检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Ervan, Osman Temeltas, Hakan Department of Control and Automation Engineering Faculty of Electric and Electronics Istanbul Technical University Ayazaga Campus Sariyer Istanbul Maslak34469 Turkey

Three-dimensional (3D) point cloud registration is a fundamental process in the fields of computer vision and robotics. It enables the alignment and fusion of multiple point cloud datasets acquired from diverse viewpoints or distinct temporal instances. The rapid progress of 3D sensing technologies in 3D LiDAR sensors has led to the widespread availability of point cloud data across various applications, including robotics, autonomous navigation, object recognition, and cultural heritage preservation. Nevertheless, the inherent presence of noise, occlusions, and varying scales within acquired point clouds presents significant challenges in achieving precise registration. In this paper, we proposed a Multi-Level Global Registration algorithm, referred to as MULEG. Geometric features of the points have been extracted using eigenvalue and eigenvector-based multi-level similarity metrics. During pairwise registrations, changing the input point cloud between source and target can impact the registration performance. To address this issue, we introduced a correspondence intersection search mechanism, which effectively overcomes this problem. The similarity percentage metric calculation procedure generates the probability of two correspondence pairs being an exact match. These robust tools enhance the quality of the coarse registration, not only in terms of accuracy but also in terms of time consumption. Finally, the results of the coarse registration are updated in the fine registration step, completing the coarse-to-fine registration pipeline. The contribution of this proposed method lies in the enhancement of coarse registration accuracy, coupled with a reduction in the time required for fine registration. Comprehensive experimentation confirms that the proposed algorithm yields favorable outcomes, encompassing a high rate of successful registration, precise rotation estimation, accurate translation estimation, efficient runtime, and notably, surpasses the capabilities

关键词： Nearest neighbor search

来源：评论

学校读者我要写书评

暂无评论

Weakly-supervised causal discovery based on fuzzy knowledge and complex data complementarity

arXiv

引用

arXiv 2024年

作者： Li, Wenrui Zhang, Wei Zhang, Qinghao Zhang, Xuegong Wang, Xiaowo The Department of Automation Tsinghua University Beijing100084 China The School of Control Science and Engineering Shandong University Shandong Jinan250061 China The Department of Electrical Engineering Tsinghua University Beijing100084 China

Causal discovery based on observational data is important for deciphering the causal mechanism behind complex systems. However, the effectiveness of existing causal discovery methods is limited due to inferior prior knowledge, domain inconsistencies, and the challenges of high-dimensional datasets with small sample sizes. To address this gap, we propose a novel weakly-supervised fuzzy knowledge and data co-driven causal discovery method named KEEL. KEEL adopts a fuzzy causal knowledge schema to encapsulate diverse types of fuzzy knowledge, and forms corresponding weakened constraints. This schema not only lessens the dependency on expertise but also allows various types of limited and error-prone fuzzy knowledge to guide causal discovery. It can enhance the generalization and robustness of causal discovery, especially in high-dimensional and small-sample scenarios. In addition, we integrate the extended linear causal model (ELCM) into KEEL for dealing with the multi-distribution and incomplete data. Extensive experiments with different datasets demonstrate the superiority of KEEL over several state-of-the-art methods in accuracy, robustness and computational efficiency. For causal discovery in real protein signal transduction processes, KEEL outperforms the benchmark method with limited data. In summary, KEEL is effective to tackle the causal discovery tasks with higher accuracy while alleviating the requirement for extensive domain expertise. Copyright © 2024, The Authors. All rights reserved.

关键词： Signal transduction

来源：评论

学校读者我要写书评

暂无评论

Liquid Filling Quality control System for Beverage Industry Using Image Processing (CNN)

Liquid Filling Quality Control System for Beverage Industry ...

引用

International Conference on control, automation and Systems ( ICCAS)

作者： B. Chatchapol W. Autanan W. Anan Department of Electrical Engineering Faculty of Electric Engineering Rajamangala University of Technology Lanna Chiang Mai Thailand Robotics Engineering and AI Faculty of Engineering Chiang Mai University Chiang Mai Thailand Department of Electronic Engineering and Automation Control System Faculty of Engineering Rajamangala University of Technology Lanna Chiang Mai Thailand

ISBN: (数字)9788993215380

ISBN: (纸本)9798331517939

The beverage industry has been leveraging automation to enhance production efficiency. An essential advancement involves the use of AI and image processing to ensure the high quality of products. Image processing systems employ sophisticated algorithms to meticulously inspect specific aspects of the production process (liquid level, lid sealing, text print). The CNN algorithm is primarily utilized to scrutinize water bottle images to verify their quality. Maintaining consistent production speed poses a challenge, underscoring the importance of examining the image processing system from various perspectives. The research proposed implementing a system that oversees liquid filling quality through an image processing algorithm, a camera module, and conveyor belt speed control to address. This system monitors liquid levels and bottle capping while the production line is operational. On average, the system achieves a 98.89 percent accuracy rate in detecting liquid levels and a 100 percent accuracy rate in sealing the lids. Furthermore, the conveyor speed control can adjust automatically to detect variations in product movement speed.

关键词： Liquids Image processing Velocity control Production Quality control Inspection Belts Filling Beverage industry Monitoring

来源：评论

学校读者我要写书评

暂无评论

Dashing for the Golden Snitch: Multi-Drone Time-Optimal Motion Planning with Multi-Agent Reinforcement Learning

arXiv

引用

arXiv 2024年

作者： Wang, Xian Zhou, Jin Feng, Yuanli Mei, Jiahao Chen, Jiming Li, Shuo College of Control Science and Engineering Zhejiang University Hangzhou310027 China Department of Automation Zhejiang University of Technology Hangzhou310023 China

Recent innovations in autonomous drones have facilitated time-optimal flight in single-drone configurations, and enhanced maneuverability in multi-drone systems by applying optimal control and learning-based methods. However, few studies have achieved time-optimal motion planning for multi-drone systems, particularly during highly agile maneuvers or in dynamic scenarios. This paper presents a decentralized policy network using multi-agent reinforcement learning for time-optimal multi-drone flight. To strike a balance between flight efficiency and collision avoidance, we introduce a soft collision-free mechanism inspired by optimization-based methods. By customizing PPO in a centralized training, decentralized execution (CTDE) fashion, we unlock higher efficiency and stability in training while ensuring lightweight implementation. Extensive simulations show that, despite slight performance trade-offs compared to single-drone systems, our multi-drone approach maintains near-time-optimal performance with a low collision rate. Real-world experiments validate our method, with two quadrotors using the same network as in simulation achieving a maximum speed of 13.65 m/s and a maximum body rate of 13.4 rad/s in a 5.5 m×5.5 m×2.0 m space across various tracks, relying entirely on onboard computation [video3][code4]. Copyright © 2024, The Authors. All rights reserved.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Simulation and Analysis of PMSM with Segmented Halbach Magnet Array

Simulation and Analysis of PMSM with Segmented Halbach Magne...

引用

International Conference on Guidance, Navigation and control, ICGNC 2022

作者： Ge, Lijia Yan, Liang Xiang, Pengjie Zhou, Yuchen Aboelhassan, Ahmed School of Automation Science and Electrical Engineering Beihang University Beijing100191 China Science and Technology on Aircraft Control Laboratory Beihang University Beijing100191 China Ningbo Institute of Technology Beihang University Ningbo315800 China Electrical and Control Engineering Department College of Engineering and Technology Arab Academy for Science Technology and Maritime Transport Alexandria1029 Egypt Key Laboratory of More Electric Aircraft Technology of Zhejiang Province University of Nottingham Ningbo China Ningbo315100 China

ISBN: (纸本)9789811966125

This paper investigates the relationship between the output performance of PMSM and the number of the Halbach magnetic segments. The static magnetic simulation models of the Halbach with three to seven segments are established, and the spatial harmonic distribution of these magnetic arrays under the static magnetic field is analyzed. The simulation date indicates that the five-segment configuration has the best suppression effect on the 5th harmonic, and the seven-segment Halbach magnet array has the maximum fundamental amplitude of magnetic flux density. Then, the transient magnetic simulation models of these magnetic configuration are established by FEM, and the dynamic performance in PMSM is simulated and analyzed. By comparing the simulation data, it indicates that the electromagnetic output performance of five-segment magnetic configuration is the best. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Harmonic analysis

来源：评论

学校读者我要写书评

暂无评论

Real-Time Identification and Self-Tuning PID controller for 1-DOF Helicopter System

Real-Time Identification and Self-Tuning PID Controller for ...

引用

Human-Computer Interaction, Optimization and Robotic Applications (HORA), International Congress on

作者： Enes Erdoğan Aydoğan Soylu Şahin Serhat Şeker Barış Başpınar Tufan Kumbasar Aeronautical Engineering Department Istanbul Technical University Istanbul Turkey Control and Automation Engineering Department Istanbul Technical University Istanbul Turkey Electrical Engineering Department Istanbul Technical University Istanbul Turkey AI and Intelligent Systems Laboratory Istanbul Technical University Istanbul Turkey

ISBN: (数字)9798331510886

ISBN: (纸本)9798331510893

Obtaining an accurate mathematical model is critical in control design applications. Therefore, the parameter uncertainties that occur during modeling or operation should be identified, and the controller design should be made to compensate for these uncertainties. In this paper, a system identification study was performed with a global-based Big Bang-Big Crunch optimization algorithm using input and output data from the one degree of freedom helicopter system. System dynamics are determined using this optimization algorithm over the flowing data, and the transfer function that best represents the system's behavior is obtained. A discrete time Proportional Integral Derivative (PID) controller is designed to minimize the overshoot and steady-state error of the system response with the same optimization algorithm. This process was used to automatically detect parametric uncertainties as long as the system receives input-output data, and to create a tuned PID controller structure. In order to demonstrate the superiority of the proposed methodology, initial PID is designed for the real-time system, and the performance of this PID and the tuned PID controller is compared under the parameter uncertainty. As a result, it is ensured that the tuned PID structure has the desired transient response dynamics of the system under parameter uncertainty compared to the initial PID structure.

关键词： Uncertain systems Transient response Uncertainty Heuristic algorithms Helicopters Transfer functions Real-time systems Mathematical models System identification Optimization

来源：评论

学校读者我要写书评

暂无评论

Expression recognition based on convolutional difference contextual feature fusion

Expression recognition based on convolutional difference con...

引用

2022 International Conference on Electronic Information engineering and Computer Science, EIECS 2022

作者： Lu, Shengfu Yang, Chuang Li, Mi Kang, Jiaming Faculty of Information Technology Beijing University of Technology Beijing International Collaboration Base on Brain Informatics and Wisdom Services Engineering Research Center of Intelligent Perception and Autonomous Control Ministry of Education Beijing China Department of Automation Faculty of Information Technology Beijing University of Technology Beijing China Department of Automation Faculty of Information Technology Beijing China

ISBN: (纸本)9781510663312

Facial expression recognition has always been a focus of study in emotion computing. With the aim of solving the problem that previous facial expression recognition studies are susceptible to individual differences and background noise, as well as the loss of facial expression features in deep networks of deep convolutional networks, we propose a facial expression method based on convolutional difference contextual feature fusion. The convolutional difference module can carry out difference operation between emotional image and neutral image in the input image, eliminate individual difference and background noise in expression features and improve the accuracy and generalization of the network. Finally, convolutional difference and contextual features are combined to improve the accuracy of the network further. Experiment results of 4 public facial expression datasets illustrate that compared with the existing facial expression recognition methods, this method has higher accuracy, can extract facial expression features more effectively, and has a better generalization ability. © 2023 SPIE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Improvement of the Electrical Properties of Silicone Rubber Doped with Nano-zirconia Grafted by Voltage Stabilizer 4

Improvement of the Electrical Properties of Silicone Rubber ...

引用

4th IEEE International Conference on Electrical Materials and Power Equipment, ICEMPE 2023

作者： Zhu, Xiaoqian Zhou, Yuanxiang Zhang, Yunxiao Chen, Ming Liu, Xuanhao Tsinghua University State Key Lab of Control and Simulation of Power System and Generation Equipment Department of Electrical Engineering Beijing China Fuzhou University College of Electrical Engineering and Automation Fuzhou China Xiamen Power Supply Company State Grid Fujian Electric Power Company Xiamen China Xinjiang University The Wind Solar Storage Division State Key Laboratory of Control and Simulation of Power System and Generation Equipment School of Electrical Engineering Urumqi China

ISBN: (纸本)9798350334678

Enhancing the electrical performance of silicone rubber (SiR) for cable accessories is noteworthy as they are almost the weakest parts of the cable system. Two types of voltage stabilizers were grafted onto the surface of nano-zirconia (ZrO2) particles, and the grafted nanoparticles were added to the SiR. Measurements such as breakdown strength, and conductivity were carried out to evaluate the electrical performance of SiR nanocomposites. The electrical performance measurement results indicated that the breakdown strength of the nanocomposite SiR improved while the conductance current was reduced. The trap distribution showed that the improvement of the electrical performance of the nanocomposite SiR is mainly due to the decrease of the shallow trap density or the increase of the deep trap density. © 2023 IEEE.

关键词： Nanoparticles

来源：评论

学校读者我要写书评

暂无评论

Gate-Aware Online Planning for Two-Player Autonomous Drone Racing

arXiv

引用

arXiv 2024年

作者： Zhao, Fangguo Mei, Jiahao Zhou, Jin Chen, Yuanyi Chen, Jiming Li, Shuo College of Control Science and Engineering Zhejiang University Hangzhou310027 China Department of Automation Zhejiang University of Technology Hangzhou310023 China

The flying speed of autonomous quadrotors has increased significantly over the past 5 years, particularly in the field of autonomous drone racing. However, most research primarily focuses on the aggressive flight of a single quadrotor, simplifying the racing gate traversal problem to a waypoint passing problem that neglects the orientations of the racing gates. In this paper, we propose a systematic method called Pairwise Model Predictive control (PMPC) that can guide two quadrotors online to navigate racing gates with minimal time and without collisions. The flight task is initially simplified as a point-mass model waypoint passing problem to provide analytical time optimal reference through an efficient two-step velocity search method. Subsequently, we utilize the spatial configuration of the racing track to compute the optimal heading at each gate, maximizing the visibility of subsequent gates for the quadrotors. To address varying gate orientations, we introduce a novel Magnetic Induction Line-based spatial curve to guide the quadrotors through racing gates of different orientations. Furthermore, we formulate a nonlinear optimization problem that uses the point-mass trajectory as initial values and references to enhance solving efficiency, enabling the method to run onboard at a frequency of 200 Hz. The feasibility of the proposed method is validated through both simulation and real-world experiments. In real-world tests, the two quadrotors achieved a top speed of 6.1m/s on a 7-waypoint racing track within a compact flying arena of 5m × 4m × 2m. Copyright © 2024, The Authors. All rights reserved.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Imitation Learning-Based Online Time-Optimal control with Multiple-Waypoint Constraints for Quadrotors

arXiv

引用

arXiv 2024年

作者： Zhou, Jin Mei, Jiahao Zhao, Fangguo Chen, Jiming Li, Shuo College of Control Science and Engineering Zhejiang University Hangzhou310027 China Department of Automation Zhejiang University of Technology Hangzhou310023 China

Over the past decade, there has been a remarkable surge in utilizing quadrotors for various purposes due to their simple structure and aggressive maneuverability, such as search and rescue, delivery and autonomous drone racing, etc. One of the key challenges preventing quadrotors from being widely used in these scenarios is online waypoint-constrained time-optimal trajectory generation and control technique. This letter proposes an imitation learning-based online solution to efficiently navigate the quadrotor through multiple waypoints with time-optimal performance. The neural networks (WN&CNets) are trained to learn the control law from the dataset generated by the time-consuming CPC algorithm and then deployed to generate the optimal control commands online to guide the quadrotors. To address the challenge of limited training data and the hover maneuver at the final waypoint, we propose a transition phase strategy that utilizes MINCO trajectories to help the quadrotor’jump over’ the stop-and-go maneuver when switching waypoints. Our method is demonstrated in both simulation and real-world experiments, achieving a maximum speed of 5.6m/s while navigating through 7 waypoints in a confined space of 5.5m×5.5m×2.0m [video3]. The results show that with a slight loss in optimality, the WN&CNets significantly reduce the processing time and enable online optimal control for multiple-waypoint constrained flight tasks. Copyright © 2024, The Authors. All rights reserved.

关键词： Constrained optimization

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：