检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Cui, Yunge Zhang, Yinlong Dong, Jiahua Sun, Haibo Chen, Xieyuanli Zhu, Feng The Key Laboratory of Opto-Electronic Information Processing Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China The Key Laboratory of Networked Control Systems Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China The State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Science Shenyang China The Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110016 China The University of Chinese Academy of Sciences Beijing101408 China The Shanghai Institute of Microsystem and Information Technology Chinese Academy of Sciences Shanghai China The College of Intelligence Science and Technology National University of Defense Technology Changsha China

Feature extraction and matching are the basic parts of many robotic vision tasks, such as 2D or 3D object detection, recognition, and registration. As is known, 2D feature extraction and matching have already achieved great success. Unfortunately, in the field of 3D, the current methods may fail to support the extensive application of 3D LiDAR sensors in robotic vision tasks due to their poor descriptiveness and inefficiency. To address this limitation, we propose a novel 3D feature representation method: Linear Keypoints representation for 3D LiDAR point cloud, called LinK3D. The novelty of LinK3D lies in that it fully considers the characteristics (such as the sparsity and complexity) of LiDAR point clouds and represents the keypoint with its robust neighbor keypoints, which provide strong constraints in the description of the keypoint. The proposed LinK3D has been evaluated on three public datasets, and the experimental results show that our method achieves great matching performance. More importantly, LinK3D also shows excellent real-time performance, faster than the sensor frame rate at 10 Hz of a typical rotating LiDAR sensor. LinK3D only takes an average of 30 milliseconds to extract features from the point cloud collected by a 64-beam LiDAR and takes merely about 20 milliseconds to match two LiDAR scans when executed on a computer with an Intel Core i7 processor. Moreover, our method can be extended to LiDAR odometry task, and shows good scalability. We release the implementation of our method at https://***/YungeCui/LinK3D. Copyright © 2022, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Key Parameters Prediction for intelligent control and Energy Optimization Based on MIC-BWO-XGBoost

Key Parameters Prediction for Intelligent Control and Energy...

引用

Cyber-Energy systems and intelligent Energy (ICCSIE), International Conference on

作者： Changyao Lv Yaqi Wang Yudong Chen Zhuo Yu Guoliang Hu Hongliang Wu Shuai Li Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang China Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China University of Chinese Academy of Sciences Beijing China Shanghai Aircraft Manufacturing Co. Ltd. Shanghai China College of Information Engineering Shenyang University of Chemical Technology Shenyang China

ISBN: (数字)9798350373318

ISBN: (纸本)9798350373325

In the aviation industry, anodic oxidation serves as a core process for surface modification of aluminum alloy components, albeit accompanied by high energy consumption. Accurate prediction of key parameters can offer decision support for the intelligent control and energy optimization of anodic oxidation. However, the limited sample size resulting from the high cost of data collection and the complex nonlinear patterns caused by the synergy of multiple factors pose a challenge in accurately predicting key parameters. Therefore, we propose a key parameters prediction method based on the Maximum Information Coefficient (MIC), Beluga Whale Optimization algorithm (BWO), and XGBoost algorithm. Considering the adverse impact of low correlation parameters on prediction accuracy, we first use MIC to extract features from the original data. Then, XGBoost is used to integrate multiple decision trees to ensure the strong fitting ability for nonlinear relationships. Compared to deep learning models, XGBoost performs well even in a limited sample size. In addition, considering XGBoost is prone to overfitting training data as an ensemble learning algorithm, we employ the BWO to optimize four key parameters of the model that are difficult to choose, thereby enhancing model's generalization. The model's performance is evaluated using Mean Squared Error (MSE), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE), with values of 0.04388, 0.09410, and 0.20730%, respectively. The experimental results demonstrate that the proposed method outperforms traditional approaches, enabling precise prediction of key parameters and holding significant value for the intelligent control and energy optimization of anode oxidation processes.

关键词： Microwave integrated circuits Accuracy Process control Prediction algorithms Feature extraction Data models Whale optimization algorithms Oxidation Optimization intelligent control

来源：评论

学校读者我要写书评

暂无评论

Urban Digital Twins for intelligent Road Inspection

Urban Digital Twins for Intelligent Road Inspection

引用

IEEE International Conference on Big Data

作者： Rui Fan Yikang Zhang Sicen Guo Jiahang Li Yi Feng Shuai Su Yanting Zhang Wenshuo Wang Yu Jiang Mohammud Junaid Bocus Xingyi Zhu Qijun Chen the Department of Control Science & Engineering Frontiers Science Center for Intelligent Autonomous Systems and State Key Laboratory of Intelligent Autonomous Systems Robotics & Artificial Intelligence Laboratory (RAIL) Tongji University Shanghai P. R. China Department of Computer Science & Technology Donghua University Shanghai P. R. China Department of Civil Engineering McGill University Montreal Canada CTO office at ClearMotion Billerica MA USA Department of Electrical & Electronic Engineering the University of Bristol BS8 1UB U.K Key Laboratory of Road and Traffic Engineering of Ministry of Education Tongji University Shanghai P. R. China

ISBN: (纸本)9781665480468

Urban digital twin (UDT) technologies offer new opportunities for intelligent road inspection (IRI). This paper first reviews the state-of-the-art algorithms used in the two key components of UDT-based IRI systems: (1) multi-temporal, multi-dimension, multi-score, and heterogeneous road data acquisition, and (2) road distress detection. This paper then summarizes the UDTIRI competition, organized in conjunction with IEEE Bigdata 2022. More details on our competition are available at ***/view/udtiri-workshop/bigdata-2022.

关键词： Roads Data acquisition Inspection Big Data Rough surfaces Digital twins

来源：评论

学校读者我要写书评

暂无评论

Position Sensorless control of Permanent Magnet Synchronous Motor Based on Adaptive Sliding Mode Observer

Position Sensorless Control of Permanent Magnet Synchronous ...

引用

Chinese Automation Congress (CAC)

作者： Tao Zhang Yingjie Xiong Bolun Wang Hongyu Yan Xiyou Chen School of Electrical Engineering Dalian University of Technology Dalian China Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang China College Of Information Science and Engineering Northeastern University Shenyang China School of Artificial Intelligence Shenyang University of Technology Shenyang China

ISBN: (纸本)9781665426480

Permanent magnet synchronous motors(PMSM) are popular in AC motor applications due to their small size, high efficiency. They have appeared widely in various areas of life. Due to the high-frequency chattering problem caused by sliding mode observer sensorless control of PMSM, an SMO with piecewise control function is designed in this paper. At the same time, based on the back EMF output of the SMO, the gain of the SMO is adapted to reduce the system bucket vibration problem caused by the conventional SMO. Finally, a simulation experiment was carried out in MATLAB/SIMULINK and compared with the conventional SMO. The results show that the improved SMO has achieved a better control effect.

关键词： Vibrations Adaptation models AC motors Force Sensorless control Observers Permanent magnet motors

来源：评论

学校读者我要写书评

暂无评论

Long and Short-Term Constraints Driven Safe Reinforcement Learning for Autonomous Driving

arXiv

引用

arXiv 2024年

作者： Hu, Xuemin Chen, Pan Wen, Yijun Tang, Bo Chen, Long School of Artificial Intelligence Hubei University Wuhan430062 China Key Laboratory of Intelligent Sensing System and Security Hubei University Ministry of Education Hubei Wuhan430062 China Department of Electrical and Computer Engineering Worcester Polytechnic Institute WorcesterMA01609 United States State Key Laboratory of Multimodal Artificial Intelligence Systems State Key Laboratory of Management and Control for Complex Systems Chinese Academy of Sciences Beijing100190 China WAYTOUS Inc. Beijing100083 China Shenzhen518107 China Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Xi’an710049 China

Reinforcement learning (RL) has been widely used in decision-making and control tasks, but the risk is very high for the agent in the training process due to the requirements of interaction with the environment, which seriously limits its industrial applications such as autonomous driving systems. Safe RL methods are developed to handle this issue by constraining the expected safety violation costs as a training objective, but the occurring probability of an unsafe state is still high, which is unacceptable in autonomous driving tasks. Moreover, these methods are difficult to achieve a balance between the cost and return expectations, which leads to learning performance degradation for the algorithms. In this paper, we propose a novel algorithm based on the long and short-term constraints (LSTC) for safe RL. The short-term constraint aims to enhance the shortterm state safety that the vehicle explores, while the long-term constraint enhances the overall safety of the vehicle throughout the decision-making process, both of which are jointly used to enhance the vehicle safety in the training process. In addition, we develop a safe RL method with dual-constraint optimization based on the Lagrange multiplier to optimize the training process for end-to-end autonomous driving. Comprehensive experiments were conducted on the MetaDrive simulator. Experimental results demonstrate that the proposed method achieves higher safety in continuous state and action tasks, and exhibits higher exploration performance in long-distance decision-making tasks compared with state-of-the-art methods. Copyright © 2024, The Authors. All rights reserved.

关键词： Lagrange multipliers

来源：评论

学校读者我要写书评

暂无评论

Simultaneous state and parameter estimation: The role of sensitivity analysis

arXiv

引用

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

来源：评论

学校读者我要写书评

暂无评论

PrePARE: Predictive Proprioception for Agile Failure Event Detection in Robotic Exploration of Extreme Terrains

arXiv

引用

arXiv 2022年

作者： Dey, Sharmita Fan, David Schmid, Robin Dixit, Anushri Otsu, Kyohei Touma, Thomas Schilling, Arndt F. Agha-Mohammadi, Ali-Akbar NASA Jet Propulsion Laboratory California Institute of Technology PasadenaCA United States The University of Goettingen University Medical Center Goettingen Germany The Institute for Robotics and Intelligent Machines Georgia Institute of Technology AtlantaGA United States Zurich8092 Switzerland Control and Dynamical Systems California Institute of Technology PasadenaCA United States Mechanical and Civil Engineering California Institute of Technology PasadenaCA United States

Legged robots can traverse a wide variety of terrains, some of which may be challenging for wheeled robots, such as stairs or highly uneven surfaces. However, quadruped robots face stability challenges on slippery surfaces. This can be resolved by adjusting the robot's locomotion by switching to more conservative and stable locomotion modes, such as crawl mode (where three feet are in contact with the ground always) or amble mode (where one foot touches down at a time) to prevent potential falls. To tackle these challenges, we propose an approach to learn a model from past robot experience for predictive detection of potential failures. Accordingly, we trigger gait switching merely based on proprioceptive sensory information. To learn this predictive model, we propose a semi-supervised process for detecting and annotating ground truth slip events in two stages: We first detect abnormal occurrences in the time series sequences of the gait data using an unsupervised anomaly detector, and then, the anomalies are verified with expert human knowledge in a replay simulation to assert the event of a slip. These annotated slip events are then used as ground truth examples to train an ensemble decision learner for predicting slip probabilities across terrains for traversability. We analyze our model on data recorded by a legged robot on multiple sites with slippery terrain. We demonstrate that a potential slip event can be predicted up to 720 ms ahead of a potential fall with an average precision greater than 0.95 and an average F-score of 0.82. Finally, we validate our approach in real-time by deploying it on a legged robot and switching its gait mode based on slip event detection. © 2022, CC BY-NC-SA.

关键词： Robots

来源：评论

学校读者我要写书评

暂无评论

Research on Collaboration Method of Edge IoT Agent Based on Actor Model

Research on Collaboration Method of Edge IoT Agent Based on ...

引用

Power and Energy Engineering (ICPEE), International Conference on

作者： Bowen Zhang Weiwei Miao Lei Wei Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang China Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China Information & Telecommunication Branch State Grid Jiangsu Electric Power Co. Ltd. Nanjing China State Grid Jiangsu Electric Power Co. Ltd. Nanjing China

ISBN: (纸本)9781665420471

Focusing on the resource constrained IoT agent collaboration requirements at the edge of the power Internet of things, this paper proposes an edge agent collaborative computation method based on Actor model to satisfy the rapid processing and response requirements of large-scale data in the perception layer of the power Internet of things. Through a unified programming model, this paper can divide the collection and analysis of sensing data in the sensing layer of the power Internet of things into functional components, which can be deployed in different edge IoT agents, to improve the rapid processing ability of edge-side data. At the same time, the components achieve the function cooperation through the message passing mechanism. Finally, this paper implements the proposed scheme based on Akka framework, and designs the edge IoT agent collaborative computing prototype. The prototype system experiments show that the proposed scheme can split the complex services with high resource requirements into different components and deploy them in different edge IoT agents. The proposed method can improve the resource utilization and data processing capacity of the edge IoT agent of the power Internet of things, while ensuring the real-time requirements of edge service analysis.

关键词： Computational modeling Message passing Collaboration Prototypes Programming Data models Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Artificial Neural Network-Based Direct Power control to Enhance the Performance of a Pmsg-Wind Energy Conversion System Under Real Wind Speed and Parameter Uncertainties: An Experimental Validation

SSRN

引用

SSRN 2023年

作者： Majout, Btissam Bossoufi, Badre Karim, Mohammed Skruch, Pawel Mobayen, Saleh El Mourabit, Youness El Zair Laggoun, Zakaria Laboratory of Engineering Modelling and Systems Analysis SMBA University Fez Morocco Department of Automatic Control and Robotics AGH University of Science and Technology Kraków30-059 Poland Graduate School of Intelligent Data Science National Yunlin University of Science and Technology 123 University Road Section 3 Yunlin Douliou640301 Taiwan National School of Applied Sciences Abdelmalek Essaadi University Tetouan Morocco Laboratory of Electrotechnique Constantine Mentouri Brothers Constantine 1 University Constantine Algeria

With the increasing emphasis on embedding advanced technology into system controls, the Direct Power control (DPC) approach has garnered significant attention, owing to its straightforward and highly adaptable algorithm. It has been adopted in many applications. However, the variable frequency, harmonic distortion of the currents, and power ripples caused by Hysteresis controllers and switching tables decrease its effectiveness and robustness, affecting the system’s performance. For this reason, this paper proposed a new DPC based on Artificial Neural Network (ANN) approaches. In this approach, the hysteresis comparator and the switching table are substituted with ANN controllers and then applied on both sides: machine-side converter (MSC) and grid-side converter (GSC) of a Permanent Magnet Synchronous Generator based Wind Energy Conversion System (PMSG-WECS). Moreover, to make the system more efficient in varying wind conditions, this study expands the utilization of the artificial neural networks (ANN) to encompass the maximum power point tracking (MPPT) control strategy. To demonstrate the effectiveness of the proposed approach on the system behaviors, a simulation test was carried out in the Matlab/Simulink environment, using a real wind profile of a Moroccan city (Essaouira). In comparison to the classical DPC control, the simulation results showed the superior performance of the proposed ANN-DPC control in terms of reference tracking, response time, overshoot, precision, and its capacity to reduce the rate of power ripples and total harmonic distortion (THD) in the injected currents. Furthermore, a robustness test was also included in this work to check the robustness of the proposed control against parameters variation. In conclusion, the feasibility and effectiveness of the ANN-DPC control approach were confirmed through experimental validation using the dSPACE DS1104 board. © 2023, The Authors. All rights reserved.

关键词： MATLAB

来源：评论

学校读者我要写书评

暂无评论

Position control of X-Y Precision Motion Stage Based on Iterative Learning and Model Prediction

Position Control of X-Y Precision Motion Stage Based on Iter...

引用

Chinese control and Decision Conference, CCDC

作者： Guopeng Zhang Tao Zhang Qingxin Li Li Chen Hualiang Zhang Jingzhe Fang Yiqiang Zhang School of Artificial Intelligence Shenyang University of Technology Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang Institute of Automation Chinese Academy of Sciences Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China School of Artificial Intelligence Shenyang University of Technology Shenyang China School of Electrical Engineering Shenyang University of Technology Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China

ISBN: (数字)9798350387780

ISBN: (纸本)9798350387797

The X-Y precision planar motion stage is a highly advanced motion control device that has been widely utilized in various precision motion control fields. This platform achieves precise positioning and control of objects through precise motion along the X and Y axes, providing an outstanding solution for scientific research, industrial production, and other applications. The X-Y platform consists of two permanent magnet synchronous linear motors. In the three-loop control of the motor, when the current loop uses a PID controller, there is a problem in tuning the parameters. This paper replaces the original PID controller in the current loop with a model predictive controller. Simultaneously, addressing the issue of improving the tracking accuracy of the X-Y precision planar motion stage, a forgetting high-order variable gain PD-type iterative learning control is proposed. Subsequently, both of these control methods are applied to the Simulink model of the X-Y precision motion stage motor. This not only solves the complex problem of tuning the motor current loop parameters but also improves the tracking accuracy of the X-Y precision motion stage. The results indicate that when using both model predictive controllers and forgetting high-order variable gain PD-type iterative learning controllers for motor control, not only can the tuning of current loop parameters be omitted, but also tracking errors can be effectively reduced, and the system convergence speed can be accelerated.

关键词： Tracking loops Trajectory tracking Predictive models Motors Mathematical models Motion control Tuning

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：