检索结果-内蒙古大学图书馆

International Conference on Mechatronics and Machine Vision in Practice (M2VIP)

作者： Yuanhao Liu Wei Liang Chu Wang Xin Zhang Huanbing Gao Yinlong Zhang State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang China University of Chinese Academy of Sciences Beijing China State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences School of Information and Electrical Engineering Shandong Jianzhu University Shandong Key Laboratory of Intelligent Buildings Technology Jinan China

ISBN: (数字)9798350391916

ISBN: (纸本)9798350391923

Safe & smart move (SSM) aims to help industrial vehicular robot (IVR), such as warehousing robots, running safely and smartly by detecting the obstacles in front and maintaining a safe distance & attitude. However, the traditional SSM methods suffer the drawbacks of limited ranges, inaccurate regression of safety distance & orientation between the robot and the forward unexpected obstacles, and the inappropriate IVR control strategies. To solve these issues, this paper designs an innovative real-time safety-aware framework using the complementary Wheel-Encoder and Inertial-RGB-Depth measurements to ensure the IVR running safely, reasonably and reliably. To estimate the robot running states, we take advantages of the complementary wheel encoder, monocular RGB images and inertial measurements to obtain the robot positions, orientations, angular and linear velocities in a tightly-coupled manner. To improve the safety relative distance & attitude estimation accuracy, we exploit the RGB and depth measurements in a task-oriented fashion. The forward obstacles with the specific contours are detected using the Mask-RCNN model, followed by the Gaussian Mixture Model to obtain the forward obstacle depth. Eventually, an IVR control strategy is designed to maintain the robot safety distance and orientation, and to keep the minimum damage to the robot mechanical system. The presented method has been evaluated on the developed industrial vehicular robot safety perception platform. The experimental results prove the competitiveness against the state-of-the-art methods.

关键词： Service robots Warehousing Robot vision systems Wheels Reliability engineering Safety Mobile robots Mechanical systems Velocity measurement Gaussian mixture model

来源：评论

学校读者我要写书评

暂无评论

Distance- And velocity-based collision avoidance for time-varying formation control of second-order multi-agent systems

引用

IEEE Transactions on Circuits and systems II: Express Briefs 2021年第4期68卷 1253-1257页

作者： Pang, Zhong-Hua Zheng, Chang-Bing Sun, Jian Han, Qing-Long Liu, Guo-Ping Key Laboratory of Fieldbus Technology and Automation of Beijing North China University of Technology Beijing100144 China State Key Laboratory of Intelligent Control and Decision of Complex Systems School of Automation Beijing Institute of Technology Beijing100081 China School of Software and Electrical Engineering Swinburne University of Technology MelbourneVIC3122 Australia Department of Artificial Intelligence and Automation Wuhan University Wuhan430072 China

This brief addresses the time-varying formation control problem with collision avoidance for second-order multi-agent systems. By taking both distances and velocities between agents into account, a novel collision avoidance scheme is proposed on the basis of conventional distance-based artificial potential field methods. Compared with the latter, the proposed scheme can more accurately determine possible collision situations and thus significantly reduce possible collision areas, which consequently not only can reduce energy consumption, but also has as few adverse effects on formation maintenance as possible. Then a time-varying formation control protocol is designed so as to achieve zero steady-state position and velocity formation tracking errors without collision. Finally, theoretical analysis, numerical demonstration, as well as comparative simulation are provided to verify the effectiveness of the proposed method. © 2004-2012 IEEE.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

A Recurrent Attention and Interaction Model for Pedestrian Trajectory Prediction

引用

IEEE/CAA Journal of Automatica Sinica 2020年第5期7卷 1361-1370页

作者： Xuesong Li Yating Liu Kunfeng Wang Fei-Yue Wang State Key Laboratory for Management and Control of Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190and also with the University of Chinese Academy of SciencesBeijing 100049China College of Information Science and Technology Beijing University of Chemical TechnologyBeijing 100029China State Key Laboratory for Management and Control of Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China IEEE

The movement of pedestrians involves temporal continuity,spatial interactivity,and random *** a result,pedestrian trajectory prediction is rather *** existing trajectory prediction methods tend to focus on just one aspect of these challenges,ignoring the temporal information of the trajectory and making too many *** this paper,we propose a recurrent attention and interaction(RAI)model to predict pedestrian *** RAI model consists of a temporal attention module,spatial pooling module,and randomness modeling *** temporal attention module is proposed to assign different weights to the input sequence of a target,and reduce the speed deviation of different *** spatial pooling module is proposed to model not only the social information of neighbors in historical frames,but also the intention of neighbors in the current *** randomness modeling module is proposed to model the uncertainty and diversity of trajectories by introducing random *** conduct extensive experiments on several public *** results demonstrate that our method outperforms many that are state-ofthe-art.

关键词： Deep learning long short-term memory(LSTM) recurrent attention and interaction(RAI)model trajectory prediction

来源：评论

学校读者我要写书评

暂无评论

Adapting Human Mesh Recovery with Vision-Language Feedback

arXiv

引用

arXiv 2025年

作者： Xu, Chongyang Huang, Buzhen Zhang, Chengfang Feng, Ziliang Wang, Yangang College of Computer Science Sichuan University Chengdu610065 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education The School of Automation Southeast University Nanjing210096 China Intelligent Policing Key Laboratory of Sichuan Province Sichuan Police College Luzhou646000 China

Human mesh recovery can be approached using either regression-based or optimization-based methods. Regression models achieve high pose accuracy but struggle with model-to-image alignment due to the lack of explicit 2D-3D correspondences. In contrast, optimization-based methods align 3D models to 2D observations but are prone to local minima and depth ambiguity. In this work, we leverage large vision-language models (VLMs) to generate interactive body part descriptions, which serve as implicit constraints to enhance 3D perception and limit the optimization space. Specifically, we formulate monocular human mesh recovery as a distribution adaptation task by integrating both 2D observations and language descriptions. To bridge the gap between text and 3D pose signals, we first train a text encoder and a pose VQ-VAE, aligning texts to body poses in a shared latent space using contrastive learning. Subsequently, we employ a diffusion-based framework to refine the initial parameters guided by gradients derived from both 2D observations and text descriptions. Finally, the model can produce poses with accurate 3D perception and image consistency. Experimental results on multiple benchmarks validate its effectiveness. The code will be made publicly available. © 2025, CC BY.

关键词： Mesh generation

来源：评论

学校读者我要写书评

暂无评论

Method of formation of reference control signals for redundant manipulators

Method of formation of reference control signals for redunda...

引用

2021 International Conference on Automatics and Energy, ICAE 2021

作者： Filaretov, V.F. Gubankov, A.S. Gornostaev, I.V. Far Eastern Federal University Department of Automation and Robotics Vladivostok690091 Russia Institute of Automation and Control Processes FEB RAS Robotics Laboratory Vladivostok690041 Russia Institute of Marine Technology Problems FEB RAS Laboratory of Robotic Systems Vladivostok690091 Russia

The paper is devoted to preservation of dynamic control accuracy of working tools of multilink manipulators when they move along arbitrary spatial trajectories, taking into account the design limits in all degrees of freedom and special cases of position of their links. Preservation of control accuracy is proposed to be ensured by eliminating reach of all degrees of freedom of the manipulators to the limits and to indicated special positions, characterized by ambiguity in solving the inverse kinematic problems of the manipulators, as well as excluding the reach of their working tools to boundaries of working area due to use of a redundant degree of freedom when approaching indicated undesirable positions. The performed simulation has confirmed efficiency of the proposed method. © 2021 institute of Physics Publishing. All rights reserved.

关键词： Degrees of freedom (mechanics)

来源：评论

学校读者我要写书评

暂无评论

Shifting Spotlight for Co-supervision: A Simple yet Efficient Single-branch Network to See Through Camouflage

Shifting Spotlight for Co-supervision: A Simple yet Efficien...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Yang Hu Jinxia Zhang Kaihua Zhang Yin Yuan Jiale Huang Zechao Zhan Xin Wang Key Laboratory of Measurement and Control of CSE School of Automation Southeast University China Advanced Ocean Institute of Southeast University China School of Computer Science Nanjing University of Information Science and Technology China Alibaba Group China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Camouflaged object detection (COD) remains a challenging task in computer vision. Existing methods often resort to additional branches for edge supervision, incurring substantial computational costs. To address this, we propose the Co-Supervised Spotlight Shifting Network (CS 3 Net), a compact single-branch framework inspired by how shifting light source exposes camouflage. Our spotlight shifting strategy replaces multi-branch designs by generating supervisory signals that highlight boundary cues. Within CS 3 Net, a Projection Aware Attention (PAA) module is devised to strengthen feature extraction, while the Extended Neighbor Connection Decoder (ENCD) enhances final predictions. Extensive experiments on public datasets demonstrate that CS 3 Net not only achieves superior performance, but also reduces Multiply-Accumulate operations (MACs) by 32.13% compared to state-of-the-art COD methods, striking an optimal balance between efficiency and effectiveness.

关键词： computer vision Image edge detection Object detection Signal processing Feature extraction Acoustics Decoding Computational efficiency Speech processing Light sources

来源：评论

学校读者我要写书评

暂无评论

Perception for Coupler Rod of Freight Train Based on Image and Point Clouds

Perception for Coupler Rod of Freight Train Based on Image a...

引用

2022 Chinese automation Congress, CAC 2022

作者： Guo, Renjie Feng, Jun Yang, Huachang Luan, Dejie Yang, Guodong Li, En Institute of Automation CAS State Key Laboratory of Management and Control for Complex Systems Beijing100190 China University of Chinese Academy of Sciences School of Artificial Intelligence Beijing100049 China China Academy of Railway Sciences Corporation Limited Signal & Communication Research Institute Beijing100081 China

ISBN: (纸本)9781665465335

In the construction of automated marshaling yards, the automatic uncoupling operation of freight trains has always been the research and development direction. The coupler rod is the operation object of the uncoupling operation. The identification of coupler rod type and estimating position and posture are the prerequisites to realizing automatic uncoupling operation. In this paper, we propose a perception method of coupler rod by RGB image combined with the point cloud. We use an RGBD camera to synchronously collect frame-aligned RGB and depth images and generate point cloud data with colors according to the mapping relationship. Then, we use the YOLOv5 neural network to detect the collected RGB images and recognize the type of coupler rod in the image. Clear clutter in the point cloud and the bounding box is mapped to a spatial coordinate system for straight-through filtering of the point cloud. We use RANSAC for coarse registration and ICP for fine registration. The result of registration is carried out with the lower sampling point cloud model to achieve the registration of the coupler rod. Experiments show that this method can effectively segment the point cloud of the region of interest with high robustness. © 2022 IEEE.

关键词： Data fusion

来源：评论

学校读者我要写书评

暂无评论

Prior Knowledge Informed Neural Network for Subsurface Flow Prediction

Prior Knowledge Informed Neural Network for Subsurface Flow ...

引用

IEEE International Symposium on Industrial Electronics (ISIE)

作者： Haibo Cheng Shichao Li Peng Zeng 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 Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China

ISBN: (数字)9798350394085

ISBN: (纸本)9798350394092

Data-driven deep learning has been widely applied to solve subsurface flow problems. However, it is difficult to achieve accurate prediction with pure data-driven methods, especially when there is only a small amount of valid data. Prior knowledge is pre-existent and comes from an independent source. The neural network can be informed by prior knowledge to improve algorithm performance even with limited and sparse data. In this study, prior knowledge informed neural network (PKINN) is proposed to predict subsurface flow. The prior knowledge, on the one hand, is embedded in the neural networks as integrated loss function to inform the training process of deep learning methods. On the other hand, it is used as part of input term of neural network to improve calculation accuracy. Subsurface flow models are built to verify the proposed PKINN model. The results show that the PKINN method can solve subsurface flow problems effectively.

关键词： Knowledge engineering Deep learning Training Industrial electronics Solid modeling Accuracy Neural networks

来源：评论

学校读者我要写书评

暂无评论

Time Synchronization in Industrial Internet of Things: A Survey

Time Synchronization in Industrial Internet of Things: A Sur...

引用

IEEE Information Technology, Networking, Electronic and automation control Conference

作者： Ke Zhou Xiaoming Wang Shijie Cui Electric Power Research Institute of Guangxi Power Grid Co. Ltd. Nanning China 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 Liaoning China

ISBN: (数字)9798350370805

ISBN: (纸本)9798350370812

Time synchronization is a fundamental strategy for many operations such as data synchronous collection, timely fault tracking, distributed control, and real-time communication in Industrial Internet of Things (IIoT). Over the years, a wide variety of protocols and technologies have been proposed for different application scenarios. The accuracy, security, robustness, low cost, and so on, are the main focus for the design of time synchronization protocol. However, so far, there is no relatively unified standard for time synchronization in IIoT. To clarify the development of time synchronization technology, this paper surveys the latest research for time synchronization in various types of networks including Precision Time Protocol and wireless sensor networks. The future development of time synchronization in IIoT is also investigated.

关键词： Surveys Wireless sensor networks Protocols Accuracy Reviews Robustness Synchronization Security Standards Industrial Internet of Things

来源：评论

学校读者我要写书评

暂无评论

Fatigue Life Analysis of Piezoelectric Actuating Mechanism with Micro-displacement Amplifier 18

Fatigue Life Analysis of Piezoelectric Actuating Mechanism w...

引用

18th IEEE Conference on Industrial Electronics and Applications, ICIEA 2023

作者： Zhang, Xinyuan Wang, Shaoping Wu, Xiao He, Siyuan Wang, Xingjian Niu, Yu Gavrilov, Alex I. Beihang University School of Automation Science and Electrical Engineering Beijing100191 China Tianmushan Laboratory Xixi Octagon City Yuhang District Hangzhou310023 China Beihang University Ningbo Institute of Technology Ningbo315800 China Beihang University Research Institute of Aero-Engine Beijing100191 China Bauman Moscow State Technical University Department of Automatic Control Systems Moscow105005 Russia

ISBN: (纸本)9798350312201

Since piezoelectric actuating mechanism generally operate in high frequency response state, fatigue life has become an important factor influencing the performance and reliability of the entire drive mechanism. In order to investigate whether the designed piezoelectric ceramic actuator meets the active control requirements of the aero-engine, the paper analyzes the fatigue characteristics and fatigue life of the piezoelectric ceramic materials and the micro displacement amplification mechanism with finite element analysis software and the optimal spacing value is obtained by studying the effect of the flexible hinge spacing on the fatigue characteristics of the displacement amplifier. And then, the fatigue life of the displacement amplifier is analyzed based on the drive load spectrum of the aircraft during simulated flight, whose result is 340.93 hours. Finally, the fatigue life of the piezoelectric actuating mechanism is 32 minutes when loaded with full power, which meets the design target initially. © 2023 IEEE.

关键词： Piezoelectric actuators

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：