检索结果-内蒙古大学图书馆

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

Design of a directional feature-driven weld target tracking algorithm 23

Design of a directional feature-driven weld target tracking ...

引用

6th International Conference on Signal Processing and Machine Learning, SPML 2023

作者： Ma, Fengying Sun, Yuhe Ji, Peng Dong, Wanlong Li, Jie Li, Xuexin Yan, Wei Geng, Baojun School of Information and Automation Engineering Qilu University of Technology Shandong Academy of Sciences China China Unicom Research Institute China Robotics Co. Ltd China Pittsburgh College of Sichuan University China

ISBN: (纸本)9798400707575

In order to solve the problems such as unique and strange working space which is not easy to weld, inconvenient operation of teaching reproduction working mode, poor tracking effect caused by environmental interference of tracking accuracy of welding seam, a welding target tracking algorithm based on direction feature was designed. The algorithm has good accuracy, strong stability and is suitable for field welding operations. The orientation feature-driven welding seam target tracking algorithm proposed in this paper processes and calculates the images and other data captured by the camera to obtain the error of welding seam tracking and carry out follow-up tracking operations, which can complete welding seam tracking more accurately and reliably. The algorithm proposed in this paper adapts to the image features of V-groove under the irradiation of auxiliary light source, and enables the camera and welding torch to find the weld coordinates more accurately under the interference of arc light, splash and other noises. The results of welding experiment in the tank show that the system has good stability, high accuracy and good weld forming quality, which is within 0.12mm and meets the process requirements of pipeline welding. © 2023 ACM.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Image Recovery and Object Detection Integrated Algorithms for Robots in Harsh Battlefield Environments 16th

Image Recovery and Object Detection Integrated Algorithms f...

引用

16th International Conference on Intelligent robotics and Applications, ICIRA 2023

作者： Wang, Xudong Chen, Xi’ai Wang, Feifan Xu, Chonglong Tang, Yandong State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110169 China University of Chinese Academy of Sciences Beijing100049 China School of Automation and Electrical Engineering Shenyang Ligong University Shenyang110159 China Limited Shenyang110170 China

ISBN: (纸本)9789819964918

Battlefield environments are harsher than normal environments, and the images captured by imaging equipment are more prone to degradation. Degraded images seriously affect the analysis of military intelligence and the deployment of intelligent weapons. To address this issue, we propose an image recovery algorithm, which recovers degraded battlefield images based on a physical imaging model and uses a light-weight network to estimate the parameters of physical model. In addition, we propose a strategy to joint training of the image recovery module and the object detection module. Specifically, we integrate the recovery module to the front of YOLO detector to jointly optimize the two modules with detection loss. The image recovery module is light-weight without significant adverse impact on the real-time running of object detection, which can be easily deployed to intelligent unmanned devices such as battlefield robots. The experimental results show that the proposed algorithm achieves better recovery performance in battlefield environments, and the joint training strategy effectively improve the accuracy of object detection. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2023.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Adaptive Neural Network Tracking for a Magnetic Microrobot in Presence of Model Uncertainty and Unknown Disturbance 19

Adaptive Neural Network Tracking for a Magnetic Microrobot i...

引用

19th IEEE International Conference on automation Science and engineering, CASE 2023

作者： Wang, Haoyu Liu, Yueyue Fan, Qigao Wu, Xiaoyu Hu, Yingbai School of Internet of Things Engineering Institute of Automation Jiangnan University Wuxi214122 China National University of Singapore Department of Biomedical Engineering 119077 Singapore Multi-Scale Medical Robotics Centre The Chinese University of Hong Kong Hong Kong

ISBN: (纸本)9798350320695

Magnetic microrobots have potential applications in many medical diagnosis and treatment applications due to the unique characteristics in biological fine manipulation, such as precise drug delivery and being able to be used in complex biological environments. Precise and robust trajectory tracking control of magnetic microrobots under complex disturbances and uncertain dynamic model is still one of the most important and challenging steps in achieving ideal applications. In this paper, an adaptive neural network control algorithm is proposed to address the uncertain dynamic parameters and complex external disturbances. The developed state feedback control strategy based on a radial basis function neural network (RBFNN) can effectively estimate the uncertainties online from the state and desired trajectories, rather than the model-based control. The controller require as little knowledge of system parameters as possible. Subsequently, the closed-loop stable system is guaranteed based on Lyapunov theory. Finally, the two experimental researches are conducted on our developed electromagnetic manipulation system to validate the effectiveness of the proposed controller. © 2023 IEEE.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

A Dog Harness Product Design Assessment Using EDAS Method 23th

A Dog Harness Product Design Assessment Using EDAS Method

引用

23rd International Conference on Intelligent Systems Design and Applications, ISDA 2023

作者： Vadivel, S.M. Alli, P. Vinoth Babu, N. Kumar, Vimal Abhinav, A. VIT Business School Chennai Vandalur Kelambakkam Road Chennai600127 India Department of Robotics and Automation Rajalakshmi Engineering College Thandalam Chennai602105 India Chaoyang University of Technology Taichung County41349 Taiwan VIT Law School Vandalur Kelambakkam Road Chennai600127 India

ISBN: (纸本)9783031648496

A smart dog harness is a wearable device that integrates technology to enhance the safety, health, and well-being of dogs. This device incorporates various features such as GPS tracking, activity monitoring, and health sensors that can provide pet owners with real-time data about their dog’s movements, health status, and behavior. The smart dog harness is designed to be comfortable, durable, and easy to use, with features like LED lights for visibility in low light conditions, a panic button that alerts the owner if the dog is lost, and an app that allows the owner to monitor the dog’s activity remotely. The technology used in a smart dog harness is rapidly evolving, and as more pet owners seek ways to enhance their dog’s care, it is likely that these devices will become increasingly popular. Ultimately, a smart dog harness can be an invaluable tool for any pet owner who wants to keep their furry friend safe, healthy, and happy. Here we are applying some product design techniques like prototype design models analyze using EDAS method for overall designing a smart dog harness. For that purpose, we have analyzed comfortability, durability, ease of use, price, health monitoring, safety features and behavioral feedback under each existing and our product prototype model. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Product design

来源：评论

学校读者我要写书评

暂无评论

Diagnosis of Faults in Edge-PLC using Optimized Deep Learning models in Industrial IoT 9

Diagnosis of Faults in Edge-PLC using Optimized Deep Learnin...

引用

9th International Conference on Advanced Computing and Communication Systems, ICACCS 2023

作者： Kumar, A. Kishore Rajesh Kumar, T. Balamanigandan, R. Kumar, A. Sasi Mahaveerakannan, R. Department of Robotics and Automation Sri Ramakrishna Engineering College Tamilnadu Coimbatore641022 India SIMATS Saveetha School of Engineering Department of Computer Science and Engineering Tamil Nadu Chennai India Srinivas University Institute of Engineering & Technology Department of Cloud Technology & Data Science Surathkal India

ISBN: (纸本)9798350397376

Industrial Internet of Things (IIoT) may allow for the state of equipment to be monitored and defects to be detected before they become serious, helping smart factories keep up with the rising demands for safety and efficiency brought on by worldwide competition. In the case of Cloud Computing, data-driven approaches implemented in the cloud are used to first train the model using a vast quantity of raw data, and then end-machines send their real-time readings for processing at the cloud data centre. It is possible, however, that this will impose a significant delay and a high computational cost. In this study, we take into account a hierarchical structure in which edge-PLCs are used to collect sensed data locally and lessen the burden on long-distance connections. Due to the fact that a single responsibility may be associated with multiple swaying topographies, we aim to first reduce the sum of features required to identify a fault, and then identify the smallest possible set of edge-PLCs that still accounts for all of the most important ones, all while keeping deployment costs to a minimum. To address this, we present an Enhanced Harris Hawkins Optimization (EHHO) approach to tackling the features selection issue, followed by the assortment of edge-PLCs through the set coverage problematic. The model named Residual Attention Neural Network (RANN) is proposed the in this study to forecast the fault detection procedure. Residual Neural Network (ResNet) is used by RANN to help diagnose problems, alongside the knowledge of experts. We evaluate the performance of our technique in comparison to existing AI-based approaches, such as the lregression model and its expansions, by simulating on a real data trail. The findings confirm competence and presentation of the suggested approach, which meets or even surpasses the correctness of approaches employing the entire collection of data. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Nonsingular Terminal Sliding Mode Adaptive Control for Unmanned Aerial Manipulator in Gliding Grasping

引用

Jixie Gongcheng Xuebao/Journal of Mechanical engineering 2023年第23期59卷 76-86页

作者： Chen, Yanjie Yu, Jianye Zhang, Zhenguo Zhong, Hang Zhang, Hui Wang, Yaonan School of Mechanical Engineering and Automation Fuzhou University Fuzhou350108 China College of Electrical and Information Engineering Hunan University Changsha410082 China School of Robotics Hunan University Changsha410082 China

Unmanned aerial manipulator (UAM) is a new type of robotic system equipping with active operation mechanism, which has the ability to physically interaction with environments. Aiming at the problem of stable control when the UAM dynamic grasping, a nonsingular terminal sliding mode adaptive controller with an auxiliary system is proposed to improve the anti-disturbance property of the UAM facing to unpredictable contact force. The Newton-Euler method is adopted to establish the dynamics model of the UAM. Considering the instantaneous contact force between the end tip of the onboard manipulator and the object is the main disturbance source in grasping, the contact force model based on dynamics is established by using impulse theorem to improve modeling accuracy when UAM dynamic grasping. To reduce the influence of violent disturbance on flight control performance during dynamic grasping, an auxiliary system is proposed in the controller to compensate for the possible input saturation, enhancing the ability to deal with instantaneous disturbances. The stability of the proposed method is analyzed by Lyapunov theory. The simulation and experimental results show that the proposed method has advantages of strong stability and rapid response for UAM dynamic grasping. © 2023 Chinese Mechanical engineering Society. All rights reserved.

关键词： Manipulators

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning Based Mobile Robot Navigation in Unknown Environment with Continuous Action Space 5

Deep Reinforcement Learning Based Mobile Robot Navigation in...

引用

5th International Conference on Intelligent Autonomous Systems, ICoIAS 2022

作者： Phueakthong, Phuwanat Varagul, Jittima Pinrath, Nattawat School of Mechatronics Engineering Suranaree University of Technology Nakhon Ratchasima Thailand School of Manufacturing Automation and Robotics Engineering Suranaree University of Technology Nakhon Ratchasima Thailand School of Industrial Engineering Suranaree University of Technology Nakhon Ratchasima Thailand

ISBN: (数字)9781665498388

ISBN: (纸本)9781665498388

This work aims to propose the use of deep reinforcement learning for mobile robot navigation and obstacle avoidance in previously unknown areas or without pre-made maps with continuous action control to increase the capabilities of mobile robots beyond conventional map-based navigation. Deep reinforcement learning is used to enable the robot to learn how to make decisions and interact with the environment observed from sensor data to safely navigate itself to its destination. The robot has a two-dimensional laser scanner, ultrasonic sensors and odometry sensor. Deep Deterministic Policy Gradient, which can function in continuous action space, was chosen as the deep reinforcement learning model. The robot is trained and tested in a Gazebo simulator with Robot Operating System. After the training process, the robot is put to the challenge to complete a waypoint navigation mission in four unknown areas as part of an assessment. The results indicate that the mobile robot is adaptable and has the capability of traveling to the specified waypoints and completing the job without the need for a pre-drawn route or an obstacle map in unidentified environments with the minimum success rate of 69.7 percent. © 2022 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Locust-Inspired Energy Storage Joint for Variable Jumping Trajectory Control 16th

A Locust-Inspired Energy Storage Joint for Variable Jumping ...

引用

16th International Conference on Intelligent robotics and Applications, ICIRA 2023

作者： Yang, Yongzun Feng, Zhiyuan Jin, Cheng Tang, Lingqi Ma, Songsong Li, Yao School of Mechanical Engineering and Automation Harbin Institute of Technology Shenzhen518052 China State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin150001 China Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics Harbin Institute of Technology Shenzhen518052 China

ISBN: (纸本)9789819964949

Jumping is a good solution for small robots over obstacles. Most of the current jumping robots are not energy store adjustable due to the design of the energy storage elements and structures, which limits the effective working space of the robot. The locust is good at jumping. Thanks to the excellent structure of the hind legs, the locust can change the degree of compression of the simi-lunar process (SLP) and change the energy storage while maintaining the same jumping stance. Herein, we design a locust-inspired energy storage joint and verified its function on a jumping robot. The motors and wires were used to imitate the muscles and the torsion springs were used to imitate SLP. To accurately describe the energy stored, a static model of the torsion springs was developed. Furthermore, the number of motor revolutions and the stored energy value were also calculated and could be used for subsequent precise control. Six jumping experiments with different compression angles for torsion springs proved the feasibility of the static model. This locust-inspired energy storage joint is the basis for the next robot capable of the omnidirectional, continuous autonomous jumping. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2023.

关键词： Energy storage

来源：评论

学校读者我要写书评

暂无评论

Dynamic modeling and analysis for a differential modular robot joint with the friction model

Dynamic modeling and analysis for a differential modular rob...

引用

2022 IEEE International Conference on robotics and Biomimetics, ROBIO 2022

作者： Liu, Yukun Luo, Ruiqing He, Minghui Du, Liang Bao, Sheng Yuan, Jianjun Wan, Weiwei Shanghai Key Laboratory of Intelligent Manufacturing and Robotics School of Mechatronic Engineering and Automation Shanghai University Shanghai China Shanghai Robotics Institute Shanghai University Shanghai China Department of System Innovation Graduate School of Engineering Science Osaka University Osaka Toyonaka Japan

ISBN: (纸本)9781665481090

The study of friction has long been popular with scientists. Considering the coupling characteristic of multi-input-multi-output (MIMO) system, the coupling friction model was established, which was based on Coulomb-Viscous friction model for the differential modular robot joint (DMRJ) according to the law of conservation of energy. Then, we identified the coefficients of the friction model through the experiment. In order to verify the accuracy of the established friction model, we regarded the DMRJ as a 2-DoF linkage and built the inertial dynamic model based on Lie theory, whose inertial parameters were estimated by computer aided design (CAD). Besides, we chose the trajectory based on the Fourier series, which has good performance in anti-interference ability, as the verification trajectory. From the generated trajectories, we used a trajectory that is able to change as much as possible in speed, position and acceleration to estimate the accuracy of the model comprehensively. Finally, the result indicated the model had good accuracy. © 2022 IEEE.

关键词： Modular robots

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：