检索结果-内蒙古大学图书馆

8th International Symposium on Computer Science and Intelligent control, ISCSIC 2024

作者： Yang, Yale Zhang, Zihao Hou, Huifang Zhang, Wenwen Zhuang, Chunsheng Henan University of Technology College of Information Science and Engineering Zhengzhou China Henan University of Technology Key Laboratory of Grain Information Processing and Control Ministry of Education Henan Key Laboratory of Grain Photoelectric Detection and Control School of Artificial Intelligence and Big Data Zhengzhou China Data Henan University of Technology School of Artificial Intelligence and Big Zhengzhou China Henan Academy of Sciences Zhengzhou China

ISBN: (纸本)9798350380286

RGB-thermal semantic segmentation is a potential solution for reliable semantic scene understanding under adverse weather and complex lighting conditions. However, past studies have primarily focused on the design of fusion paradigms. Unfortunately, these methods have not fully considered the modality differences caused by different imaging mechanisms, thereby reducing the performance of pixel-level semantic analysis. In response to this issue, this paper proposes an innovative Cross-Modality Comprehensive Feature Aggregation Network (CFANet). This method first designs a Cross-Modality Feature Rectification Module (CFRM) to align modality differences;then, it constructs a Global-Local Fusion Module (GLF) to sharpen object edges and refine the segmentation map. Results on two urban scene understanding datasets demonstrate that CFANet can effectively aggregate multi-layer deep features and outperform existing advanced deep learning methods in scene understanding performance. © 2024 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Optimal Planning of Zero-Carbon Off-Grid Ammonia-Hydrogen-Based Microgrids Considering Hybrid Types of Electrolyzer Modules

Optimal Planning of Zero-Carbon Off-Grid Ammonia-Hydrogen-Ba...

引用

Power system and Green Energy Conference (PSGEC)

作者： Junhao Gu Longyan Li Chao Ning 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: (数字)9798350365573

ISBN: (纸本)9798350365580

The off-grid ammonia-hydrogen-based microgrid is recognized as a promising paradigm for industrial decarbonization. In this paper, we propose a novel planning model for off-grid ammonia-hydrogen-based microgrids, where the hydrogen is produced in a distributed manner and the ammonia is synthesized in a large-scale energy-intensive plant. In specific, the proposed planning model considers hybrid types of electrolyzer modules and systematically investigates the operational constraints of distribution networks and hydrogen storage equipment, enabling distributed flexible hydrogen production. To seamlessly bridge distributed hydrogen sources and centralized ammonia production site, the delivery of hydrogen through the transportation network is structured as a vehicle routing problem. Eventually, the effectiveness of the proposed model is validated through case studies. Simulation results show that the proposed model lowers the total system cost by 11.8% compared with the simplified scenario which uses one single type of electrolyzer.

关键词： Ammonia Costs Hydrogen Vehicle routing Production Microgrids Distribution networks Planning Numerical models Optimization

来源：评论

学校读者我要写书评

暂无评论

Online-Learning-Based Distributionally Robust Motion control with Collision Avoidance for Mobile Robots

Online-Learning-Based Distributionally Robust Motion Control...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Han Wang Chao Ning Longyan Li Weidong Zhang 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: (数字)9798350384574

ISBN: (纸本)9798350384581

Collision-free navigation is a critical issue in robotic systems as the environment is often dynamic and uncertain. This paper investigates a data-stream-driven motion control problem for mobile robots to avoid randomly moving obstacles when the probability distribution of the obstacle’s movement is partially observable through data and can be even time-varying. A data-stream-driven ambiguity set is firstly constructed from movement data by leveraging a Dirichlet process mixture model and is updated online using real-time data. Then we propose an Online-Learning-based Distributionally Robust Nonlinear Model Predictive control (OL-DR-NMPC) approach for limiting the risk of collision through considering the worst-case distribution within the ambiguity set. To facilitate solving the OL-DR-NMPC problem, we reformulate it as a finite-dimensional nonlinear optimization problem. To cope with the bilinear matrix inequality constraints in the nonlinear problem, we develop a parabolic relaxation and a sequential algorithm, by which the problem is further transformed into polynomial-time solvable surrogates. The simulations using a quadrotor model are employed to demonstrate the effectiveness and advantages of the proposed method.

关键词： Navigation Simulation Real-time systems Probability distribution Safety Mobile robots Collision avoidance

来源：评论

学校读者我要写书评

暂无评论

Robust Stability and Stabilization Conditions for Fractional-order systems with Distributed Delays and Polytopic Uncertainties

Robust Stability and Stabilization Conditions for Fractional...

引用

Chinese control and Decision Conference, CCDC

作者： Yi-Nan Chen Jun-Guo Lu Zhen Zhu Jia-Rui Zhang Qing-Hao Zhang 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: (数字)9798350387780

ISBN: (纸本)9798350387797

This paper investigates the robust stability and stabilization conditions for fractional-order systems with distributed delays (FOSDDs) with polytopic uncertainties. To begin with, two robust stability conditions for FOSDDs with polytopic uncertainties are formulated. Subsequently, the state feedback controllers are put forward to robustly stabilize the FOSDDs with polytopic uncertainties. The obtained results are illustrated utilizing linear matrix inequalities (LMIs). Finally, two numerical instances are provided to showcase the effectiveness of the derived conditions.

关键词： State feedback Uncertainty Robust stability Delays Linear matrix inequalities Numerical stability

来源：评论

学校读者我要写书评

暂无评论

Towards Autonomous Indoor Parking: A Globally Consistent Semantic SLAM system and A Semantic Localization Subsystem

arXiv

引用

arXiv 2024年

作者： Sha, Yichen Zhu, Siting Guo, Hekui Wang, Zhong Wang, Hesheng Department of Automation Key Laboratory of System Control and Information Processing Ministry of Education Shanghai Jiao Tong University China Dimensional Robot Shanghai China

We propose a globally consistent semantic SLAM system (GCSLAM) and a semantic-fusion localization subsystem (SF-Loc), which achieves accurate semantic mapping and robust localization in complex parking lots. Visual cameras (front-view and surround-view), IMU, and wheel encoder form the input sensor configuration of our system. The first part of our work is GCSLAM. GCSLAM introduces a novel factor graph for the optimization of poses and semantic map, which incorporates innovative error terms based on multi-sensor data and BEV (bird’s-eye view) semantic information. Additionally, GCSLAM integrates a Global Slot Management module that stores and manages parking slot observations. SF-Loc is the second part of our work, which leverages the semantic map built by GCSLAM to conduct map-based localization. SF-Loc integrates registration results and odometry poses with a novel factor graph. Our system demonstrates superior performance over existing SLAM on two real-world datasets, showing excellent capabilities in robust global localization and precise semantic mapping. Copyright © 2024, The Authors. All rights reserved.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Accelerated Simulation of Master Equation for Open Quantum systems

Accelerated Simulation of Master Equation for Open Quantum S...

引用

第42届中国控制会议

作者： Bo Yue Yanfang Wang Shibei Xue Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China

Simulation of open quantum systems is undoubtedly critical to design of quantum devices and applications of quantum technologies since dynamics of open quantum systems cannot be solved analytically in general. However, the dimension of open quantum systems grows exponentially as the number of their subsystems increases or as involving complicated environments,which reduces the computational efficiency of the simulation. In this paper, we boost numerical simulation of master equations of open quantum systems from several aspects with which the total time and the occupied memory in the simulation are significantly reduced without losing precision. Our method can be applied to the simulation of non-Markovian quantum systems described by an augmented system model as well. We conduct numerical experiments on simulation of a non-Markovian spin *** with the algorithm in a well-known toolbox, QuTiP, our method can take 26.3% time and less memory under fair conditions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Few-Shot Class-Incremental Semantic Segmentation via Pseudo-Labeling and Knowledge Distillation 4

Few-Shot Class-Incremental Semantic Segmentation via Pseudo-...

引用

4th International Conference on information Science, Parallel and Distributed systems, ISPDS 2023

作者： Jiang, Chengjia Wang, Tao Li, Sien Wang, Jinyang Wang, Shirui Antoniou, Antonios Minjiang University Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Fuzhou China Fujian Education Institutions Wuyi University The Key Laboratory of Cognitive Computing and Intelligent Information Processing Wuyishan China College of Computer and Data Science Fuzhou University Fuzhou China European University Cyprus Department of Computer Science and Engineering Nicosia Cyprus

ISBN: (纸本)9798350337181

We address the problem of learning new classes for semantic segmentation models from few examples, which is challenging because of the following two reasons. Firstly, it is difficult to learn from limited novel data to capture the underlying class distribution. Secondly, it is challenging to retain knowledge for existing classes and to avoid catastrophic forgetting. For learning from limited data, we propose a pseudo-labeling strategy to augment the few-shot training annotations in order to learn novel classes more effectively. Given only one or a few images labeled with the novel classes and a much larger set of unlabeled images, we transfer the knowledge from labeled images to unlabeled images with a coarse-to-fine pseudo-labeling approach in two steps. Specifically, we first match each labeled image to its nearest neighbors in the unlabeled image set at the scene level, in order to obtain images with a similar scene layout. This is followed by obtaining pseudo-labels within this neighborhood by applying classifiers learned on the few-shot annotations. In addition, we use knowledge distillation on both labeled and unlabeled data to retain knowledge on existing classes. We integrate the above steps into a single convolutional neural network with a unified learning objective. Extensive experiments on the Cityscapes and KITTI datasets validate the efficacy of the proposed approach in the self-driving domain. Code is available from https://***/ChasonJiang/FSCILSS. © 2023 IEEE.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Spatial-Temporal-Rule-based Traffic Movement Status Interpretation at Intersections *

Spatial-Temporal-Rule-based Traffic Movement Status Interpre...

引用

2023 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2023

作者： Zhuang, Hanyang Gao, Liyang Qian, Yeqiang Wang, Chunxiang Yang, Ming University of Michigan Shanghai Jiao Tong University Joint Institute Shanghai Jiao Tong University Shanghai200240 China Ministry of Education of China Key Laboratory of System Control and Information Processing Shanghai200240 China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai200240 China

ISBN: (纸本)9798350327182

Traffic light is the most significant component of road transportation. Traffic lights control the traffic movement at intersections by allowing the movement of some lanes and forbidding that of the others to ensure safety and efficiency. It is important for intelligent vehicles to understand the meaning of traffic lights. Conventional research works on traffic light detection and tracking consider each light independently, so the occlusion of some lights may mislead the decision of the vehicle. Since all traffic lights at an intersection work together, it is more essential to understand the traffic movement status controlled by the traffic lights rather than the perception of a single light. Therefore, this paper proposes a spatial-temporal-rule-based framework to interpret the current traffic movement status and predict the next status. The spatial information, including position and class, is obtained by traffic light detection. The temporal information is perceived by the proposed topologic-feature-based tracking method. The rule information is recognized by combination of spatial and temporal information. A dual-view camera system consisting of a telephoto camera and a wide-angle camera is adopted to ensure long perception distance and wide coverage simultaneously. The successful tracking of traffic lights from 200 m to 10 m away provides enough data to recognize the phase-change rule, which leads to correct interpretation and prediction. A customized dataset was collected, and experiments were conducted to illustrate the capability of the proposed method. © 2023 IEEE.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

A novel compilation method of comprehensive mission spectrum of aero-engine maneuvering load based on use-related mission segment

引用

Chinese Journal of Aeronautics 2023年第3期36卷 161-170页

作者： Xuming NIU Qi LU Zhigang SUN Yingdong SONG Jiangsu Province Key Laboratory of Aerospace Power System and College of Energy and Power Engineering Nanjing University of Aeronautics and AstronauticsNanjing 210016China Laboratory of Aero-Engine Thermal Environment and Structure Ministry of Industry and Information Technology College of Energy and Power EngineeringNanjing University of Aeronautics and AstronauticsNanjing 210016China College of Energy and Power Engineering and State Key Laboratory of Mechanics and Control of Mechanical Structures Nanjing University of Aeronautics and AstronauticsNanjing 210016China

Comprehensive Mission Spectrum(CMS)of an aero-engine can reflect the usage characteristics of the *** can provide load input for engine life prediction and accelerated mission *** this paper,a novel compilation method of CMS of aero-engine maneuvering load based on mission segment is ***,the use-related Typical Mission Segment(TMS)of maneuvering load is divided and identified according to spectral ***,the mathematical model of different kinds of TMS are established based on stochastic process ***,the CMS of maneuvering load is compiled based on *** proposed method can accurately quantify the compilation of *** compiled CMS shows good agreement with the original load *** to damage consistency inspection,the compiled CMS is consistent with the damage caused by the original load spectrum in terms of low cycle fatigue.

关键词： Aero-engine Comprehensive mission spectrum Maneuvering load Spectrum compilation Typical mission segment

来源：评论

学校读者我要写书评

暂无评论

Mission segment division of the whole aeroengine loading spectrum based on flight actions

引用

Chinese Journal of Aeronautics 2022年第2期35卷 164-174页

作者： Yu JIN Zhigang SUN Yingdong SONG Xin LIN Xuming NIU Junjie DING Jiangsu Province Key Laboratory of Aerospace Power System College of Energy and Power EngineeringNanjing University of Aeronautics and AstronauticsNanjing 210016China Key Laboratory of Aero-engine Thermal Environment and StructureMinistry of Industry and Information TechnologyNanjing 210016China State Key Laboratory of Mechanics and Control Mechanical Structures Nanjing University of Aeronautics and AstronauticsNanjing 210016China

This paper studies on a division method of the whole aeroengine loading spectrum flight mission segment and rotor speed mission segment,which is based on the actual flight actions and related to the flight operations of aeroengine and is suitable for the variable-speed aeroengines such as turbojet and *** the research,the aeroengine loading spectrum operation-related mission segments can be divided,which can provide important data basis for the life research on the structures which are sensitive to flight maneuver(such as the main shaft,large gearbox and installation section),lay a foundation for the simulation,compilation and prediction of the whole aeroengine loading ***,based on the summary of basic flight actions in actual flight,the division of flight mission segment was realized by ***,the aeroengine rotor speed mission segments,associated with flight actions and missions,were divided based on the flight mission segment division ***,the efficiency and accuracy of the mission segment division results were verified by adopting measured loading spectrum ***,the characteristics of speed mission segment division results were compared and analyzed in tables and *** comparison results show that the characteristics of similar speed mission segments are similar,while the characteristics of different speed mission segments are *** the shapes of similar mission segments vary to the change of flight actions and operations,which can reflect the operation-related feature of the segments.

关键词： Aircraft engine Flight mission segment Mission segment division Rotor speed mission segment Spectrum analysis

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：