检索结果-内蒙古大学图书馆

International Conference on Intelligent Transportation

作者： Teng Liu Bin Tian Yunfeng Ai Long Chen Fei Liu Dongpu Cao Ning Bian Fei-Yue Wang Mechanical and Mechatronics Engineering Department University of Waterloo Canada Vehicle Intelligence Pioneers Inc. Qingdao China Xilinx Technology Beijing Limited Beijing China Department of Mechanical and Mechatronics Engineering University of Waterloo Ontario Canada dongfeng motor corporation Wuhan China State Key Lab. of Manage. and Control for Complex Syst. Inst. of Autom. Beijing China

ISBN: (纸本)9781538670255

As a combination of various kinds of technologies, autonomous vehicles could complete a series of driving tasks by itself, such as perception, decision-making, planning and control. Since there is no human driver to handle the emergency situation, future transportation information is significant for automated vehicles. This paper proposes different methods to forecast the time series for autonomous vehicles, which are the nearest neighborhood (NN), fuzzy coding (FC) and long short term memory (LSTM). First, the formulation and operational process for these three approaches are introduced. Then, the vehicle velocity is regarded as a case study and the real-world dataset is utilized to predict future information via these techniques. Finally, the performance, merits and drawbacks of the presented methods are analyzed and discussed.

关键词： Artificial neural networks Autonomous vehicles Time series analysis Predictive models Trajectory Recurrent neural networks Neurons

来源：评论

学校读者我要写书评

暂无评论

Siamese-ResNet: Implementing Loop Closure Detection based on Siamese Network

Siamese-ResNet: Implementing Loop Closure Detection based on...

引用

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

A Multi-Player Potential Game Approach for Sensor Network Localization with Noisy Measurements 63

A Multi-Player Potential Game Approach for Sensor Network Lo...

引用

63rd IEEE Conference on Decision and control, CDC 2024

作者： Xu, Gehui Chen, Guanpu Fidan, Baris Hong, Yiguang Qi, Hongsheng Parisini, Thomas Johansson, Karl H. Kth Royal Institute of Technology Division of Decision and Control Systems School of Electrical Engineering and Computer Science Stockholm100 44 Sweden University of Waterloo Department of Mechanical and Mechatronics Engineering WaterlooONN2L 3G1 Canada Tongji University Department of Control Science and Engineering shanghai201804 China Shanghai Research Institute for Intelligent Autonomous Systems Shanghai201210 China Key Laboratory of Systems and Control Academy of Mathematics and Systems Science Beijing China University of Chinese Academy of Sciences School of Mathematical Sciences Beijing China Aalborg University Department of Electronic Systems Denmark Imperial College London Department of Electrical and Electronic Engineering LondonSW7 2AZ United Kingdom University of Trieste Department of Engineering and Architecture Italy

ISBN: (纸本)9798350316339

Sensor network localization (SNL) is a challenging problem due to its inherent non-convexity and the effects of noise in inter-node ranging measurements and anchor node position. We formulate a non-convex SNL problem as a multiplayer non-convex potential game and investigate the existence and uniqueness of a Nash equilibrium (NE) in both the ideal setting without measurement noise and the practical setting with measurement noise. We first show that the NE exists and is unique in the noiseless case, and corresponds to the precise network localization. Then, we study the SNL for the case with errors affecting the anchor node position and the inter-node distance measurements. Specifically, we establish that in case these errors are sufficiently small, the NE exists and is unique. It is shown that the NE is an approximate solution to the SNL problem, and that the position errors can be quantified accordingly. Based on these findings, we apply the results to case studies involving only inter-node distance measurement errors and only anchor position information inaccuracies. © 2024 IEEE.

关键词： Nash equilibrium

来源：评论

学校读者我要写书评

暂无评论

Dead reckoning and Kalman filter design for trajectory tracking of a quadrotor UAV

Dead reckoning and Kalman filter design for trajectory track...

引用

2010 IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications, MESA 2010

作者： Zhou, Qing-Li Zhang, Youmin Qu, Yao-Hong Rabbath, Camille-Alain Mechanical and Industrial Engineering Department Concordia University Montreal QC H3G 2WI Canada Dept. of Mechanical and Industrial Engineering Diagnosis Flight Control and Simulation Lab Concordia University Montreal H3G 2WI Canada Dept. of Mechanical and Industrial Engineering Concordia University Montreal H3G 2Wl Canada School of Automation Northwestern Polytechnical University Xi'an 710072 China Defence Research and Development Valcartier QC G3J 1X5 Canada

ISBN: (纸本)9781424471010

The dynamic equations of a quadrotor unmanned aerial vehicle (UAV), namely Qball-X4, are analyzed and built, trajectory tracking control design based on an inner/outer loop control structure is proposed in this paper. The method of analytic geometry is used in dead-reckoning, discrete Kalman filter has been applied to trajectory tracking for improving the accuracy of estimated location. Integrated online waypoints pre-planning and trajectory tracking control have been carried out. Simulation results demonstrate the effectiveness of the proposed approach. © 2010 IEEE.

关键词： Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning-Based Predictive control for Autonomous Electrified Vehicles

Reinforcement Learning-Based Predictive Control for Autonomo...

引用

2018 IEEE Intelligent Vehicles Symposium, IV 2018

作者： Liu, Teng Yang, Chao Hu, Chuanzheng Wang, Hong Li, Li Cao, Dongpu Wang, Fei-Yue State Key Laboratory of Automotive Simulation and Control Jilin University China Vehicle Intelligence Pioneers Inc. Qingdao Shandong266109 China Jiangsu XCMG Construction Machinery Research Institute Ltd. Xuzhou Jiangsu221004 China Mechanical and Mechatronics Engineering Department Waterloo University N2L 3G1 Canada Faculty of Department of Automation Tsinghua University China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China

ISBN: (纸本)9781538644522

This paper proposes a learning-based predictive control technique for self-driving hybrid electric vehicle (HEV). This approach is a hierarchical framework. The higher-level is a human-like driver model, which is applied to predict accelerations in the car following situation to replicate a human driver's demonstrations. The lower-level is a reinforcement learning (RL)-based controller, which enforces the battery and fuel consumption constraints to improve energy efficiency of HEV. In addition, we present induced matrix norm (IMN) to handle cases that the training data cannot provide sufficient information on how to operate in current driving situation. Simulation results illustrate that the proposed method can reproduce human driver's driving style and promote fuel economy. © 2018 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Detection probability improvement for nondestructive evaluation using a magnetic camera

Detection probability improvement for nondestructive evaluat...

引用

作者： Lee, Jinyi Hwang, Jiseoung Choi, Seho Lim, Jaekyu Department of Information Control and Instrument Engineering College of Electronics and Information Engineering Chosun University 375 Susuk-dong Dong-gu Gwangju 501-759 Korea Republic of Graduate School of Electronics and Information Engineering Chosun University 375 Susuk-dong Dong-gu Gwangju 501-759 Korea Republic of Technical Research Lab. Instrumentation and Control Research Group POSCO 1 Goedong-dong Nam-gu Pohang Gyeongbuk 790-785 Korea Republic of Faculty of Mechanical Engineering Chonbuk University Duckjin Chonju 561-756 Korea Republic of

It is important to estimate the intensity distribution of a magnetic field as a possible magnetic method in an industrial nondestructive evaluation application. A magnetic camera provides the distribution of a quantitative magnetic field with homogeneous lift-off and same spatial resolution. Magnetic flux leakage near a crack on the specimen can be amplified by using a 3-dimensional magnetic fluid, that is to say a magnetic lens. This study introduces the experimental consideration of the effects of magnetic lenses for concentrating of magnetic flux. The experimental results showed that the magnetic fluid has a sufficient lens effect for magnetic camera and effect of improvement in probability of detection.

关键词： Magnetic devices

来源：评论

学校读者我要写书评

暂无评论

Design and control of dual servo actuator for near field optical recording system

Design and control of dual servo actuator for near field opt...

引用

Optomechatronic Actuators and Manipulation

作者： Jeong, Jaehwa Choi, Young-Man Lee, Jun-Hee Yoon, Hyoung-Kil Gweon, Dae-Gab Nano Opto-Mechatronics Lab. Dept. of Mechanical Engineering KAIST 373-1 Gusong-Dong Yuseong-Gu Daejon 305-701 Korea Republic of Dept. of Advanced Industrial Technology Korea Institute of Machinery and Material 171 Jang-dong Yuseong-Gu Daejon 305-343 Korea Republic of Devices and Materials Lab. LG Electronics Institute of Technology 16 Woomyeon-Dong Seocho-Gu Seoul 137-724 Korea Republic of

ISBN: (纸本)0819460842

Near field recording (NFR) has been introduced as a new optical data storage method to realize higher data density beyond the diffraction limit. As the data density increases, the track pitch is remarkably reduced to about 400nm. Thus, more precise actuator is required and we propose a dual servo actuator to improve the accuracy of actuator. The proposed dual servo actuator consists of a coarse actuator and a fine actuator, multisegmented magnet array (MSMA) voice coil motor (VCM) and PMN-PT actuator. In design of VCM actuator, a novel magnetic circuit of VCM with MSMA is proposed. It can generate higher air gap flux density than the magnetic circuit of VCM with the conventional magnet array. In design of fine actuator, the fine actuator including PMN-PT single crystal instead of the conventional PZT is proposed. The displacement gain of PMN-PT fine actuator is 26 nm/V and that of PZT fine actuator is 17 nm/V. The displacement gain is increased by 53%. To evaluate tracking performance of the manufactured dual servo actuator and to assign the proper role to each actuator, the PQ method is selected. From experiment results, the total bandwidth of the dual servo actuator is increased to 2.5kHz and the resolution is 25 nm. Comparing with the resolution of one servo actuator, 70 nm, we can find that the accuracy of actuator is remarkably improved. And the proposed dual servo actuator shows satisfactory performances to be applied to NFR and it can be applied to other future disk drives.

关键词： Servomechanisms

来源：评论

学校读者我要写书评

暂无评论

Thermal Management of Large-Sized Lifepo4 Pouch Cell Using Simplified Mini-Channel Cold Plates

SSRN

引用

SSRN 2023年

作者： Kausthubharam Koorata, Poornesh Kumar Panchal, Satyam Department of Mechanical Engineering Seoul National University Seoul08826 Korea Republic of Electrochemical Energy System Design Lab Department of Mechanical Engineering National Institute of Technology Karnataka Surathkal Mangalore575 025 India Mechanical and Mechatronics Engineering Department University of Waterloo 200 University Avenue West WaterlooONN2L 3G1 Canada

An efficient, simplified mini-channel cooling plate-based thermal management system is presented for LiFePO4 pouch cell. The proposed design improves the uniformity in surface temperature difference by more than 100% compared to existing literature data on similar designs. The proposed coolant design is tested for temperature distribution and cooling efficiency parameters by varying the cooling fluid volume flow rate and inlet temperatures from 15ml/min to 150ml/min and 5°C to 35°C, respectively. The proposed design maintains the maximum temperature in the cell well below 40ºC even under a 4C discharge rate and a high coolant inlet temperature of 35ºC. Increasing the coolant temperature is observed to positively impact the temperature homogeneity in the pouch cell. Further, an increase in cooling liquid flow rate is observed to have a reduced impact on the maximum temperature reduction at all discharge rates. The proposed simple design can be scaled to modular packs of pouch cells. © 2023, The Authors. All rights reserved.

关键词： Flow patterns

来源：评论

学校读者我要写书评

暂无评论

Directed energy deposition powder stream modeling using a Gaussian beam ray representation

arXiv

引用

arXiv 2022年

作者： Martinez-Marchese, Alexander Klumpp, Maximilian Toyserkani, Ehsan Lab Department of Mechanical and Mechatronics Engineering University of Waterloo WaterlooONN2L 3G1 Canada Institute of Analysis Dynamics and Modeling University of Stuttgart Pfaffenwaldring 57 Stuttgart70569 Germany

The powder stream from a side feed nozzle, or part of the powder stream in some coaxial nozzles, in a directed energy deposition via powder feeding (DED-PF) machine, can be modeled using a particle velocity field that has a constant downward component and a linearly increasing outward component, in proportion to the powder stream's center line distance [1]. However, when the powder stream is subject to a force field, it was found that the shape of the powder concentration function close to the center of the powder stream diverges considerably at high degrees of focusing. This discrepancy is reduced by modeling the powder stream based on the ray representation of a Gaussian beam [2]. Experimental results from high-speed camera particle tracking and numerically extrapolating the trajectories to the nozzle exit suggests that the statistics of the powder stream correspond to this model. A novel method to compute the particle concentration along the stream using an optical system analog, with the focusing force field modeled as the transfer matrix of a graded refractive index (GRIN) lens, is also demonstrated. This method is orders of magnitude faster than the corresponding Lagrangian simulation. Copyright © 2022, The Authors. All rights reserved.

关键词： Gaussian beams

来源：评论

学校读者我要写书评

暂无评论

A Constant Force Tracking Strategy for Complex Surface Robots Fused with NURBS Speed Planning and Teaching/Learning Mode

A Constant Force Tracking Strategy for Complex Surface Robot...

引用

WRC Symposium on Advanced Robotics and Automation (WRC SARA)

作者： Duan Jinjun Cui Kunkun Guo An Wang Lingyu BinYiming Wan Minhong Huang Qiulan School of Mechatronics Nanjing University of Aeronautics and Astronautics China School of Automation Southeast University China College of Mechanical and Electrical Engineering Nanjing University of Aeronautics and Astronautics China Chinese Academy of Sciences Shenyang Institute of Automation China Zhejiang Lab Hangzhou China Control Theory and Control Egineering Zhejiang University

Compliance control technology is particularly im-portant in contact operations such as grinding and polishing, surface tracking, and medical diagnosis. The core technology achieves contact control of a constant force for complex heterogeneous surfaces. However, due to the unknown environmental stiffness/position and dynamic changes, there are some problems, such as poor position/force tracking accuracy and a low degree of complex surface fit. To solve the above problems, a piecewise trajectory planning algorithm based on speed controllable NURBS and a teaching and learning mode constant force tracking strategy based on position/force coordination planning are proposed in this paper. First, a NURBS segmented trajectory planning algorithm with controllable speed is proposed by combining the NURBS trajectory planning algorithm with the T-type speed interpolation algorithm, and constant force tracking control based on the FCPressNURBS instruction set is realized by combining the adaptive admittance control algorithm. Second, based on the concept of teaching and learning modes, the position/force tracking parameters are obtained by the compliant control method, and the learning ideas is used to optimize the constant force tracking trajectory of the robot. Finally, the algorithm is tested on the ROKAE xMate robot, and the results show that the proposed algorithm improves the constant force tracking accuracy of the robot to the complex contact surface in the heterogeneous environment and can realize the adaptive constant force tracking effect of the robot to the unknown environment.

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：