检索结果-内蒙古大学图书馆

IEEE Conference on Decision and control

作者： Bohan Cui Alessandro Giua Xiang Yin Department of Automation Key Laboratory of System Control and Information Processing Shanghai Jiao Tong University Shanghai China Department of Electrical and Electronic Engineering University of Cagliari Cagliari Italy

In this paper, we propose a new framework for supervisory control of discrete-event systems in tactical environments. In contrast to the standard supervisory control theory, where the environments are considered fully adversarial, we consider the possibility of the presence of attackers who have their own objectives that may not necessarily be in opposition to the specification of the supervisor. We formulate this scenario as a Stakelberg game in the leader-follower setting, where the designer proposes a supervisor, and the attacker takes a best response to the supervisor. We characterize the solution to the Stakelberg supervisory control problem as having both cooperative and antagonistic solutions. Moreover, we provide an effective algorithm for synthesizing a cooperative supervisor that enables both players to achieve their objectives. Our work makes an initial step forward from the traditional zero-sum setting of supervisory control theory to the non-zero-sum setting. Examples are provided to illustrate our results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Construction of Minecraft Virtual Reality Scene Based on Voxel Point Cloud 8th

Construction of Minecraft Virtual Reality Scene Based on Vox...

引用

8th International Conference on Cognitive systems and Information Processing, ICCSIP 2023

作者： Ji, Nuocheng Zhuang, Hanyang Yang, Ming The University of Michigan – Shanghai Jiao Tong University Joint Institute Shanghai Jiao Tong University Shanghai200240 China Global Institute of Future Technology Shanghai Jiao Tong University Shanghai200240 China Department of Automation Shanghai Jiao Tong University Shanghai200240 China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai200240 China

ISBN: (纸本)9789819980208

Virtual Reality is an important development direction in recent years. Minecraft, a popular sandbox game, has a great potential to become a virtual reality platform for building immersive environments. Traditional methods of building virtual reality scenes rely heavily on massive human labors and require high levels of proficiency. To address these limitations, we propose an automatic, voxelated 3D modeling method with foreground and background environment segmented that can reduce modeling costs and achieve effective application in Minecraft virtual reality scenes such as virtual campuses. The proposed method leverages the use of point cloud reconstruction using a voxelization approach. A pipeline of converting point cloud to Minecraft scene is developed. Through preprocessing, segmenting, coloring, and exporting, a Minecraft virtual reality scene can be automatically generated based on voxel point cloud. Due to the noise in point cloud may cause defect during voxelization, a denoising and smoothing method using slice scanning and voxel connectivity segmentation has been implemented. It can generate building structures with clear outlines and uniform colors. And the entire process requires low computational complexity and achieves fast generation. We conducted experiments based on this method in indoor scenes, outdoor building landmarks, and complex underground scenes, and obtained results with clear structures and smooth surfaces, saving a lot of time for subsequent detailed modeling. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： 3D modeling

来源：评论

学校读者我要写书评

暂无评论

Depth-Aware Multi-Modal Fusion for Generalized Zero-Shot Learning 22

Depth-Aware Multi-Modal Fusion for Generalized Zero-Shot Lea...

引用

22nd IEEE International Conference on Industrial Informatics, INDIN 2024

作者： Cao, Weipeng Yao, Xuyang Xu, Zhiwu Pan, Yinghui Sun, Yixuan Li, Dachuan Qiu, Bohua Wei, Muheng Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Stony Brook University New York United States Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China ZhenDui Industry Artificial Intelligence Co. Ltd Shenzhen China Department of Automation Shanghai Jiao Tong University Shanghai China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China

ISBN: (纸本)9798331527471

Realizing Generalized Zero-Shot Learning (GZSL) based on large models is emerging as a prevailing trend. However, most existing methods merely regard large models as black boxes, solely leveraging the features output by the final layer while disregarding potential performance enhancements from other layers. Indeed, numerous researchers have visually depicted variations in the features learned across different layers of neural networks. Motivated by this observation, we propose a Vision Transformer (ViT)-based GZSL method named Depth-Aware Multi-Modal ViT (DAM2ViT), which exploits multi-level features of ViT. DAM2ViT incorporates a multi-modal interaction block to align semantic information of categories across multiple layers, thereby augmenting the model’s capacity to learn associations between visual and semantic spaces. Extensive experiments conducted on three benchmark datasets (i.e., CUB, SUN, AWA2) have showcased that DAM2ViT achieves competitive results compared to state-of-the-art methods. © 2024 IEEE.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

A Multimodal Fault Diagnosis Model Utilizing GAF Transformation for controllable Pitch Propeller Hydraulic system

A Multimodal Fault Diagnosis Model Utilizing GAF Transformat...

引用

International Conference on control, Decision and Information Technologies (CoDIT)

作者： Huihuang Cai Wei Chen Huanglong Fu Hua Wang Jingcheng Wang Department of Automation Key Laboratory of System Control and Information Processing Ministry of Education of China and Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Shanghai China Shanghai Marine Equipment Research Institute Shanghai China Department of Automation the Key Laboratory of System Control and Information Processing Ministry of Education of China and the Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Shanghai China Autonomous Systems and Intelligent Control International Joint Research Center Xi'an Technological University Xi'an China

ISBN: (数字)9798350373974

ISBN: (纸本)9798350373981

The hydraulic system of the controllable pitch propeller (CPP) serves as the power source for adjusting the blade pitch. Due to its structural complexity and harsh operating conditions, any malfunction of this system could significantly impair the vessel's navigation. Apart from the pitch command and the pitch feedback of CPP itself, the number and types of sensors added for fault diagnosis are not fixed. Therefore, this study establishes a multimodal fault diagnosis model based on Gramian angular field(GAF). By considering the deviation values of pitch feedback and pitch command as key variables, this model transforms them into a two-dimensional image using GAF, thereby obtaining more effective feature information. Image features are extracted using ResNet, while the temporal features of additional sensors are extracted using GRU. Finally, a multi-head attention mechanism is employed for feature fusion. This method achieves a classification accuracy of 100% in the classification of four types of hydraulic system faults simulated on the experimental platform.

关键词： Fault diagnosis Propellers Navigation Hydraulic systems Transforms Sensor phenomena and characterization Feature extraction Sensor systems Marine vehicles Load modeling

来源：评论

学校读者我要写书评

暂无评论

Self-Organized Criticality in C. Elegans Neural Network 42

Self-Organized Criticality in C. Elegans Neural Network

引用

42nd Chinese control Conference, CCC 2023

作者： Gu, Xiao Liu, Jian Yuan, Ye Zhao, Peng Xin, Kuankuan Fang, Tao Department of Automation Shanghai Jiao Tong University Shanghai200240 China Key Laboratory of System Control and Information Processing Ministry of Education Shanghai200240 China Shanghai Engineering Research Centre of Intelligent Control and Management Shanghai200240 China Institute of Machine Intelligence University of Shanghai for Science and Technology Shanghai200093 China Queensland Brain Institute The University of Queensland BrisbaneQLD4072 Australia

ISBN: (纸本)9789887581543

The self-organized criticality is a fundamental property for organisms to perform normal functional activities. Extensive large-scale biological neural network researches have found the existence of self-organized criticality through avalanche phenomenon, which is typical characteristic of self-organized criticality. However, such research method is not suitable for small-scale biological neural network, because number of neurons in small-scale biological neural network is not large enough to support the emergence of avalanche phenomenon. It has been demonstrated that branching parameter can also be used to describe the propagation of activity in the neural network. Here, in this paper, the C. elegans neural network composed of 302 neurons is selected to investigate the existence of self-organized criticality using branching parameter. Based on the obtained connectome of C. elegans, a directed graph model is constructed to simulate the gradient potential of neurons and the activity of C. elegans, then, the existence of self-organized criticality in the neural network of C. elegans is proved by using branching parameter method. Meanwhile, the result is further confirmed by analyzing the calcium activity data of C. elegans obtained from biological experiments. © 2023 Technical Committee on control Theory, Chinese Association of automation.

关键词： Calcium

来源：评论

学校读者我要写书评

暂无评论

A GM-TCN based Hybrid Prediction Method for Ash Fouling Prediction in Coal-fired Power Plant Boiler

A GM-TCN based Hybrid Prediction Method for Ash Fouling Pred...

引用

2022 Chinese automation Congress, CAC 2022

作者： Shi, Yuanhao Han, Tianxiang Cui, Fangshu Wen, Jie Qiao, Gangzhu North University of China School of Electrical and Control Engineering Taiyuan China Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China North University of China School of Data Science and Technology Taiyuan China

ISBN: (纸本)9781665465335

In response to the problem that ash deposition in boilers has a great impact on production efficiency as well as production safety, a grey level theory prediction model based on time convolution networks (GM-TCN) is proposed to predict the degree of ash in boiler heated areas by using a cleaning factor to assess the ash deposition condition on the heated surfaces. The accuracy of the prediction model is improved by utilizing the features of grey level theory that can predict the developmental changes in system behavior, combined with the high-precision approximation capability of the time-convolutional network. The modelling prediction of the ash level in the heated area of boilers during the production of coal-fired power stations is investigated. Experiments demonstrate that the model can predict the cleanliness factor with high accuracy, and the predicted values are closest to the true values compared to the other two models, verifying the accuracy and reliability of the model. © 2022 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

DiffRoad: Realistic and Diverse Road Scenario Generation for Autonomous Vehicle Testing

arXiv

引用

arXiv 2024年

作者： Zhou, Junjie Wang, Lin Meng, Qiang Wang, Xiaofan Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China Department of Automation Shanghai Jiao Tong University School of Mechatronic Engineering and Automation Shanghai University School of Electrical and Electronic Engineering Shanghai Institute of Technology Shanghai201418 China Department of Civil and Environmental Engineering National University of Singapore Singapore117576 Singapore

Generating realistic and diverse road scenarios is essential for autonomous vehicle testing and validation. Nevertheless, owing to the complexity and variability of real-world road environments, creating authentic and varied scenarios for intelligent driving testing is challenging. In this paper, we propose DiffRoad, a novel diffusion model designed to produce controllable and high-fidelity 3D road scenarios. DiffRoad leverages the generative capabilities of diffusion models to synthesize road layouts from white noise through an inverse denoising process, preserving real-world spatial features. To enhance the quality of generated scenarios, we design the Road-UNet architecture, optimizing the balance between backbone and skip connections for high-realism scenario generation. Furthermore, we introduce a road scenario evaluation module that screens adequate and reasonable scenarios for intelligent driving testing using two critical metrics: road continuity and road reasonableness. Experimental results on multiple real-world datasets demonstrate DiffRoad’s ability to generate realistic and smooth road structures while maintaining the original distribution. Additionally, the generated scenarios can be fully automated into the OpenDRIVE format, facilitating generalized autonomous vehicle simulation testing. DiffRoad provides a rich and diverse scenario library for large-scale autonomous vehicle testing and offers valuable insights for future infrastructure designs that are better suited for autonomous vehicles. Copyright © 2024, The Authors. All rights reserved.

关键词： Automobile testing

来源：评论

学校读者我要写书评

暂无评论

Sensor-based Multi-agent Coverage control with Spatial Separation in Unstructured Environments

arXiv

引用

arXiv 2024年

作者： Wang, Xinyi Xu, Jiwen Gao, Chuanxiang Chen, Yizhou Zhang, Jihan Wang, Chenggang Ding, Yulong Chen, Ben M. Department of Mechanical and Automation Engineering The Chinese University of Hong Kong N.T. Shatin Hong Kong Department of Automation Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Jiao Tong University Shanghai200240 China Department of Control Science and Engineering Tongji University Shanghai China Frontiers Science Center for Intelligent Autonomous Systems Ministry of Education China

Multi-robot systems have increasingly become instrumental in tackling coverage problems. However, the challenge of optimizing task efficiency without compromising task success still persists, particularly in expansive, unstructured scenarios with dense obstacles. This paper presents an innovative, decentralized Voronoi-based coverage control approach to reactively navigate these complexities while guaranteeing safety. This approach leverages the active sensing capabilities of multi-robot systems to supplement GIS (Geographic Information system), offering a more comprehensive and real-time understanding of environments like post-disaster. Based on point cloud data, which is inherently non-convex and unstructured, this method efficiently generates collision-free Voronoi regions using only local sensing information through spatial decomposition and spherical mirroring techniques. Then, deadlock-aware guided map integrated with a gradient-optimized, centroid Voronoi-based coverage control policy, is constructed to improve efficiency by avoiding exhaustive searches and local sensing pitfalls. The effectiveness of our algorithm has been validated through extensive numerical simulations in high-fidelity environments, demonstrating significant improvements in task success rate, coverage ratio, and task execution time compared with others. Copyright © 2024, The Authors. All rights reserved.

关键词： Multipurpose robots

来源：评论

学校读者我要写书评

暂无评论

Asynchronous distributed charging protocol for plug-in electric vehicles

Journal of Economy and Technology

引用

Journal of Economy and Technology 2023年 1卷 29-47页

作者： Yunfan Zhang Yifan Su Yue Chen Feng Liu State Key Laboratory of Power System Operation and Control Department of Electrical Engineering Tsinghua University Beijing China China Electric Power Planning & Engineering Institue Beijing China Department of Mechanical and Automation Engineering The Chinese University of Hong Kong Hong Kong Special Administrative Region China

The proliferation of plug-in electric vehicles (PEVs) advocates a distributed paradigm for coordinating PEV charging. Unlike existing primal-dual decomposition or consensus methods, this paper proposes a cutting-plane-based distributed algorithm considering a peer-to-peer (P2P) communication network, which enables asynchronous coordination among PEVs. First, an equivalent surrogate model is established by exploiting the duality of the original optimization problem, which masks the private information of individual users by equivalent transformation. Then, a cutting-plane based algorithm is derived to solve the surrogate problem in a distributed manner with intrinsic superiority to cope with various asynchrony. Critical implementation issues, including distributed initialization, distributed cutting-plane generation, and localized stopping criteria, are discussed in detail. Numerical tests on IEEE 37- and 123-node feeders with actual data illustrate that the proposed method is resilient to several asynchronies and admits the plug-and-play operation mode. The proposed methodology is expected to provide an alternative path toward the robust protocol for PEV charging.

关键词： Asynchronous algorithm Charging protocol Distributed optimization Plug-in electrical vehicles

来源：评论

学校读者我要写书评

暂无评论

Domain-adaptation with knowledge accumulation through parallel stacked autoencoders: methodology and application to sulfur recovery

Domain-adaptation with knowledge accumulation through parall...

引用

American control Conference (ACC)

作者： Tianhao Mou Jinfeng Liu Yuanyuan Zou Shaoyuan Li Maria Gabriella Xibilia Department of Automation Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Jiao Tong University Shanghai China Department of Chemical and Materials Engineering University of Al-berta Edmonton Alberta Canada Department of Engineering University of Messina Messina Italy

ISBN: (数字)9798350382655

ISBN: (纸本)9798350382662

Data-driven predictive models for end-point quality variables are important tools in industrial process modeling. However, establishing an effective predictive model with limited labeled data remains challenging. Transfer learning (TL) offers a solution by leveraging knowledge from similar but different tasks. This paper introduces a novel TL-based predictive model, domain-adaptation parallel stacked auto encoders (DA-PSAE), which can extract and accumulate knowledge from multiple similar processes. First, a parallel model structure is designed for the simultaneous extraction of static and plastic latent features. Besides, an effective TL-based training strategy is proposed, which utilizes data from multiple similar processes. The proposed model is applied to a sulfur recovery unit composed of four parallel sub-units. Experimental results verify the effectiveness of the proposed model.

关键词： Training Industries Process modeling Transfer learning Predictive models Feature extraction Data models

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：