检索结果-内蒙古大学图书馆

Domain-Invariant Similarity Activation Map Contrastive Learning for Retrieval-Based Long-Term Visual Localization

IEEE/CAA Journal of Automatica Sinica 2022年第2期9卷 313-328页

作者： Hanjiang Hu Hesheng Wang Zhe Liu Weidong Chen Department of Automation Shanghai Jiao Tong UniversityShanghai 200240China IEEE Department of Automation Institute of Medical RoboticsKey Laboratory of System Control and Information Processing of Ministry of EducationKey Laboratory of Marine Intelligent Equipment and System of Ministry of EducationShanghai Jiao Tong UniversityShanghai 200240China Department of Computer Science and Technology University of CambridgeCambridge CB30FDUnited Kingdom

Visual localization is a crucial component in the application of mobile robot and autonomous *** retrieval is an efficient and effective technique in image-based localization *** to the drastic variability of environmental conditions,e.g.,illumination changes,retrievalbased visual localization is severely affected and becomes a challenging *** this work,a general architecture is first formulated probabilistically to extract domain-invariant features through multi-domain image ***,a novel gradientweighted similarity activation mapping loss(Grad-SAM)is incorporated for finer localization with high *** also propose a new adaptive triplet loss to boost the contrastive learning of the embedding in a self-supervised *** final coarse-to-fine image retrieval pipeline is implemented as the sequential combination of models with and without Grad-SAM *** experiments have been conducted to validate the effectiveness of the proposed approach on the CMU-Seasons *** strong generalization ability of our approach is verified with the RobotCar dataset using models pre-trained on urban parts of the CMU-Seasons *** performance is on par with or even outperforms the state-of-the-art image-based localization baselines in medium or high precision,especially under challenging environments with illumination variance,vegetation,and night-time ***,real-site experiments have been conducted to validate the efficiency and effectiveness of the coarse-to-fine strategy for localization.

关键词： Deep representation learning place recognition visual localization

来源：评论

学校读者我要写书评

暂无评论

Monocular Visual-Inertial and Robotic-Arm Calibration in a Unifying Framework

引用

IEEE/CAA Journal of Automatica Sinica 2022年第1期9卷 146-159页

作者： Yinlong Zhang Wei Liang Mingze Yuan Hongsheng He Jindong Tan Zhibo Pang Key Laboratory of Networked Control Systems Shenyang Institute of AutomationChinese Academy of SciencesShenyang 110016 State Key Laboratory of Robotics Shenyang Institute of AutomationChinese Academy of SciencesShenyang 110016 Institutes for Robotics and Intelligent Manufacturing Chinese Academy of SciencesShenyang 110169China School of Computing Wichita State UniversityWichita 67260 USA Department of Mechanical Aerospace and Biomedical EngineeringUniversity of TennesseeTN 37996 USA Department of Automation Technology ABB Corporate Research SwedenVasteras 72178Sweden Department of Intelligent Systems Royal Institute of Technology(KTH)Stockholm 11428Sweden

Reliable and accurate calibration for camera,inertial measurement unit(IMU)and robot is a critical prerequisite for visual-inertial based robot pose estimation and surrounding environment ***,traditional calibrations suffer inaccuracy and *** address these problems,this paper proposes a monocular visual-inertial and robotic-arm calibration in a unifying *** our method,the spatial relationship is geometrically correlated between the sensing units and robotic *** decoupled estimations on rotation and translation could reduce the coupled errors during the ***,the robotic calibration moving trajectory has been designed in a spiral pattern that enables full excitations on 6 DOF motions repeatably and *** calibration has been evaluated on our developed *** the experiments,the calibration achieves the accuracy with rotation and translation RMSEs less than 0.7°and 0.01 m,*** comparisons with state-of-the-art results prove our calibration consistency,accuracy and effectiveness.

关键词： Calibration inertial measurement unit(IMU) monocular camera robotic arm spiral moving trajectory

来源：评论

学校读者我要写书评

暂无评论

Affine Formation Maneuver control for Multiagent Systems Based on Unknown Input Reconstruction

引用

IEEE Access 2025年 13卷 102311-102322页

作者： Liduo Hu Wei Zhang Chenhang Yan Yuhang Cai Hao Chen Zhi Hu Laboratory of Intelligent Control and Robotics Shanghai University of Engineering Science Shanghai China National Key Laboratory of Autonomous Intelligent Unmanned Systems School of Automation Beijing Institute of Technology Beijing China

Disturbances can significantly impact the dynamic performance and stability of a system, making them a key focus in stability analysis. However, direct measurement of disturbances is often challenging due to technological and cost limitations. These disturbances introduce uncertainties that complicate multi-agent coordination, particularly in formation control tasks. Consequently, designing effective control strategies for multi-agent systems becomes both challenging and crucial. This paper addresses the affine transformation formation control problem of multi-agent systems in the presence of unknown disturbances. We begin by using a state-space model to describe agent dynamics and employing an unknown input observer to estimate both the state and the unknown disturbances. Based on these estimates, we redesign the control law to ensure that tracking errors converge to an adjustable residual set. This distributed control approach allows agents to operate without global information, thereby reducing communication requirements. Finally, a simulation example demonstrates the feasibility and effectiveness of the proposed control law.

关键词： Formation control Observers Laplace equations Directed graphs Vectors Multi-agent systems Protocols Matrix decomposition Aerospace electronics Vehicle dynamics

来源：评论

学校读者我要写书评

暂无评论

Transfer Learning in Subsurface Flow Surrogate Model with Physics-Guided Neural Network

Transfer Learning in Subsurface Flow Surrogate Model with Ph...

引用

2024 SPE Annual Technical Conference and Exhibition, ATCE 2024

作者： Cheng, H.B. Qiao, J.H. Wei, Y.C. Li, S.C. Zeng, P. Yu, H.B. State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang China University of Chinese Academy of Sciences Beijing China Institute for Interdisciplinary Information Sciences Tsinghua University Beijing China

ISBN: (纸本)9781959025375

It is a great challenge for reservoir engineers to accurately and quickly model the subsurface flow surrogate for oil and gas reservoirs. The traditional numerical simulation methods are high computational complexity and time-consuming. The widely used pure data- driven flow surrogate methods require massive high-quality data due to lack of theoretical foundation. Therefore, it is necessary to develop transfer learning methods integrating prior knowledge with data-driven deep learning methods to solve complex seepage problems. To reduce data requirements and improving modeling efficiency, a theory-guided and data-driven transfer learning method is proposed to build the fast and accurate subsurface flow surrogate model. Specifically, a data-driven machine learning method is first proposed to simulate and predict the flow processes and build the primary surrogate model. In addition, physical mechanism and constraints are embedded into the data-driven model to make the prediction results satisfy the prior domain knowledge. The transfer learning method based on physics-guided neural network (TL-PG) integrates the seepage theory with sparse spatial data to improve the prediction accuracy of the surrogate model. The proposed TL-PG method is verified by a subsurface flow problem in heterogeneous reservoir models. First, we build a flow field to simulate 50 years of production history. A physics-guided neural network model is trained based on the samples from the first 30 years and tested based on the last 20 years of data. The relative L2 loss and the coefficient of determination R2 are used for comparison. Compared with the purely data-driven method, the relative L2 loss of physics-guided neural network is increased by 16%, and the mean coefficient of determination R2 is up to 0.8932, which means the embedded physical mechanism can greatly improve the performance of neural networks. Secondly, the physics-guided neural network is selected as the pretraining model. Then, th

关键词： Seepage

来源：评论

学校读者我要写书评

暂无评论

High-precision Calibration of Camera and IMU on Manipulator for Bio-inspired Robotic System

引用

Journal of Bionic Engineering 2022年第2期19卷 299-313页

作者： Yinlong Zhang Wei Liang Sichao Zhang Xudong Yuan Xiaofang Xia Jindong Tan Zhibo Pang State Key Laboratory of Robotics Shenyang Institute of AutomationChinese Academy of SciencesShenyang 110016China Key Laboratory of Networked Control Systems Chinese Academy of SciencesShenyang 110016China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of SciencesShenyang 110169China The School of Computer Science and Technology Xidian UniversityXi’an 710071China Department of Mechanical Aerospace and Biomedical EngineeringUniversity of TennesseeKonxville 37996USA Department of Automation Technology ABB Corporate Research Sweden72178 VästerasSweden

Inspired by box jellyfish that has distributed and complementary perceptive system,we seek to equip manipulator with a camera and an Inertial Measurement Unit(IMU)to perceive ego motion and surrounding unstructured *** robot perception,a reliable and high-precision calibration between camera,IMU and manipulator is a critical *** paper introduces a novel calibration ***,we seek to correlate the spatial relationship between the sensing units and manipulator in a joint ***,the manipulator moving trajectory is elaborately designed in a spiral pattern that enables full excitations on yaw-pitch-roll rotations and x-y-z translations in a repeatable and consistent *** calibration has been evaluated on our collected visual inertial-manipulator *** systematic comparisons and analysis indicate the consistency,precision and effectiveness of our proposed calibration method.

关键词： Bio-inspired robotic system Monocular camera IMU Manipulator Calibration

来源：评论

学校读者我要写书评

暂无评论

Smart Plant Application of Autonomous Decentralized Systems with the Introduction of Edge Nodes 15

Smart Plant Application of Autonomous Decentralized Systems ...

引用

15th International Conference on Advanced Computer Theory and Engineering, ICACTE 2022

作者： Wang, Jingyang Zou, Tao Yang, Zhijia Wang, Hongrui Key Laboratory Of Networked Control System Institutes For Robotics And Intelligent Manufacturing Shenyang Institute Of Automation Chinese Academy Of Sciences Shenyang China Guangzhou University College Of Mechanical And Electrical Engineering Guangzhou China State Key Laboratory Of Robotics Key Laboratory Of Networked Control System Institutes For Robotics And Intelligent Manufacturing Shenyang Institute Of Automation Chinese Academy Of Sciences Shenyang China University Of Chinese Academy Of Sciences Beijing China

ISBN: (数字)9781665481809

ISBN: (纸本)9781665481809

This paper illustrates the application of an autonomous decentralized system introducing edge nodes in a smart factory. The nodes include atomic nodes, the most fundamental autonomic units constituting an autonomous decentralized system that are capable of independently extracting information from the data field and processing that information internally and simultaneously transmitting the processing results and other internal information to the data field proactively in a broadcast mode, where the transmitted information circulates in the data field. The group-based data field enables the sharing of information by atomic nodes. Grouped management nodes are the managers of the whole group, and edge nodes are the terminal intelligent control units of an intelligent autonomous decentralized system. Improvements in system decentralization, fault tolerance characteristics and flexibility of the system can lead to homogenization, autonomous control and autonomous coordination in complex manufacturing environments, as well as excellent online fault tolerance, online expansion and online maintenance of the system. In addition, it enhances the ever-changing and evolving control requirements by deconstructing the complexity in the system. © 2022 IEEE.

关键词： Fault tolerance

来源：评论

学校读者我要写书评

暂无评论

Measuring the Sim2Real Gap in 3D Object Classification for Different 3D Data Representation 13th

Measuring the Sim2Real Gap in 3D Object Classification for D...

引用

13th International Conference on Computer Vision Systems, ICVS 2021

作者： Weibel, Jean-Baptiste Rohrböck, Rainer Vincze, Markus Vision for Robotics Laboratory Automation and Control Institute TU Wien Vienna Austria

ISBN: (纸本)9783030871550

Perceiving the environment geometry is necessary for a robot to perform safe motions and actions. To decide upon meaningful actions, however, semantic understanding is also required. At the object level, this semantic classification task can directly be performed using the extracted object 3D data. While continuously improving, the performance of methods designed for this task still decrease on data captured by a robot because of input data differences [18], referred to as the Sim2Real gap. In this paper, we aim to better evaluate that gap for different 3D data representations and understand the impact of a variety of design choices through a set of specific experiments, performed both on the ModelNet dataset [20] to which a variety of alterations is applied and on the ScanObjectNN dataset [18]. Results indicate that occlusions plays an essential part in the gap and that their impact is mitigated by the use of hierarchical representation learned from the surface of the object itself. © 2021, Springer Nature Switzerland AG.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Dimension Reduction for Dynamic Analysis of Gene Expression Data Using Variational Autoencoder 13

Dimension Reduction for Dynamic Analysis of Gene Expression ...

引用

13th IEEE International Conference on CYBER Technology in automation, control, and Intelligent Systems, CYBER 2023

作者： Yuan, Shuai Chen, Shipeng Yang, Yongliang School of Electrical and Control Engineering Shenyang Jianzhu University Liaoning Shenyang110016 China Shenyang Institute of Automation State Key Laboratory of Robotics Chinese Academy of Sciences Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Liaoning Shenyang110106 China

ISBN: (纸本)9798350315196

Single-cell RNA sequencing technology captures gene expression at the whole-genome scale and single-cell level in many cells. Thus, the cellular states during a physiological process would be captured in detail. These data provide new opportunities and challenges for systems biology. Previously, the models in systems biology dealt with the dynamics of specific signaling pathways. However, it is almost impossible to directly model the dynamics of the whole genome due to the ultrahigh dimensionality of the data. Here, to model its gene regulatory dynamics, the dimensionality of the whole genome was reduced significantly using the latent space of a variational autoencoder, a generative deep learning model. In the low-dimensional latent space, an ordinary differentiation equation (ODE) system has been established to analyze the dynamic characteristics of the whole genome system. To demonstrate the effectiveness of this method, we generated a low-dimensional representation of a systems biology model we previously developed. The variational autoencoder reduced the dimension from 13 to 2 in latent space. An ODE model was developed to analyze the dynamics of this two-dimensional system. The results indicated that the 2-dimensional model captured the essence of the original systems biology model. © 2023 IEEE.

关键词： Dynamics

来源：评论

学校读者我要写书评

暂无评论

Development of a Method for Approaching the Autonomous Vehicle to a Moving Object

Development of a Method for Approaching the Autonomous Vehic...

引用

2024 International Russian automation Conference, RusAutoCon 2024

作者： Naidanova, Irina Gubankov, Anton Maritime State University Named after Admiral G.I. Nevelskoy Laboratory of Marine Unmanned Aviation and Marine Aviation Systems Vladivostok Russia Institute of Automation and Control Processes Maritime State University Named after Admiral G.I. Nevelskoy Robotics Laboratory Vladivostok Russia

The paper considers the development of a method for approaching an autonomous vehicle to a moving object. Approaching to objects may be necessary in various fields, for example, when landing an unmanned aircraft on a moving platform, animals and marine wildlife photo and videorecording, following the leader in group control, etc. It is assumed that the coordinates of the object are obtained without delay, however, at some points in time, position data is not received, that is, the trajectory of the object is represented by several separate segments of the trajectory. The paper proposes to use a combination of two classical guidance methods to approach the object. This eliminates the disadvantages of both methods and increases the overall efficiency of movement to the object. The pursuit method is used at short distances between the controlled vehicle and the object. The proportional approach method is used at long distances. A comparison of the simulation results on the generated data of the developed algorithm with the results obtained using only classical methods confirms the efficiency of simultaneous use of two guidance methods. © 2024 IEEE.

关键词： Extended Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Trajectory Planning for Minimizing Floating Pedestal Disturbance of Spatial Dual-Arm Robots 43

Trajectory Planning for Minimizing Floating Pedestal Disturb...

引用

43rd Chinese control Conference, CCC 2024

作者： Zhang, Hui Zuo, Xiaozhong Zhang, Wei Gao, Sheng Shenyang Jianzhu University College of Electrical and Control Engineering Shenyang110168 China Shenyang Institute of Automation Chinese Academy of Sciences State Key Laboratory of Robotics Shenyang110016 China China-Portugal Belt and Road Joint Laboratory on Space & Sea Technology Advanced Research Shanghai200120 China

ISBN: (纸本)9789887581581

This paper addresses the trajectory planning problem of a spatial dual-arm robot and proposes a method to minimize the floating pedestal perturbation using a nonlinear planning method. The joint angle of the dual-arm robot is the optimization variable, and the positioning accuracy of the end-effector and the pedestal disturbance are the optimization objective and constraints, respectively. A constrained multi-objective optimization problem is formulated, and the kinematic model of the robot is established by parameterizing the joint trajectory. A penalty factor and a collision detection mechanism are applied to ensure the safety of the planning process. A nonlinear planning method is used to solve the optimization problem and obtain the optimal joint trajectory of the dual-arm robot. Simulation results demonstrate that the proposed method effectively reduces the base disturbance while ensuring the positioning accuracy of the end-effector. © 2024 Technical Committee on control Theory, Chinese Association of automation.

关键词： End effectors

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：