检索结果-内蒙古大学图书馆

Data-Driven Tracking Control of a Cushion Robot with Safe Autonomous Motion Considering Human-Machine Interaction Environment

引用

Journal of Dynamic systems, Measurement and Control 2025年第4期147卷 041003页

作者： Sun, Ping Shan, Rui Chang, Hongbin Wang, Shuoyu School of Artificial Intelligence Shenyang University of Technology Shenyang110870 China State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110169 China Department of Intelligent Mechanical Systems Engineering Kochi University of Technology Kochi7828502 Japan

This study proposes a data-driven safety controller with velocity constraints for a cushion robot. We constructed a mathematical description of the human-machine interaction environment by decomposing the generalized input force and coefficient matrix in the dynamic model. We established a new equivalent data model, which considered various human-machine interaction environments using a pseudo-Jacobian matrix. A stochastic configuration network (SCN) estimation method for variations in the human-machine interaction environment was proposed, with hidden layer nodes added at random. We designed a safe autonomous navigation path and proposed a data-driven control method that limited the actual velocity while stabilizing the tracking error system. In addition, the desired motion velocity of the robot was designed. This approach has the advantage of ensuring safety at a specified velocity. We also demonstrated and validated the effectiveness of the proposed data-driven algorithm using simulation-based comparative analysis and an experimental study. Copyright © 2024 by ASME.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Enhance Planning with Physics-informed Safety Controller for End-to-end Autonomous Driving

Enhance Planning with Physics-informed Safety Controller for...

引用

2024 IEEE International Conference on robotics and Biomimetics, ROBIO 2024

作者： Zhou, Hang Liu, Haichao Lu, Hongliang Ma, Jun Ji, Yiding Robotics and Autonomous Systems Thrust Systems Hub Guangzhou China School of Engineering The Hong Kong University of Science and Technology Department of Electronic and Computer Engineering SAR Hong Kong Hong Kong Intelligent Transportation Thrust Systems Hub Guangzhou China

ISBN: (纸本)9781665481090

Recent years have seen a growing research interest in applications of Deep Neural Networks (DNN) on autonomous vehicle technology. The trend started with perception and prediction a few years ago and it is gradually being applied to motion planning tasks. Despite the performance of networks improve over time, DNN planners inherit the natural drawbacks of Deep Learning. Learning-based planners have limitations in achieving perfect accuracy on the training dataset and network performance can be affected by out-of-distribution problem. In this paper, we propose FusionAssurance, a novel trajectory-based end-to-end driving fusion framework which combines physics-informed control for safety assurance. By incorporating Potential Field into Model Predictive Control, FusionAssurance is capable of navigating through scenarios that are not included in the training dataset and scenarios where neural network fail to generalize. The effectiveness of the approach is demonstrated by extensive experiments under various scenarios on the CARLA benchmark. © 2024 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Centralizing Data Warehouse Platform for Mining Management Using AWS Computing Instance

Centralizing Data Warehouse Platform for Mining Management U...

引用

2024 IEEE Region 10 Conference, TENCON 2024

作者： Sathaporn, Posathip Chaowalittawin, Vasutorn Krungseanmuang, Woranidtha Benjangkaprasert, Chawalit Purahong, Boonchana School of Engineering King Mongkut's Institute of Technology Ladkrabang Department of Robotics and Computational Intelligent Systems Bangkok Thailand School of Engineering King Mongkut's Institute of Technology Ladkrabang Computer Engineering Department Bangkok Thailand

ISBN: (纸本)9798350350821

Mining industry is one of significant industry in the world. In order to increase efficiency, safety, sustainability and environmental impacts in mining process. This article presents a centralized data platform for mining process by design based on microservices architecture which can be supported various of input data source such as manual form, excel file and internet of things (IoT) device and notification when the value is abnormal. Our platform implementation on Amazon Web Service (AWS) cloud. For development of productivity in process and controlling quality the mine environment. The results of the platform operations with various source of data acquisition with response time is less than 1.5 seconds per each request. © 2024 IEEE.

关键词： Cloud Computing Data Warehouse Internet of Things Microservices Architecture Mining Industry

来源：评论

学校读者我要写书评

暂无评论

Droplet-based Microfluidic Platform for High-throughput Formation of Multicellular Spheroids

Droplet-based Microfluidic Platform for High-throughput Form...

引用

2023 Annual IEEE International Conference on Manipulation, Manufacturing and Measurement on the Nanoscale, 3M-NANO 2023

作者： Zhan, Zhen Xie, Hanhan Hu, Chengzhi Southern University of Science and Technology Shenzhen Key Laboratory of Biomimetic Robotics and Intelligent Systems Department of Mechanical and Energy Engineering Shenzhen China

ISBN: (纸本)9798350344486

Cell culture in vitro is essential for drug screening, disease modeling, and stem cell-related research. Previous studies have indicated that two-dimensional (2D) cellular environments can significantly differ from physiological cells in vivo, leading to a high failure rate when translating therapeutics developed in 2D cell models to clinical applications. Therefore, there is a strong focus on developing three-dimensional (3D) cell culture techniques that more closely mimic in vivo cell microenvironments. These techniques hold great promise for enhancing precision in drug discovery and tissue regeneration. In this study, we introduce a novel microfluidic technique that utilizes droplets to fabricate hydrogel microspheres, each exhibiting a unique internal morphology suitable for 3D cell culture applications. Specifically, we employed this method to cultivate human umbilical vein endothelial cells (HUVECs) within the interior canals of the hydrogel microspheres, forming monolayers on the surfaces of the spiral canals. This setup effectively mimicked the configurations of native blood vessels. Furthermore, we successfully demonstrated the fabrication of heterogeneous spheroids with spiral blood vessel lumens, which can be utilized to construct spiral vascularized bone tissue. © 2023 IEEE.

关键词： Microfluidics

来源：评论

学校读者我要写书评

暂无评论

Terrain Classification Using Inside-Wheel Cameras Based on Wheel-Terrain Interaction Characteristics

Terrain Classification Using Inside-Wheel Cameras Based on W...

引用

2023 IEEE International Conference on robotics and Biomimetics, ROBIO 2023

作者： Hu, Longteng Xue, Feng Yao, Chen Li, Yunzhou Wei, Jin Wang, Peichen Zhu, Zheng Jia, Zhenzhong Shenzhen Key Laboratory of Biomimetic Robotics and Intelligent Systems Department of Mechanical and Energy Engineering Shenzhen518055 China Harbin150090 China

ISBN: (纸本)9798350325706

The wheeled rover is widely used in off-road planetary exploration tasks nowadays. However, complex operating environment like soft deformable terrains on the planet surface demands the high performance of rover. In order to reduce danger, environmental perception technologies need to be used on the rover. Terrain classification is a critical method in environmental perception. In this research, a wheel-vision-based terrain classification method is proposed. This method uses wheel-terrain interaction parameters obtained from inside-wheel cameras which are strongly related to the terrain as input. We use single-wheel testbed to collect and process data to form a dataset. The data is obtained under different slip ratios and different terrains. Then, we train four terrain classification models using machine learning algorithms and analyze their performance. From the results, all performance criteria of the models achieve over 95%, with DT being the optimal method. The feasibility of our method in the case of fewer training samples and the rationality of dataset selection are also verified through the results of different training set sizes and the ablation experiment. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cascaded Optimal Disturbance Rejection Control Scheme for Permanent Magnet Motor Drives 5

Cascaded Optimal Disturbance Rejection Control Scheme for Pe...

引用

5th IEEE International Conference on Technology, Informatics, Management, engineering and Environment, TIME-E 2024

作者： Suleimenov, Kanat Ali, Md. Hazrat Do, Ton Duc Cybersecurity Astana IT University Department of Intelligent Systems Astana Kazakhstan School of Engineering and Digital Sciences Nazarbayev University Department of Mechanical and Aerospace Engineering Astana Kazakhstan School of Engineering and Digital Sciences Nazarbayev University Department of Robotics Astana Kazakhstan

ISBN: (纸本)9798350364743

In this work, an optimal parameter tuning method for the PI controller is proposed to control speed and current loops of the surface mounted permanent magnet synchronous motor (SPMSM) under the field-oriented control (FOC) strategy. Furthermore, to guarantee robustness of the system to parameter variations and disturbance effect, the extended state observer (ESO) is introduced in both speed and current control loops. The performance of the PI controller tuned by the proposed optimal tuning method is compared with the PI-PI and disturbance observer-based (DOB) controllers where the parameters of the PI schemes are tuned by the Ziegler-Nichols method. Different critical testing conditions (i.e., step changes of speed and load torque, step change of load during the acceleration of the motor) are studied to compare the performances of each scheme. Simulation results have shown that the DOB controller and ESO- based PI speed controller tuned by the proposed algorithm shown almost similar peformance, whereas an ESO-based PI-PI cascaded control scheme with optimal parameters had superior characteristics compared to other controllers in the study. The worst performance among the studied control schemes was shown by the conventional PI - PI cascaded control with largest speed drop and longest time to reach a steady state. All the control algorithms are implemented in MATLAB/Simulink environment. © 2024 IEEE.

关键词： MATLAB

来源：评论

学校读者我要写书评

暂无评论

Facial Expression Recognition using Recent Convolutional Neural Network Models 26

Facial Expression Recognition using Recent Convolutional Neu...

引用

26th International Conference on Computer and Information Technology, ICCIT 2023

作者： Yenilmez, Fulya Yildiz, Canan Ugur, Mukden Turkish-German University Department of Computer Engineering Istanbul34820 Turkey Turkish-German University Department of Robotics and Intelligent Systems Istanbul34820 Turkey

ISBN: (纸本)9798350359015

In recent years, deep learning architectures have demonstrated remarkable achievements on diverse computer vision tasks, including the recognition of facial expressions. The development of precise and robust facial expression recognition (FER) models has the potential to improve a wide range of applications in various fields, such as human-computer interaction, emotion analysis, marketing, robotics, psychology, and health *** this domain, several Convolutional Neural Network (CNN) architectures have been employed to yield promising results. In this paper, we undertake a comparative analysis with the latest iterations of five widely adopted CNN models for the FER task: VGG19, InceptionV3, ResNet152V2, MobileNetV2, and EfficientNetV2B1. We also explore the effect of transfer learning, specifically the difference between pretraining on VGGFace versus ImageNet. Our primary goal is to comprehensively assess these architectures under identical conditions and provide clarity on their performance in comparison to each other and to previous works using various training strategies. Our assessments allow the conclusion that increasing the size and depth of these common "backbone"models leads to only minor improvements. Augmenting these models with additional architectural elements such as attention mechanisms seems much more promising in comparison. Our results further show that pretraining on a domain-specific dataset can lead to significant improvements, demonstrating the importance of a large FER related dataset. © 2023 IEEE.

关键词： CNN architectures face expression recognition fine-tuning neural networks transfer learning

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Sponge-Hydrogel Hybrid Structures with Robust Interfaces

引用

Chinese Journal of Chemistry 2023年第20期41卷 2635-2640页

作者： Pei Zhang Guangda Chen Xingmei Chen Junfei Xing Yue Tao Ji Liu Department of Mechanical and Energy Engineering Southern University of Science and TechnologyShenzhenGuangdong518055 China Shenzhen Key Laboratory of Biomimetic Robotics and Intelligent Systems Department of Mechanical and Energy EngineeringSouthern University of Science and TechnologyShenzhenGuangdong518055 China Guangdong Provincial Key Laboratory of Human-Augmentation and Rehabilitation Robotics in Universities Southern University of Science and TechnologyShenzhenGuangdong518055 China

Soft materials including elastomers and hydrogels are playing critical roles in a variety of fields,including bioelectrodes,batteries,supercapacitors,biomedical scaffolds,and solar vapor *** hydrophobic sponges(i.e.,mechanical robustness,elasticity and macroscopic porous structure)and hydrophilic hydrogels(i.e.,autonomous water absorption and transportation,biocompatibility)within one unit could readily combine the complementary characters from each component,making a number of future research directions and applications *** propose a simple yet effective strategy to construct sponge-hydrogel hybrid structures with robust hydrophobic-hydrophilic *** sponge scaffold imparts the sponges-hydrogel hybrids with desirable mechanical robustness,elasticity and macroscopic *** the other hand,the incorporated hydrogel component endows the hybrids with high water content(98 wt%hydrogel and 2 wt%sponge),superior compatibility,and nanoscale pores allowing for storage and transportation of various chemical and biological *** further demonstrate that the introduction of hydrophilic hydrogel components could effectively improve the liquid absorption capability,blood coagulation rate,hemostatic capacity and hemocompatibility,thus promising as hemostatic agents.

关键词： Sponge-hydrogel hybrid Interface Hierarchical Robustness Liquid absorption Gels Polymer Composites Materials Science

来源：评论

学校读者我要写书评

暂无评论

Robust Counting in Overcrowded Scenes Using Batch-Free Normalized Deep ConvNet

引用

Computer systems Science & engineering 2023年第9期46卷 2741-2754页

作者： Sana Zahir Rafi Ullah Khan Mohib Ullah Muhammad Ishaq Naqqash Dilshad Amin Ullah Mi Young Lee Institute of Computer Sciences and Information Technology(ICS/IT) The University of AgriculturePeshawar25130Khyber PakhtunkhwaPakistan Department of Convergence Engineering for Intelligent Drone Sejong UniversitySeoul05006Korea Collaborative Robotics and Intelligent Systems(CoRIS)Institute Oregon State UniversityORUSA Department of Software Sejong UniversitySeoul05006Korea

The analysis of overcrowded areas is essential for flow monitoring,assembly control,and *** counting’s primary goal is to calculate the population in a given region,which requires real-time analysis of congested scenes for prompt reactionary *** crowd is always unexpected,and the benchmarked available datasets have a lot of variation,which limits the trained models’performance on unseen test *** this paper,we proposed an end-to-end deep neural network that takes an input image and generates a density map of a crowd *** proposed model consists of encoder and decoder networks comprising batch-free normalization layers known as evolving normalization(EvoNorm).This allows our network to be generalized for unseen data because EvoNorm is not using statistics from the training *** decoder network uses dilated 2D convolutional layers to provide large receptive fields and fewer parameters,which enables real-time processing and solves the density drift problem due to its large receptive *** benchmark datasets are used in this study to assess the proposed model,resulting in the conclusion that it outperforms conventional models.

关键词： Artificial intelligence deep learning crowd counting scene understanding

来源：评论

学校读者我要写书评

暂无评论

CH-LSTTM: A Taxonomy of Traffic Hazards 4

CH-LSTTM: A Taxonomy of Traffic Hazards

引用

4th IEEE International Conference on Human-Machine systems, ICHMS 2024

作者： Yan, Song Huang, Chunxi He, Dengbo Thrust Of Robotics And Autonomous Systems Guangzhou China Hong Kong Thrust Of Intelligent Transportation Guangzhou China The Hong Kong University Of Science And Technology Department Of Civil And Environmental Engineering Hong Kong

ISBN: (纸本)9798350315790

During driving, drivers must interact with various objects in the highly dynamic driving environment, in which they need to perceive the traffic hazards and handle safety-critical scenarios. Previous studies have proved the importance of drivers' hazard perception skills and designed corresponding driver training programs. However, due to the lack of a suitable taxonomy for hazards, most driver training programs on hazard perception are simply a collection of various hazardous scenarios but do not guide drivers' hazard perception skills in a systematic way. The existing taxonomies of hazards were mainly based on the characteristics of hazards but did not take the hazard perception procedures into consideration, which can hardly be applied to improve drivers' hazard perception skills. Therefore, in this study, we proposed a taxonomy of traffic hazards based on an analysis of hazard perception procedures. Overall, a four-element taxonomy of traffic hazards (i.e., CH-LSTTM) was proposed, in which the Cues (single-element-based, multiple-element-based, and no-element-based), Hazards (visible vs. invisible), Link Strength (LS, which accounts for the uncertainty between the cues and the hazards during the hazard development process), and Time to Materialization (TTM, which indicates the imminence level of the hazard) were considered. We demonstrated the capability of the proposed taxonomy in depicting and categorizing realworld traffic hazards through a naturalistic driving case study. The proposed taxonomy can support the optimization of driver training programs to improve their hazard perception skills. © 2024 IEEE.

关键词： Taxonomies

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：