检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Zhang, Hui Chen, Yurong Wang, Yaonan Cao, Yihong Wu, Q.M. Jonathan Yang, Yimin National Engineering Laboratory of Robot Visual Perception and Control Technology School of Robotics Hunan University Changsha Hunan410082 China Department of Electrical and Computer Engineering University of Windsor WindsorONN9B3P4 Canada Department of Computer Science Lakehead University OntarioP7B 5E1 Canada Vector Institute TorontoM5G 1M1 Canada

To mitigate the inspector’s workload and improve the quality of the product, computer vision-based anomaly detection (AD) techniques are gradually deployed in real-world industrial scenarios. Recent anomaly analysis benchmarks progress to generative models. The aim is to model the defect-free distribution so that anomalies can be classified as out-of-distribution samples. Nevertheless, there are two disturbing factors that need researchers and deployers to prioritize: (i) the simplistic prior latent distribution inducing limited expressive capability;(ii) the collapsed mutual-dependent features resulting in poor generalization. In this paper, we propose a novel Patch-wise Wasserstein AutoEncoder (P-WAE) architecture to alleviate those challenges. In particular, a patch-wise variational inference model coupled with solving the jigsaw puzzle is designed, which is a simple yet effective way to increase the expressiveness and complexity of the latent manifold. This alleviates the blurry reconstruction problem. In addition, the Hilbert-Schmidt Independence Criterion (HSIC) bottleneck is introduced to constrain the over-regularization representation. Comprehensive experiments, conducted on the MVTec AD dataset, demonstrate the superior performance of our proposed method. © 2021, CC BY.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Projected Sliced Wasserstein Autoencoder-based Hyperspectral Images Anomaly Detection

arXiv

引用

arXiv 2021年

作者： Chen, Yurong Zhang, Hui Wang, Yaonan Wu, Q. M. Jonathan Yang, Yimin National Engineering Laboratory of Robot Visual Perception and Control Technology School of Robotics Hunan University Hunan Changsha410082 China Department of Electrical and Computer Engineering University of Windsor WindsorONN9B3P4 Canada Department of Computer Science Lakehead University ONP7B 5E1 Canada Vector Institute TorontoONM5G 1M1 Canada

Anomaly detection refers to identifying the observation that deviates from the normal pattern, which has been an active research area in various domains. Recently, the increasing data scale, complexity, and dimension turns the traditional representation and statistical-based outlier detection method into challenging. In this paper, we leverage the generative model in hyperspectral images anomaly detection. The gist is to model the distribution of the normal data, while the out-of-distribution sample can be viewed as the outlier. At first, the variational inference-based anomaly detection methods are investigated. We theoretically and empirically find that they are unstable due to the strong notion of distance (f-divergence) served as the regularization. Secondly, this paper introduces sliced Wasserstein distance, which is a weaker distribution measure compared with f-divergence. However, the number of randomly slicing poses a difficulty to estimate the true distance. In the end, we propose a projected sliced Wasserstein (PSW) autoencoder-based anomaly screening method. In particular, we leverage a computation-friendly eigen-decomposition method to find the principal component as slicing the high-dimensional data. Furthermore, our proposed distance can be calculated with the closed-form, even the prior distribution is not Gaussian. Comprehensive experiments conducted on various real-world hyperspectral anomaly detection benchmarks demonstrate the superior performance of our proposed method. © 2021, CC BY.

关键词： Spectroscopy

来源：评论

学校读者我要写书评

暂无评论

3D Hierarchical Refinement and Augmentation for Unsupervised Learning of Depth and Pose from Monocular Video

arXiv

引用

arXiv 2021年

作者： Wang, Guangming Zhong, Jiquan Zhao, Shijie Wu, Wenhua Liu, Zhe Wang, Hesheng Department of Automation Institute of Medical Robotics Key Laboratory of System Control and Information Processing 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 Engineering Mechanics Shanghai Jiao Tong University Shanghai200240 China Department of Computer Science and Technology University of Cambridge CambridgeCB2 1TN United Kingdom

Depth and ego-motion estimations are essential for the localization and navigation of autonomous robots and autonomous driving. Recent studies make it possible to learn the per-pixel depth and ego-motion from the unlabeled monocular video. A novel unsupervised training framework is proposed with 3D hierarchical refinement and augmentation using explicit 3D geometry. In this framework, the depth and pose estimations are hierarchically and mutually coupled to refine the estimated pose layer by layer. The intermediate view image is proposed and synthesized by warping the pixels in an image with the estimated depth and coarse pose. Then, the residual pose transformation can be estimated from the new view image and the image of the adjacent frame to refine the coarse pose. The iterative refinement is implemented in a differentiable manner in this paper, making the whole framework optimized uniformly. Meanwhile, a new image augmentation method is proposed for the pose estimation by synthesizing a new view image, which creatively augments the pose in 3D space but gets a new augmented 2D image. The experiments on KITTI demonstrate that our depth estimation achieves state-of-the-art performance and even surpasses recent approaches that utilize other auxiliary tasks. Our visual odometry outperforms all recent unsupervised monocular learning-based methods and achieves competitive performance to the geometry-based method, ORB-SLAM2 with back-end optimization. Copyright © 2021, The Authors. All rights reserved.

关键词： Robots

来源：评论

学校读者我要写书评

暂无评论

OTE: Optimal Trustworthy EdgeAI solutions for smart cities

OTE: Optimal Trustworthy EdgeAI solutions for smart cities

引用

IEEE/ACM International Symposium on Cluster Computing and the Grid (CCGRID)

作者： Vasileios Mygdalis Lorenzo Carnevale Jose Ramiro Martí nez-De-Dios Dmitriy Shutin Giovanni Aiello Massimo Villari Ioannis Pitas Department of Informatics Aristotle University of Thessaloniki Thessaloniki Greece Department of Mathematical and Computer Science Physics and Hearth Sciences University of Messina Messina Italy Gruppo Nazionale per il Calcolo Scientifico (GNCS) Istituto Nazionale di Alta Matematica (INdAM) &#x201C F. Severi&#x201D Rome Italy Robotics Vision and Control Group University of Seville Seville Spain Institute of Communications and Navigation German Aerospace Center (DLR) Wessling Germany Research and Development Lab. Engineering Ingegneria Informatica S.p.A Rome Italy

This work studies and defines the problem of providing extensive and opportunistic Edge AI-based area coverage in smart city application scenarios, by researching and determining the optimal configuration of sensing and computational resources for minimizing the environmental/technology footprint of the solution. A typical smart city computing continuum consists of statically installed multimodal sensing Internet-of-Things (IoT) nodes at various city locations, accompanied by interconnected computational Cloud/Edge/IoT nodes. This paper presents Optimal Trustworthy EdgeAI (OTE), an entirely novel research pipeline, that complements existing smart city infrastructure with intelligent drone Edge/IoT nodes (in the form of modularly equipped unmanned aerial vehicles), capable of autonomous repositioning according to individual/collective sensing and coverage criteria. Thereby, we envisage the emerging cutting-edge technologies of trustworthy sensing, perceiving, modelling technologies for predicting the behavior of moving targets (e.g., citizens/vehicles/objects), understanding natural phenomena (e.g., sea wave motion, urban flora/fauna, biodiversity) in order to anticipate events (people's bad habits, environmental changes), by exploiting novel continuous data processing services across the whole span of the enhanced Cloud-Edge-IoT computing continuum.

关键词： Cloud computing Privacy Smart cities Pipelines Semantics Robot sensing systems Software

来源：评论

学校读者我要写书评

暂无评论

Flight control design for a highly flexible flutter demonstrator

Flight control design for a highly flexible flutter demonstr...

引用

AIAA Scitech Forum, 2019

作者： Luspay, Tamás Baár, Tamás Teubl, Dániel Vanek, Bálint Ossmann, Daniel Wüstenhagen, Matthias Pusch, Manuel Kier, Thiemo Waitman, Sérgio Iannelli, Andrea Marcos, Andres Lowenberg, Mark Systems and Control Lab Institute for Computer Science and Control Kende u 13-17 Budapest Hungary DLR German Aerospace Center Institute of Robotics and Mechatronics Wessling82234 Germany Aerospace Engineering Department University of Bristol University Walk BristolBS8 1TR United Kingdom

ISBN: (数字)9781624105784

ISBN: (纸本)9781624105784

The paper presents the control design approaches for the European research project FLEXOP. The ultimate goal is to develop and apply active flutter suppression and load alleviation techniques on an unmanned flying aircraft demonstrator. Due to the flexible wing of the aircraft new challenges rise for the control design: the traditional rigid body (baseline) control loops have to be augmented with flutter control laws. In our approach, the controllers are designed based on a dynamical model, which is briefly discussed first. Details of the baseline control design, as well as the two different flutter suppression algorithms are discussed in the paper. Hardware-in-the-Loop testing of the controllers are reported before the first test flights of the aircraft. © 2019, American institute of Aeronautics and Astronautics Inc, AIAA. All rights reserved.

关键词： controllers

来源：评论

学校读者我要写书评

暂无评论

Dense r-robust formations on lattices

Dense r-robust formations on lattices

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Luis Guerrero-Bonilla David Saldaña Vijay Kumar Division of Decision and Control Systems in the School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden Autonomous and Intelligent Robotics Laboratory (AIRLab) Lehigh University Bethlehem PA USA GRASP Laboratory University of Pennsylvania

ISBN: (数字)9781728173955

ISBN: (纸本)9781728173962

Robot networks are susceptible to fail under the presence of malicious or defective robots. Resilient networks in the literature require high connectivity and large communication ranges, leading to high energy consumption in the communication network. This paper presents robot formations with guaranteed resiliency that use smaller communication ranges than previous results in the literature. The formations can be built on triangular and square lattices in the plane, and cubic lattices in the three-dimensional space. We support our theoretical framework with simulations.

关键词： Lattices Robot kinematics Communication networks Robustness Robot sensing systems Energy consumption

来源：评论

学校读者我要写书评

暂无评论

Adaptive tracking control of flapping wing micro-air vehicles with averaging theory

引用

CAAI Transactions on Intelligence Technology 2018年第1期3卷 18-27页

作者： Chen Qian Yongchun Fang Institute of Robotics and Automatic Information Systems College of Computer and Control Engineering Tianjin 300353People's Republic of China Tianjin Key Laboratory of Intelligent Robotics Nankai University Tianjin 300353 People's Republic of China

An input constrained adaptive tracking controller is designed for flapping micro aerial vehicles, wherein the moving averaging filter is adopted to estimate the averaged states of the system. Specifically, in the outer loop controller, an observer is constructed to estimate the disturbances within the system. Moreover, the constrained thrust is designed to keep the frequency in a proper region so as to meet the requirement of average estimation. Then, a tracking differentiator is used to provide trackable trajectories for the inner loop. Subsequently, a new quaternion- based hybrid attitude tracking controller is designed which successfully deals with high-frequency noises and avoids possible chattering. As supported by mathematical analysis, the proposed control strategy guarantees the uniform ultimate boundedness of the closed-loop system, and it keeps the control torques within the permitted range to meet the application requirement. At last, numerical simulations are carried out to support the validity of the proposed controller, whose results are satisfactory even when the thrust and torques are saturated.

关键词：飞行器跟踪器人工智能发展现状

来源：评论

学校读者我要写书评

暂无评论

Accurate object recognition for unmanned aerial vehicle electric power inspection using an improved YOLOv2 algorithm 4

Accurate object recognition for unmanned aerial vehicle elec...

引用

4th IEEE International Conference on Data Science in Cyberspace, DSC 2019

作者： Chen, Qiang Gao, Yunyuan Peng, Yun Zhang, Jianhai Sun, Ke Intelligent Control and Robotics Institute Hangzhou Dianzi University Hangzhou China Department of Biomedical Engineering University of Houston Houston United States School of Computer Science and Technology Hangzhou Dianzi University Hangzhou China Hangzhou Chuangjiang Information Technology Co. Ltd. Hangzhou China

ISBN: (纸本)9781728145280

With the growing application of Unmanned Aerial Vehicle (UAV) in the electric power inspection, there is an increasing demand for accurate recognition of power tower components from a large number of pictures and videos. Traditional machine learning methods require feature extraction of, such as edge, color, texture, etc., are not suitable for the complex scene of the UAV electric power inspection. The end-toend object detection algorithm YOLOv2, offers overall high recognition accuracy and speed, but is less so in recognizing small targets. In this study, the YOLOv2 was improved by: 1)adding an additional passthrough layer to the original network to fuse more fine-grained features to improve the recognition capability for small targets, and 2) removing the redundant convolutional layers and reducing the number of the filters in the middle convolutional layers to simplify the network structure. The datasets are from Multi-rotor UAV inspection of high voltage transmission lines. Three types of power tower components including the tower, tower base, and signs are selected as recognition targets. Results showed that the mean average precision (mAP) of the improved model for three types of target recognition was increased to 98.19%, higher than that of the original one, and the recognition speed was increased by 35%. © 2019 IEEE.

关键词： Inspection

来源：评论

学校读者我要写书评

暂无评论

Discrete Fourier Transform based Virtual Constraint control of Powered Ankle-Foot Prosthesis

Discrete Fourier Transform based Virtual Constraint Control ...

引用

International Conference on robotics and Artificial Intelligence (ICRAI)

作者： Awais Naeem Mohsin Rizwan Hafiz Farhan Maqbool Muhammad Ahsan Ali Raza Syed Abbas Zilqurnain Naqvi Al-Khwarizmi Institute of Computer Science UET Lahore HCR Lab National Center of Robotics and Automation Lahore Pakistan Department of Mechatronics and Control Engineering National Center of Robotics and Automation Lahore Pakistan Department of Mechatronics and Control Engineering UET Lahore Lahore Pakistan

Active prosthetic devices have been controlled using several methods such as Echo control, EMG signal based Position control and Finite State Machine (FSM) based Impedance/Compliance control. This manuscript proposes Virtual Constraint control of active prosthesis which obviates any need for the classification of EMG signals, identification of the gait phase for state switching and potentially avoids an exhaustive procedure for the tuning of impedance parameters. In this paper, a Discrete Fourier Transform (DFT) based Virtual Constraint control is presented to characterize the ankle-foot joint trajectory as a function of the human-inspired phase variable in a unified manner. An optimization-based algorithm is employed for the robust generation of continuously monotonic and linear phase variable for DFT based Virtual Constraint control. The results are generalized across various walking speeds for a specific user during the level ground walking.

关键词：

来源：评论

学校读者我要写书评

暂无评论

H∞ Model-free Reinforcement Learning with Robust Stability Guarantee

arXiv

引用

arXiv 2019年

作者： Han, Minghao Zhang, Lixian Tian, Yuan Wang, Jun Pan, Wei Department of Control Science and Engineering Harbin Institute of Technology Department of Cognitive Robotics Delft University of Technology Department of Computer Science University College London

Reinforcement learning is showing great potentials in robotics applications, including autonomous driving, robot manipulation and locomotion. However, with complex uncertainties in the real-world environment, it is difficult to guarantee the successful generalization and sim-to-real transfer of learned policies theoretically. In this paper, we introduce and extend the idea of robust stability and H∞ control to design policies with both stability and robustness guarantee. Specifically, a sample-based approach for analyzing the Lyapunov stability and performance robustness of a learning-based control system is proposed. Based on the theoretical results, a maximum entropy algorithm is developed for searching Lyapunov function and designing a policy with provable robust stability guarantee. Without any specific domain knowledge, our method can find a policy that is robust to various uncertainties and generalizes well to different test environments. In our experiments, we show that our method achieves better robustness to both large impulsive disturbances and parametric variations in the environment than the state-of-art results in both robust and generic RL, as well as classic control. Anonymous code is available to reproduce the experimental results at https://***/RobustStabilityGuaranteeRL/RobustStabilityGuaranteeRL. Copyright © 2019, The Authors. All rights reserved.

关键词： Reinforcement 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：