检索结果-内蒙古大学图书馆

2018 IEEE Intelligent Vehicles Symposium, IV 2018

作者： Qiu, Kai Ai, Yunfeng Tian, Bin Wang, Bin Cao, Dongpu School of Aritificial Intelligence University of Chinese Academy of Sciences Beijing100049 China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China Cloud Computing Center Chinese Academy of Sciences Dongguan523808 China School of Software Engineering University of Science and Technology of China HeFei230026 China Department of Mechanical and Mechatronics Engineering University of Waterloo WaterlooONN2L 3G1 Canada

ISBN: (纸本)9781538644522

Deep learning has made significant breakthroughs in the tasks of image classification, detection, segmentation, etc. However, the application of deep learning in robotics is still scarce. SLAM is a fundamental problem in robotics and loop closure detection is an important part of SLAM. This paper attempts to use supervised learning methods to solve the loop closure detection problem in vision SLAM. We proposed Siamese-ResNet network, which combines Siamese network with ResNet to detect loop closure. To show the effectiveness of Siamese-ResNet, we evaluate Siamese-ResNet and FabMap2.0 on several open published datasets, like TUM SLAM dataset and FabMap SLAM dataset. Compared with FabMap2.0, Siamese-ResNet shows higher accuracy, better robustness and shorter time-consuming. © 2018 IEEE.

关键词： Robotics

来源：评论

学校读者我要写书评

暂无评论

Neural-Network-Based Filtering with Encoding Mechanisms: Applications to Multiple Unmanned Aerial Vehicles

Neural-Network-Based Filtering with Encoding Mechanisms: App...

引用

Chinese automation Congress (CAC)

作者： Kaiqun Zhu Xinpeng Xu Zhiru Cao Ran Sun Ya Yang State Key Laboratory of Internet of Things for Smart City University of Macau Macau China Shanghai Electro-Mechanical Engineering Institute Shanghai China School of Mechatronic Engineering and Automation Shanghai University Shanghai China Department of Control Science and Engineering University of Shanghai for Science and Technology Shanghai China

In this paper, the neural-network-based filtering problem is investigated for multi-sensor systems with dynamic encoding mechanisms. The sensor nodes and the remote filter are connected through bandwidth-constrained communication networks. To alleviate the communication burden, a novel dynamic encoding-based data compression-decompression mechanism is proposed so as to encode the data into a limited number of bits. Then, with the aid of the neural network learning method, a neural-network-based set-membership filter is developed for estimating the system states. Sufficient conditions are obtained to ensure that the filtering error remains within the bounded ellipsoidal set. In addition, the neural network tuning parameters and the filter gains are calculated by solving constrained optimization problems. Finally, the effectiveness of the proposed filtering algorithm is verified through a scenario of maneuvering target tracking using multiple unmanned aerial vehicles.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Landslide Sensitivity Mapping Based on One-Dimensional Residual Convolutional Neural Networks

Landslide Sensitivity Mapping Based on One-Dimensional Resid...

引用

Chinese automation Congress (CAC)

作者： Yougang Ke Chengda Lu Min Wu Wanke Yu Ruiqing Niu School of Automation China University of Geosciences Wuhan China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China Ministry of Education Engineering Research Center of Intelligent Technology for Geo-Exploration Wuhan China Institute of Geophysics and Geomatics China University of Geosciences Wuhan China

Landslide is a common geological disaster. Landslide sensitivity mapping (LSM) is the key technology for landslide monitoring, early warning and risk assessment. Deep learning shows good performance in feature extraction. This paper proposes a one-dimensional residual convolution neural network (1DRCNN), which takes Yunyang County, Chongqing City, China, located in the Three Gorges Reservoir area as the research area. Extracting 12 evaluation factors from multi-source remote sensing data and building a training set. The spatial probability of landslide occurrence is quantitatively predicted by the proposed model, and finally, the landslide sensitivity mapping is generated. Compared with the common machine learning models SVM and logistic regression, the results show that the AUC (area under curve) and accuracy of 1D-RCNN are 0.9860 and 93.38%, respectively, which proving that this method is effective and can provide a reference for disaster prevention and reduction.

关键词： Support vector machines Training Sensitivity Urban areas Feature extraction Reservoirs Terrain factors

来源：评论

学校读者我要写书评

暂无评论

A NOVEL CPG WITH PROPRIOCEPTION AND ITS APPLICATION ON THE LOCOMOTION control OF QUADRUPED ROBOT

引用

International Journal of Information Acquisition 2009年第1期6卷 33-46页

作者： LEI SUN MAX Q.-H. MENG SHUAI LI HUAWEI LIANG TAO MEI Center for Biomimetic Sensing and Control Research Institute of Intelligent Machines Chinese Academy of Sciences Hefei Anhui Province China Department of Automation University of Science and Technology of China Hefei Anhui Province China Department of Electronic Engineering The Chinese University of Hong Kong Hong Kong China

This paper proposes a novel central pattern generator (CPG) model with proprioceptive mechanism and the dynamic connectivity mechanism. It not only contains the sensory information of the environment but also contains the information of the actuators and automatically tunes the parameters of CPG corresponding to the actuators information and inner sensory information. The position of the joints linked directly with the output of CPG is introduced to the CPG to find its proprioceptive system, spontaneously making the robot realize the actuator working status, further changing the CPG output to fit the change and decrease the influence of the problematic joints or actuators on the robot being controlled. So the damage would be avoided and self-protection is implemented. Its application on the locomotion control of a quadruped robot demonstrates the effectiveness of the proposed approach.

关键词： CPG proprioception dynamic connectivity mechanism locomotion quadruped robot

来源：评论

学校读者我要写书评

暂无评论

Multi-objective Group Decision and Cooperative Planning Based on Preference and Fuzzy Measure 1

引用

7th Chinese Conference on Swarm Intelligence and Cooperative control, CCSICC 2023

作者： Ma, Xiwen Xie, Wei Yang, Jingsong Zhang, Weidong Lu, Jinhui School of Oceanography Shanghai Jiao Tong University Shanghai China State Key Laboratory of Satellite Ocean Environment Dynamics Second Institute of Oceanography Ministry of Natural Resources Hangzhou China Department of Automation Shanghai Jiao Tong University Shanghai China Zhuhai China School of Information and Communication Engineering Hainan University Hainan Haikou China National Engineering Research Center of Ship and Shipping Control System Shanghai China Crossocean of Suzhou technology No. 218 East Oingdao Road Suzhou China

ISBN: (数字)9789819733323

ISBN: (纸本)9789819733316

To pursue interest balance and improve collaboration efficiency, this paper proposes a multi-agent cooperation method integrating decision-making and planning. Based on preference and fuzzy measures, this method can balance individual and group benefits under fuzzy uncertain environment. The equilibrium solution of a multi-agent multi-objective game, namely group decision-making (GDM) solution, can be obtained by the Gaussian oscillation particle swarm optimization (GOPSO) algorithm, which overcomes the dilemma of a multi-objective group game and improves the computational efficiency. Considering the smoothness and continuity of the trajectory, a heuristic motion planning (MP) generation model that satisfies the kinematic constraints and minimizes differential thrust is proposed, which improves the cooperation efficiency. To verify the performance of this proposed method, simulation results are presented and some comparative statements are given. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Robust H∞ controller Design With Regional Pole-Placement for Quarter Car Active Suspension System

Robust H∞ Controller Design With Regional Pole-Placement fo...

引用

control Conference (ANZCC), Australian and New Zealand

作者： Sonali Singh Ganta Jane Gladys P P Gouri Jitendra Kumar Goyal Ankit Sachan Surender Hans Shubhi Purwar Neeraj Gupta Department of Electical Engineering M.N. National Institute of Technology Allahabad Prayagraj India Department of Control and Automation School of Electrical Engineering Vellore Institute of Technology Vellore Tamil Nadu India Department of Electronics and Communication Engineering Poornima College of Engineering Jaipur India Graduate School of Advanced Science & Engineering Hiroshima University Japan Department of Electical Engineering Ajay Kumar Garg Engineering College Ghaziabad India

In the modern world, automobile suspension holds crucial importance in uplifting a cars ride comfort and handling ability. Active suspension can doubtless enhance the driving quality and traveler comfort at the same time. Its a fourth-order advanced system that requires a highly accurate and precise robust control technique. This work presents a highly robust $H_{\infty}$ controller proposed for a quarter car active suspension system and a comparison of it with the prevailing LQR controller design. Also, the design criteria to enhance the transient performance of the system consist of the concept of regional pole placement. controller behavior is examined through simulation setup using MATLAB/Simulink. Simulation results are shown to explain the efficacy of the developed design.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Two Intersections Traffic Signal control Method Based on ADHDP

Two Intersections Traffic Signal Control Method Based on ADH...

引用

2016年IEEE汽车电子与安全国际会议

作者： Lin Cao Bin Hu Xisong Dong Gang Xiong Fenghua Zhu Zhen Shen Dong Shen Yuliang Liu The State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of Sciences College of Information Science and Technology Beijing University of Chemical Technology Institute of Smart Education Systems Qingdao Academy of Intelligent Industries Dongguan Research Institute of CASIA Cloud Computing CenterChinese Academy of Sciences Beijing Engineering Research Center of Intelligent Systems and Technology Institute of AutomationChinese Academy of Sciences

With the rapid development of Chinese economy and automotive industry,urban traffic congestion has become increasingly ***,how to effectively alleviate the traffic congestion and improve the efficiency of vehicles has become the main *** signal control is one of the effective ways to solve urban traffic *** this paper,a traffic signal control method based on Action-Dependent Heuristic Dynamic Programming(ADHDP) is *** control algorithm is simulated on two intersections,both of which have two phases with four entrance *** computer simulation results show that the control method has the better ability of on-line learning compared with traditional Fix-Time control,and can effectively improve the average speed of vehicles,and reduce travel time and alleviate the traffic pressure.

关键词： ADHDP Traffic Signal control Adaptive control Intelligent Transportation Systems

来源：评论

学校读者我要写书评

暂无评论

Design and Stability Analysis of Non-smooth Integral Sliding Surface for Coupled-Tank System with Matching/Non-matching Disturbance

Design and Stability Analysis of Non-smooth Integral Sliding...

引用

control Conference (ANZCC), Australian and New Zealand

作者： Sonali Singh Ankit Sachan Jitendra Kumar Goyal Shubhi Purwar Neeraj Gupta Ganta Jane Gladys P P Gouri Surender Hans Department of Electical Engineering M.N. National Institute of Technology Allahabad Prayagraj India Graduate School of Advanced Science & Engineering Hiroshima University Japan Department of Control and Automation School of Electrical Engineering Vellore Institute of Technology Vellore Tamil Nadu India Department of Electical Engineering Ajay Kumar Garg Engineering College Ghaziabad India Department of Electronics and Communication Engineering Poornima College of Engineering Jaipur India

This paper examine the challenges posed by conventional sliding mode design in the presence of matching/nonmatching disturbances. Previously designed approaches have proven inadequate in offering an efficient and straightforward solution to non-matching disturbances. To overcome this, a novel sliding mode control strategy centered on a non-smooth integral sliding manifold is introduced. The newly proposed sliding manifold possesses two crucial characteristics. Firstly, it functions transform to a reduced-order disturbance observer by autonomously estimating the mismatched disturbances, eliminating the need for an additional observer design. Secondly, the system consistently initiates its operation from the sliding surface, eliminating any reaching phase dynamics. As a result, the system trajectory remains resilient to disturbances right from the outset. To validate the effectiveness of the proposed method, it is simulated for a coupled tank system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Solar Radiation Forecasting Based on Random Forest and XGBoost 7

Solar Radiation Forecasting Based on Random Forest and XGBoo...

引用

7th International Conference on Green Technology and Sustainable Development, GTSD 2024

作者： Nguyen, Nhat-Truong Tuong Dao, Thai Cat Tuyen Nguyen, Le Nhut Nguyen, Thanh-Dat Le, Minh-Vuong French, Isobel Timothea Doan, Van-Tuong Kim Vo, Van Hoang Tran, Nghi C. Pham, Duc-Hung Nguyen, Van-Trung Ho Chi Minh City University of Technology and Education Department of Renewable Energy Viet Nam Ho Chi Minh City Industry and Trade College Department of Control Engineering and Automation Viet Nam LILAMA2 International Technology College Dongnai Viet Nam Institute of Cognitive Neuroscience National Central University Taiwan College of Information and Communication Technology Can Tho University Viet Nam Hung Yen University of Technology and Education Faculty Electrical and Electronic Engineering Viet Nam

ISBN: (纸本)9798350386073

Renewable energy offers a viable alternative to depleting fossil fuels, contributing to global warming and greenhouse gas emissions. Thus, solar energy is widely favored as a renewable energy source. However, the output power of solar systems is unstable and is highly dependent on environmental circumstances such as radiation, humidity, temperature, and wind. Therefore, accurately estimating solar radiation is crucial for successful integration of the solar system into existing electrical grid systems. In this study, two different machine learning models, XGBoost and Random Forest, were used to predict solar radiation data in Ho Chi Minh City, Vietnam. The results show that RMSE and MAE of the Random Forest model (61.09 and 24.37) is smaller compared to XGBoost (61.31 and 25.08). Regression value of the two models is close to 0.955. In summary, this paper demonstrates that these two machine learning algorithms effectively forecast solar radiation, with the Random Forest model showing better performance. © 2024 IEEE.

关键词： Solar irradiance

来源：评论

学校读者我要写书评

暂无评论

Reliability Models for a Safe Train Traffic control Systems Accounting the Railway Infrastructure States

Reliability Models for a Safe Train Traffic Control Systems ...

引用

International Russian automation Conference (RusAutoCon)

作者： Dmitrii V. Efanov Evgenii M. Mikhailiuta Valerii V. Khóroshev Higher School of Transport Mechanical Engineering Material and Transport Institute Peter the Great St. Petersburg Polytechnic University St. Petersburg Russia "Automation and Remote Control" Department Tashkent State Transport University Tashkent Uzbekistan "Automation Remote Control and Communication on Railway Transport" Department Russian University of Transport Moscow Russia Higher School of Mechanical Engineering Material and Transport Institute in St. Petersburg Peter the Great St. Petersburg Polytechnic University St. Petersburg Russia

The authors developed the advanced train traffic control system architecture. This architecture is based on the railway infrastructure facilities monitoring techniques integrated into the railway automation and remote-control equipment. Such system has a higher level of safety due to the transferring data about the infrastructure facilities state into control complexes directly without the "human – operator" link of the monitoring system. Data from infrastructure facilities that do not directly interact with railway automation equipment’s make it possible to quickly develop control actions for the timely developing defects counteract. The authors developed reliability models for the train traffic control systems, in which the railway infrastructure facilities states are considered. Authors presents the accounting the infrastructure complex safe state relevance in train traffic control systems. The developed reliability models using are advisable in the safe train traffic control systems development, as well as in railway infrastructure facilities digital twins developing include real-time modeling of processes.

关键词：

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：