselines or achieve comparable on the real-world Oxford RobotCar dataset with the visualization of registration on the virtual dataset. Copyright © 2020, The Authors. All rights reserved.

关键词： Three dimensional computer graphics

Trends and perspectives in proportional pneumatics

学校读者我要写书评

暂无评论

IOP Conference Series: Materials Science and engineering 2020年第1期997卷

作者： M Avram A I Sgârciu C Bucşan Mechanical Engineering Mechatronics and Robotics Department POLITEHNICA University of Bucharest Bucharest Romania Automatic Control and Informatics Department POLITEHNICA University of Bucharest Bucharest Romania

Trends and perspective directions in the field of pneumatic equipment and systems are first identified in the paper. Special attention is given to identifying the equipment and systems that can be adapted to the requirements imposed by a new industrial revolution - Industry 4.0. Pneumatics will continue to be an important domain and the paper presents arguments for that. The current stage of proportional pneumatics is presented and a comparison between analog and digital proportional pneumatics is made. In the final part of the paper an experimental model of a distributor controlled with modulated pulses is presented. The distributor is integrated in a system that controls the pressure in a reference volume.

关键词：

Anchor-based spatio-temporal attention 3D convolutional networks for dynamic 3D point cloud sequences

学校读者我要写书评

暂无评论

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

Simultaneous state and parameter estimation: The role of sensitivity analysis

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Liu, Jianbang Gnanasekar, Aristarchus Zhang, Yi Bo, Song Liu, Jinfeng Hu, Jingtao Zou, Tao Key Laboratory of Networked Control Systems Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Institute for Robotics & Intelligent Manufacturing Chinese Academy of Sciences Shenyang110016 China University of Chinese Academy of Sciences Beijing100049 China Department of Chemical & Materials Engineering University of Alberta EdmontonABT6G 1H9 Canada Key Laboratory of Energy Thermal Conversion & Control Southeast University Nanjing210096 China School of Mechanical and Electrical Engineering Guangzhou University Guangzhou510006 China

State and parameter estimation is essential for process monitoring and control. Observability plays an important role in both state and parameter estimation. In simultaneous state and parameter estimation, the parameters are often augmented as extra states of the original system. When the augmented system is observable, various existing state estimation approaches may be used to estimate the states and parameters simultaneously. However, when the augmented system is not observable, how we should proceed to maximally extract the information contained in the measured outputs is not clear. This paper concerns about simultaneous state and parameter estimation when the augmented system is not fully observable. Specifically, we first show how sensitivity analysis is related to observability of a dynamical system, and then illustrate how it may be used to select variables for simultaneous estimation. We also propose a moving horizon state estimation (MHE) design that can use the variable selection results in a natural way. Extensive simulations are carried out to show the efficiency of the proposed approach. Copyright © 2020, The Authors. All rights reserved.

关键词： Sensitivity analysis

Saturated Continuous Twisting Algorithm 15

学校读者我要写书评

暂无评论

Saturated Continuous Twisting Algorithm

15th International Workshop on Variable Structure Systems, VSS 2018

作者： Golkani, M.A. Fridman, L.M. Koch, S. Reichhartinger, M. Horn, M. Faculty of Electrical and Information Engineering Graz University of Technology Institute of Automation and Control Graz Austria Department of Control Engineering and Robotics Division of Electrical Engineering Engineering Faculty National Autonomous University of Mexico Mexico D.F. Mexico Institute of Automation and Control Graz University of Technology Christian Doppler Laboratory for Model Based Control of Complex Test Bed Systems Graz Austria

ISBN: (纸本)9781538664391

In this paper, a second-order system affected by perturbations is considered. A feedback control law adopting the continuous twisting algorithm is designed such that a saturated and continuous control signal is introduced to the system. In the case that a state variable is not measurable, estimate information obtained through a super-twisting observer is incorporated into the design. For the closed-loops (with and without observer), global finite-time stability properties are established. The feasibility and effectiveness of the strategy is shown employing numerical simulations. © 2018 IEEE.

关键词： Stability

Vision-based Navigation Using Deep Reinforcement Learning

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Kulhánek, Jonáš Derner, Erik de Bruin, Tim Babuška, Robert Cognitive Robotics Faculty of 3mE Delft University of Technology Delft2628 CD Netherlands Czech Institute of Informatics Robotics and Cybernetics Czech Technical University in Prague Prague16636 Czech Republic Department of Control Engineering Faculty of Electrical Engineering Czech Technical University in Prague Prague16627 Czech Republic

— Deep reinforcement learning (RL) has been successfully applied to a variety of game-like environments. However, the application of deep RL to visual navigation with realistic environments is a challenging task. We propose a novel learning architecture capable of navigating an agent, e.g. a mobile robot, to a target given by an image. To achieve this, we have extended the batched A2C algorithm with auxiliary tasks designed to improve visual navigation performance. We propose three additional auxiliary tasks: predicting the segmentation of the observation image and of the target image and predicting the depth-map. These tasks enable the use of supervised learning to pre-train a large part of the network and to reduce the number of training steps substantially. The training performance has been further improved by increasing the environment complexity gradually over time. An efficient neural network structure is proposed, which is capable of learning for multiple targets in multiple environments. Our method navigates in continuous state spaces and on the AI2-THOR environment simulator outperforms state-of-the-art goal-oriented visual navigation methods from the literature. Copyright © 2019, The Authors. All rights reserved.

关键词： Deep learning

Thermometry of photosensitive and optically induced electrokinetics chips

学校读者我要写书评

暂无评论

Microsystems & Nanoengineering 2018年第1期4卷 190-198页

作者： Feifei Wang Lianqing Liu Gongxin Li Pan Li Yangdong Wen Guanglie Zhang Yuechao Wang Gwo-Bin Lee Wen Jung Li State Key Laboratory of Robotics Shenyang Institute of AutomationChinese Academy of Sciences110016 ShenyangChina University of Chinese Academy of Sciences 100049 BeijingChina Shenzhen Academy of Robotics 518057 ShenzhenChina Key Laboratory of Advanced Process Control for Light Industry of the Ministry of Education Institute of AutomationJiangnan University214122 WuxiChina Department of Power Mechanical Engineering National Tsing Hua University30013 HsinchuTaiwan Department of Mechanical and Biomedical Engineering City University of Hong KongKowloon TongHong KongChina

Optically induced electrokinetics(OEK)-based technologies,which integrate the high-resolution dynamic addressability of optical tweezers and the high-throughput capability of electrokinetic forces,have been widely used to manipulate,assemble,and separate biological and non-biological entities in parallel on scales ranging from micrometers to ***,simultaneously introducing optical and electrical energy into an OEK chip may induce a problematic temperature increase,which poses the potential risk of exceeding physiological conditions and thus inducing variations in cell behavior or activity or even irreversible cell damage during ***,we systematically measure the temperature distribution and changes in an OEK chip arising from the projected images and applied alternating current(AC)voltage using an infrared *** have found that the average temperature of a projected area is influenced by the light color,total illumination area,ratio of lighted regions to the total controlled areas,and amplitude of the AC *** an example,optically induced thermocapillary flow is triggered by the light image-induced temperature gradient on a photosensitive substrate to realize fluidic hydrogel *** studies show that the projected light pattern needs to be properly designed to satisfy specific application requirements,especially for applications related to cell manipulation and assembly.

关键词： exceeding illumination manipulation

Recognition of patient groups with sleep related disorders using bio-signal processing and deep learning

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Jarchi, Delaram Andreu-Perez, Javier Kiani, Mehrin Vysata, Oldrich Kuchynka, Jiri Prochazka, Ales Sanei, Saeid Smart Health Technologies Group School of Computer Science and Electronic Engineering University of Essex ColchesterCO4 3SQ United Kingdom Embedded and Intelligent Systems Laboratory School of Computer Science and Electronics University of Essex ColchesterCO4 3SQ United Kingdom Department of Computing and Control Engineering University of Chemistry and Technology in Prague Prague 6166 28 Czech Republic Department of Neurology Faculty of Medicine in Hradec Králové Charles University Hradec Králové500 05 Czech Republic Czech Institute of Informatics Robotics and Cybernetics Czech Technical University in Prague Prague 6160 00 Czech Republic School of Science and Technology Nottingham Trent University NottinghamNG11 8NS United Kingdom

Accurately diagnosing sleep disorders is essential for clinical assessments and treatments. Polysomnography (PSG) has long been used for detection of various sleep disorders. In this research, electrocardiography (ECG) and electromayography (EMG) have been used for recognition of breathing and movement-related sleep disorders. Bio-signal processing has been performed by extracting EMG features exploiting entropy and statistical moments, in addition to developing an iterative pulse peak detection algorithm using synchrosqueezed wavelet transform (SSWT) for reliable extraction of heart rate and breathing-related features from ECG. A deep learning framework has been designed to incorporate EMG and ECG features. The framework has been used to classify four groups: healthy subjects, patients with obstructive sleep apnea (OSA), patients with restless leg syndrome (RLS) and patients with both OSA and RLS. The proposed deep learning framework produced a mean accuracy of 72% and weighted F1 score of 0.57 across subjects for our formulated four-class problem. © 2021, CC BY-NC-ND.

关键词： Wavelet transforms

Robust cooperative synchronization of homogeneous agents with delays on directed communication graphs

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Alikoc, Baran Hengster-Movric, Kristian Czech Institute of Informatics Robotics and Cybernetics Czech Technical University in Prague Prague160 00 Czech Republic Department of Control Engineering Faculty of Electrical Engineering Czech Czech Technical University in Prague Prague166 36 Czech Republic

This study deals with analysis and control of cooperative synchronization for identical agents interacting on a directed graph topology. The agents are considered to have general continuous linear time-invariant dynamics with homogeneous communication and/or control delays. An LMI approach based on a Lyapunov-Krasovskii functional is proposed, together with the synchronizing region concept, which decouples the single-agent dynamics from the detailed graph topology. Moreover, the conventional notion of synchronizing region is here extended by an LMI relaxation utilizing quasi-convex characteristic of the problem. This leads to less conservative results for the region of graph matrix eigenvalues in the complex domain, where the synchronization is guaranteed. The proposed method to calculate the allowable delay bound for synchronization is also less conservative as compared to the results from the literature. Furthermore, two designs for distributed state-feedback control are suggested. The precise delay value and the detailed graph topology need not be known for their application;it suffices only to know the upper bound on the delay and the approximate region where the Laplacian eigenvalues lie. Specific improvements over the results existing in the literature are demonstrated by a numerical example, which validates the proposed approaches. Copyright © 2019, The Authors. All rights reserved.

关键词： Lyapunov functions