检索结果-内蒙古大学图书馆

IEEE International Conference on Robotics and Automation (ICRA)

作者： Guangming Wang Xiaoyu Tian Ruiqi Ding Hesheng Wang Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University 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 China

Scene flow represents the motion of points in the 3D space, which is the counterpart of the optical flow that represents the motion of pixels in the 2D image. However, it is difficult to obtain the ground truth of scene flow in the real scenes, and recent studies are based on synthetic data for training. Therefore, how to train a scene flow network with unsupervised methods based on real-world data shows crucial significance. A novel unsupervised learning method for scene flow is proposed in this paper, which utilizes the images of two consecutive frames taken by monocular camera without the ground truth of scene flow for training. Our method realizes the goal that training scene flow network with real-world data, which bridges the gap between training data and test data and broadens the scope of available data for training. Unsupervised learning of scene flow in this paper mainly consists of two parts: (i) depth estimation and camera pose estimation, and (ii) scene flow estimation based on four different loss functions. Depth estimation and camera pose estimation obtain the depth maps and camera pose between two consecutive frames, which provide further information for the next scene flow estimation. After that, we used depth consistency loss, dynamic-static consistency loss, Chamfer loss, and Laplacian regularization loss to carry out unsupervised training of the scene flow network. To our knowledge, this is the first paper that realizes the unsupervised learning of 3D scene flow from monocular camera. The experiment results on KITTI show that our method for unsupervised learning of scene flow meets great performance compared to traditional methods Iterative Closest Point (ICP) and Fast Global Registration (FGR). The source code is available at: https://***/IRMVLab/3DUnMonoFlow.

关键词： Training Three-dimensional displays Laser radar Laplace equations Pose estimation Training data Cameras

来源：评论

学校读者我要写书评

暂无评论

Efficient Computer Vision-Based Excavator Bucket Fill Estimation Using Depth Map and Faster R-Cnn

SSRN

引用

SSRN 2023年

作者： Helian, Bobo Huang, Xiaoqian Yang, Meng Bian, Yongming Geimer, Marcus Institute of Mobile Machines Karlsruhe Institute of Technology Karlsruhe76131 Germany State Key Laboratory of Fluid Power and Mechatronic System Zhejiang University Hangzhou310027 China School of Mechanical Engineering Tongji University Shanghai201804 China Shanghai Engineering Research Center for Safety Intelligent Control of Building Machinery Shanghai200032 China

Excavators play an essential role in the construction industry, and the development of autonomous excavator systems is important for increasing productivity and improving worker safety. Accurate estimation of the volume of material in the excavator bucket is a key metric for monitoring and evaluating system automation performance. In this study, a novel solution is proposed that utilizes 2D depth maps as input to a faster region convolutional neural network (Faster R-CNN) model for bucket volume fill estimation. This approach achieves a high estimation accuracy while maintaining a fast real-time processing speed. In addition, a custom loss function is proposed specifically for the classification-regression task of this study to improve the network's generalization despite the data out of distribution. Comparative experiments show that the proposed approach achieves an impressive 96.91% accuracy in fill factor estimation, demonstrating its advantages and promising potential in the practical estimation of automated excavator operations. © 2023, The Authors. All rights reserved.

关键词： Automation

来源：评论

学校读者我要写书评

暂无评论

Arbitrary State Transition of Open Qubit system Based on Switching control

arXiv

引用

arXiv 2024年

作者： Wu, Guangpu Xue, Shibei Ma, Shan Kuang, Sen Dong, Daoyi Petersen, Ian R. Department of Automation Shanghai Jiao Tong University Shanghai200240 China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai200240 China School of Automation Central South University Changsha410083 China Department of Automation University of Science and Technology of China Hefei230027 China School of Engineering Australian National University CanberraACT2601 Australia

We present a switching control strategy based on Lyapunov control for arbitrary state transitions in open qubit systems. With coherent vector representation, we propose a switching control strategy, which can prevent the state of the qubit from entering invariant sets and singular value sets, effectively driving the system ultimately to a sufficiently small neighborhood of target states. In comparison to existing works, this control strategy relaxes the strict constraints on system models imposed by special target states. Furthermore, we identify conditions under which the open qubit system achieves finite-time stability (FTS) and finite-time contractive stability (FTCS), respectively. This represents a critical improvement in quantum state transitions, especially considering the asymptotic stability of arbitrary target states is unattainable in open quantum systems. The effectiveness of our proposed method is convincingly demonstrated through its application in a qubit system affected by various types of decoherence, including amplitude, dephasing and polarization decoherence. Copyright © 2024, The Authors. All rights reserved.

关键词： Asymptotic stability

来源：评论

学校读者我要写书评

暂无评论

Robust Simultaneous Tracking and Local Dense Structured Mapping at Scenes lack of Geometric Features

Robust Simultaneous Tracking and Local Dense Structured Mapp...

引用

International Conference on Mechatronics and Machine Vision in Practice (M2VIP)

作者： Yueling Shen Zhijian Qiao Xu Wang Hesheng Wang 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 Shanghai China

ISBN: (纸本)9781665431545

In this paper, we present a simultaneous tracking and dense structured mapping method aimed at robotic tasks including obstacle avoidance, path planning and manipulation. This is achieved through (1) sparse-to-dense pose estimation with both keypoints and dense vertex images for keeping robust at scenes lack of geometric features, (2) dense local map algorithm, which clears map outside the neighborhood of the robot for the consistency of the system at large-scale scenes, (3) structured analysis to obtain elevation and norms of surfaces, (4) the proposed dynamic mode for ghosting-free mapping in dynamic scenes. Experiments are conducted to evaluate each part of the system. The effectiveness and efficiency are proved by quantitative experiments.

关键词： Meters Surface reconstruction Three-dimensional displays Mechatronics Heuristic algorithms Pose estimation Path planning

来源：评论

学校读者我要写书评

暂无评论

Sewage sludge pyrolysis ‘kills two birds with one stone’: Biochar synergies with persulfate for pollutants removal and energy recovery

引用

Chemosphere 2024年 363卷 142824页

作者： Li, Shaoya Zhou, Yanmei Wang, Jin Dou, Mengmeng Zhang, Qingyun Huo, Kaili Han, Chao Shi, Jinyang School of Environment Beijing Key Laboratory of Aqueous Typical Pollutants Control and Water Quality Safeguard Beijing Jiaotong University Haidian District Beijing100044 China The Center of National Railway Intelligent Transportation System Engineering and Technology China Academy of Railway Sciences Corporation Limited Beijing100081 China School of Traffic and Transportation Beijing Jiaotong University Haidian District Beijing100044 China

The disposal and resource utilization of sewage sludge (SS) have always been significant challenges for environmental protection. This study employed straightforward pyrolysis to prepare iron-containing sludge biochar (SBC) used as a catalyst and to recover bio-oil used as fuel energy. The results indicated that SBC-700 could effectively activate persulfate (PS) to remove 97.2% of 2,4-dichlorophenol (2,4-DCP) within 60 min. Benefiting from the appropriate iron content, oxygen-containing functional groups and defective structures provide abundant active sites. Meanwhile, SBC-700 exhibits good stability and reusability in cyclic tests and can be easily recovered by magnetic separation. The role of non-radicals is emphasized in the SBC-700/PS system, and in particular, single linear oxygen (1O2) is proposed to be the dominant reactive oxygen. The bio-oil, a byproduct of pyrolysis, exhibits a higher heating value (HHV) of about 30 MJ/kg, with H/C and O/C ratios comparable to those of biodiesel. The energy recovery rate of the SS pyrolysis system was calculated at 80.5% with a lower input cost. In conclusion, this investigation offers a low-energy consumption and sustainable strategy for the resource utilization of SS while simultaneously degrading contaminants. © 2024

关键词： Sewage sludge

来源：评论

学校读者我要写书评

暂无评论

Event-triggered model predictive control for cyber-physical system under false data injection attacks

Event-triggered model predictive control for cyber-physical ...

引用

第33届中国过程控制会议

作者： Bin Zhang Zhiwen Wang Yanrong Lu Long Li College of Electrical and Information Engineering Lanzhou University of Technology Key Laboratory of Gansu Advanced Control for Industrial Processes Lanzhou University of Technology National Demonstration Center for Experimental Electrical and Control Engineering Education Lanzhou University of Technology GS-Unis Intelligent Transportation System&Control Technology Co. Ltd.

In this paper,an event-triggered model predictive control strategy is proposed for cyber-physical systems under the perception of false data injection *** on attack perception,two different event-triggered mechanisms are designed for the sensor-to-controller channel and the controller-to-actuator *** the sensor-to-controller channel,the event-triggered strategy 1 effectively reduces the network bandwidth pressure caused by the sensor *** the controller-actuator channel,the event-triggered model predictive control strategy effectively compensates for the adverse effects of signal data loss or unavailability of signal data caused by spurious data injection ***,the simulation of the networked first-order inverted pendulum model shows the effectiveness of the proposed methods.

关键词： Cyber-physical systems False data injection attacks Event-triggered mechanism Model predictive control

来源：评论

学校读者我要写书评

暂无评论

A SINS Error Correction Approach Based on Dual-Threshold ZV Detection and Cubature Kalman Filter

A SINS Error Correction Approach Based on Dual-Threshold ZV ...

引用

IEEE International Conference on systems, Man and Cybernetics

作者： Ruijie Xu Shichao Chen Wenqiao Sun Yisheng Lv Jialiang Luo Ying Tang The State Key Laboratory for Management and Control of Complex System State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences College of Information Science & Technology Beijing University of Chemical Technology Beijing China The State Key Laboratory for Management and Control of Complex System State Key Laboratory of Multimodal Artificial Intelligence Systems The Center of National Railway Intelligent Transportation System Engineering and Technology Institute of Automation Chinese Academy of Sciences China Academy of Railway Sciences Corporation Limited Beijing China China Academy of Railway Sciences Corporation Limited Transportation and Economics Research Institute and the Center of National Railway Intelligent Transportation System Engineering and Technology Beijing China The State Key Laboratory for Management and Control of Complex System State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China The State Key Laboratory for Management and Control of Complex System State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences School of Information Engineering China University of Geosciences Beijing Beijing China Department of Electrical and Computer Engineering Rowan University Glassboro USA

Global Navigation Satellite systems (GNSS) can provide real-time positioning information for outdoor users, but cannot for indoor scenarios or heavily occluded outdoor scenarios. Strap-down Inertial Navigation system (SINS) are widely used to locate people in complex interior or heavily occluded outdoor scenarios due to its light weight and low power consumption. However, IMU of SINS are noisy, and the sampling data error is large, which is a divergence of the error with time. Therefore, it will generate a positioning accumulation error, which affects the final positioning accuracy. The problem of cumulative IMU errors is usually dealt with by Zero-Velocity Update (ZUPT). The zero-velocity detection part of basic ZUPT method usually uses a single threshold to determine the gait of pedestrian, which often has the problem of gait misjudgment and omission. To address these problems, this paper proposes a composite conditional detection method to solve the problem of misjudgment in the zero-velocity interval. In addition, we redesign the zero-velocity update algorithm and uses the Cubature Kalman filter (CKF) for pedestrian positioning error correction. The experimental results demonstrate that the proposed ZUPT method based on dual-threshold detection can better detect the interval between pedestrian motion and stationery than ones with single threshold. The zero-velocity update algorithm based on CKF has higher performance than conventional EKF and UKF methods, which constrains the cumulative error of SINS to about 0.2% of the whole walking distance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Simulation study on control characteristics of semiconductor grade monocrystalline silicon growth process

Simulation study on control characteristics of semiconductor...

引用

Chinese Automation Congress (CAC)

作者： Yuyu Liu Ding Liu Zezhong Song Local Joint Engineering Research Center of Crystal Growth Equipment and System Integration Xiàn University of Technology Xiàn China Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xiàn University of Technology Xiàn China

The growth of Czochralski(CZ) monocrystalline silicon is a nonlinear dynamic time-varying system with complex physical changes and multi-field and multi-phase coupling. In order to meet the needs of information development, it is urgent to develop large-scale, high-quality monocrystalline silicon. However, it is extremely difficult to establish an accurate control system model. Therefore, this paper considers the complex physical changes of multi-field coupling and non-linear processes in the growth of CZ monocrystalline silicon, a lumped parameter model for the growth of monocrystalline silicon is established based on energy balance model, fluid mechanics model, and geometry model, according to the internal mechanism of the monocrystalline silicon growth and the transfer mechanism of internal material flow. According to the model, a CZ monocrystalline silicon growth simulation control system is established under the Matlab/Simulink environment, and the real-time simulation data of each state variable of crystal growth is obtained. So that the control characteristics of each state variable in the crystal growth process can be analyzed. Finally, the validity of the established model is checked by the records evaluation of the semiconductor industry production process. Finally, the validity of the established model is verified based on the data analysis of the semiconductor industry production process. The results show that the model has high accuracy and can better describe the dynamic behavior of the actual monocrystalline silicon growth system.

关键词： Semiconductor device modeling Crystal growth Analytical models Electronics industry Process control Production Crystals

来源：评论

学校读者我要写书评

暂无评论

An accurate stop control method of high-speed rolling machine for automobile production line using laser ranging and two positon close loop

An accurate stop control method of high-speed rolling machin...

引用

2020 International Conference on Applied Mechanics and Mechanical engineering, ICAMME 2020

作者： Qiao, Zhifeng Ge, Weimin Zhang, Haikang Wei, Huiyong Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin University of Technology Tianjin300384 China National Demonstration Center for Experimental Mechanical and Electrical Engineering Education Tianjin University of Technology China NO.591Changjiang Road Nankai DistrictTianjin China

The high-speed rolling machine is a key equipment in the automatic production line of automobile body-in-white welding. This article focuses on analyzing a method for accurately stopping the high-speed rolling machine using laser distance measurement. Firstly, through the analysis of the movement process, the calculation method of the length of each period in the 7-stage S-type acceleration and deceleration in the movement of the high-speed rolling machine is given;secondly, the system control theory model of the measurement and control system is established to analyze the dual-position closed-loop strategy The method of realizing the accurate stopping of the high-speed rolling machine;finally, the accurate stopping control method of the high-speed rolling machine proposed in this paper was verified by building an experimental system and developing the corresponding control program. © 2021 Institute of Physics Publishing. All rights reserved.

关键词： Speed

来源：评论

学校读者我要写书评

暂无评论

Road Damage Detection and Classification Based on Multi-Scale Contextual Features

Road Damage Detection and Classification Based on Multi-Scal...

引用

IEEE International Conference on Big Data

作者： Lu Yang Hualin He Tao Liu Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin University of Technology Tianjin China National Demonstration Center for Experimental Mechanical and Electrical Engineering Education Tianjin University of Technology Tianjin China

ISBN: (纸本)9781665480468

Road damage detection is particularly essential for improving road traffic safety. Existing methods do not perform well due to complex road conditions and sparse features contained in road damage. Therefore, we propose a new road damage detection network - YPLNet, which could obtain more refined multi-scale contextual features. Specifically, the network proposed in this paper is based on YOLOv5, by adding the PSA module to the backbone network, the spatial information of the feature map at multi-scale is obtained to enrich the feature space, and the long-term information dependence between channels is further constructed. In addition, in the feature fusion stage, the LCFI module is utilized to obtain contextual features under the multi-scale receptive fields, and these contextual features include rich low-level and high-level information. Our proposed network achieves a Mean-F1 Score of 0.635 in the competition. The source code and model are publicly available at https://***/hehualin-tut/YPLNet

关键词： Roads Source coding Big Data Feature extraction Data models Safety Context modeling

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：