检索结果-内蒙古大学图书馆

FFPA-Net: Efficient Feature Fusion with Projection Awareness for 3D Object Detection

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Jiang, Chaokang Wang, Guangming Wu, Jinxing Miao, Yanzi Wang, Hesheng Engineering Research Center of Intelligent Control for Underground Space Ministry of Education School of Information and Control Engineering Advanced Robotics Research Center China University of Mining and Technology Xuzhou221116 China Department of Automation Key Laboratory of System Control and Information Processing of Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Shanghai200240 China The Department of Engineering Mechanics Shanghai Jiao Tong University Shanghai200240 China

Promising complementarity exists between the texture features of color images and the geometric information of LiDAR point clouds. However, there still present many challenges for efficient and robust feature fusion in the field of 3D object detection. In this paper, first, unstructured 3D point clouds are filled in the 2D plane and 3D point cloud features are extracted faster using projection-aware convolution layers. Further, the corresponding indexes between different sensor signals are established in advance in the data preprocessing, which enables faster cross-modal feature fusion. To address LiDAR points and image pixels misalignment problems, two new plug- and-play fusion modules, LiCamFuse and BiLiCamFuse, are proposed. In LiCamFuse, soft query weights with perceiving the Euclidean distance of bimodal features are proposed. In BiLiCamFuse, the fusion module with dual attention is proposed to deeply correlate the geometric and textural features of the scene. The quantitative results on the KITTI dataset demonstrate that the proposed method achieves better feature-level fusion. In addition, the proposed network shows a shorter running time compared to existing methods. Copyright © 2022, The Authors. All rights reserved.

关键词： Object detection

The DRTS-Net Framework: Enhanced Probabilistic Health Perception for Wind Turbine Bearings Under Complex Operating Conditions With Improved Interpretability

学校读者我要写书评

暂无评论

IEEE Transactions on Instrumentation and Measurement 2025年 74卷

作者： Yang, Tongguang Li, Guanchen Huo, Jinzhao Li, Xiaoyong Zhou, Xianwen Han, Qingkai Northeastern University School of Mechanical Engineering and Automation Shenyang110819 China Johns Hopkins University Department of Mechanical Engineering BaltimoreMD21218 United States Foshan University School of Mechatronic Engineering and Automation Foshan528225 China SCNU Environmental Research Institute Guangdong Provincial Key Laboratory of Chemical Pollution and Environmental Safety MOE Key Laboratory of Theoretical Chemistry of Environment South China Normal University School of Environment Guangzhou510006 China SCNU Qingyuan Institute of Science and Technology Innovation Company Ltd. Qingyuan511517 China Northeastern University Key Laboratory of Vibration and Control of Aero-Propulsion System Ministry of Education Shenyang110819 China

Health perception in mechanical systems is a crucial aspect of prognostics and health management (PHM). Deep learning models have been successfully applied to health perception in wind turbine bearings. However, due to the time-varying, redundant, and noisy characteristics of time-series data representing bearing wear, existing models face significant challenges, particularly in terms of generalization and interpretability. Moreover, although most current models have provided health perceptions, they overlook the strong stochastic nature of bearing degradation data, and thus fail to deliver reliable predictions of uncertainty information. To address these technical challenges, this study introduces a novel Deep residual temporal-spatial framework (DRTS-Net) for probabilistic health perception of wind turbine bearing wear states. This article creatively designs spatiotemporal information fusion module for extracting features from bearing degradation data. Inspired by improvements in residual network structures, the DRTS-Net integrates an attention mechanism and a soft thresholding mechanism from the deep residual shrinkage network to optimize the feature extraction process. This integration aims to mitigate the interference from minor redundant features in the degradation data. The framework incorporates Gaussian process regression in the output layer to yield the probability distribution of single-health perception values for bearing features. A comparative study was conducted using the same bearing health state dataset against current mainstream deep learning methods for bearing health assessment. Results demonstrate that the proposed DRTS-Net achieves superior performance in high-precision health perception, high-reliability probabilistic health perception. © 1963-2012 IEEE.

关键词： Stochastic systems

Discrete Continuous Nonlinear control system for Non-Affine Periodic Action Plant

学校读者我要写书评

暂无评论

Discrete Continuous Nonlinear Control System for Non-Affine ...

2020 International Russian automation Conference, RusAutoCon 2020

作者： Eremin, E.L. Nikiforova, L.V. Shelenok, E.A. Amur State University Information and Control Systems Department Blagoveshchensk Russia Pacific National University Automation and System Engineering Department Khabarovsk Russia

ISBN: (纸本)9781728161303

In the present paper authors discusses the problem of construct the discrete algorithms of nonlinear-periodic control system for one class of non-affine continuous plants which working in the priory uncertainty conditions. As methods to solve the posed in paper problem hyperstability criterion, Ldissipativity conditions and continuous models method are used. With the help of numerical experiments it is depicted the operating quality of the proposed hybrid nonlinear-periodic control system. The obtained results may be useful for construction the automated control system for dynamic plants which mathematical model contains non-linearity with respect to input signal. The paper results may be useful for construct the control systems for the class of non-affine dynamic plants with mathematical models are equivalent discussed plant's model. © 2020 IEEE.

关键词： Quality control

Can Digital Intelligence and Cyber-Physical-Social systems Achieve Global Food Security and Sustainability?

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2023年第11期10卷 2070-2080页

作者： Yanfen Wang Mengzhen Kang Yali Liu Juanjuan Li Kai Xue Xiujuan Wang Jianqing Du Yonglin Tian Qinghua Ni Fei-Yue Wang College of Resources and Environment University of Chinese Academy of SciencesBeijing 100049 Beijing Yanshan Earth Critical Zone National Research Station University of Chinese Academy of SciencesBeijing 101408 State Key Laboratory of Tibetan Plateau Earth System Environment and ResourcesInstitute of Tibetan Plateau ResearchChinese Academy of SciencesBeijing 100101China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of AutomationChinese Academy of Sciences(CASIA)Beijing 100190 School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China School of Grassland Science Beijing Forestry UniversityBeijing 100083China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China State Key Laboratory of Plateau Ecology and Agriculture Qinghai UniversityXining 810016 Key Laboratory of Adaptation and Evolution of Plateau Biota Northwest Institute of Plateau BiologyChinese Academy of SciencesXining 810001 Binzhou Institute of Technology Weiqiao-UCAS Science and Technology ParkBinzhou 256606China Beijing Yanshan Earth Critical Zone National Research Station University of Chinese Academy of SciencesBeijing 101408China Department of Engineering Science Faculty of Innovation EngineeringMacao University of Science and TechnologyMacao 999078 State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of AutomationChinese Academy of Sciences(CASIA)Beijing 100190China Faculty of Innovation Engineering Macao University of Science and TechnologyMacao 999078 Beijing Engineering Research Center of Intelligent Systems and Technology Chinese Academy of SciencesBeijing 100098 State Key Laboratory for Management and Control of Complex Systems Chinese Academy of SciencesBeijing 100190China IEEE

Plants sequester carbon through photosynthesis and provide primary productivity for the ecosystem. However, they also simultaneously consume water through transpiration, leading to a carbon-water balance relationship. Agricultural production can be regarded as a form of carbon sequestration *** the perspective of the natural-social-economic complex ecosystem, excessive water usage in food production will aggravate regional water pressure for both domestic and industrial purposes. Hence, achieving a harmonious equilibrium between carbon and water resources during the food production process is a key scientific challenge for ensuring food security and sustainability. Digital intelligence(DI) and cyber-physical-social systems(CPSS) are emerging as the new research paradigms that are causing a substantial shift in the conventional thinking and methodologies across various scientific fields, including ecological science and sustainability studies. This paper outlines our recent efforts in using advanced technologies such as big data, artificial intelligence(AI), digital twins, metaverses, and parallel intelligence to model, analyze, and manage the intricate dynamics and equilibrium among plants, carbon, and water in arid and semiarid ecosystems. It introduces the concept of the carbon-water balance and explores its management at three levels: the individual plant level, the community level, and the natural-social-economic complex ecosystem level. Additionally, we elucidate the significance of agricultural foundation models as fundamental technologies within this context. A case analysis of water usage shows that, given the limited availability of water resources in the context of the carbon-water balance, regional collaboration and optimized allocation have the potential to enhance the utilization efficiency of water resources in the river basin. A suggested approach is to consider the river basin as a unified entity and coordinate the relationship between the

关键词： Carbon-water balance decision-support digital intelligence(DI) foundation models planning

Quantum Approximate Optimization Algorithm in Non-Markovian Quantum systems

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Yue, Bo Xue, Shibei Pan, Yu Jiang, Min Department of Automation Shanghai Jiao Tong University The Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control College of Control Science and Engineering Zhejiang University Hangzhou310027 China School of Electronics and Information Engineering Soochow University Suzhou215006 China

Although quantum approximate optimization algorithm (QAOA) has demonstrated its quantum supremacy, its performance on Noisy Intermediate-Scale Quantum (NISQ) devices would be influenced by complicated noises, e.g., quantum colored noises. To evaluate the performance of QAOA under these noises, this paper presents a framework for running QAOA on non-Markovian quantum systems which are represented by an augmented system model. In this model, a non-Markovian environment carrying quantum colored noises is modelled as an ancillary system driven by quantum white noises which is directly coupled to the corresponding principal system;i.e., the computational unit for the algorithm. With this model, we mathematically formulate QAOA as piecewise Hamiltonian control of the augmented system, where we also optimize the control depth to fit into the circuit depth of current quantum devices. For efficient simulation of QAOA in non-Markovian quantum systems, a boosted algorithm using quantum trajectory is further presented. Finally, we show that non-Markovianity can be utilized as a quantum resource to achieve a relatively good performance of QAOA, which is characterized by our proposed exploration rate. Copyright © 2022, The Authors. All rights reserved.

关键词： White noise

Spirometer and sEMG respiratory patterns for clinical decision support system

学校读者我要写书评

暂无评论

Spirometer and sEMG respiratory patterns for clinical decisi...

IEEE Instrumentation and Measurement Technology Conference

作者： Amit Krishan Kumar Mansour H. Assaf Voicu Z. Groza Emil M. Petriu Faculty of Electrical-Electronic Engineering Duy Tan University Da Nang Vietnam Key Laboratory of Complex System Intelligent Control and Decision School of Automation Beijing Institute of Technology Beijing China School of Information Technology Engineering Mathematics and Physics The University of the South Pacific Suva Republic of Fiji School of Electrical Engineering and Computer Science University of Ottawa Ottawa Canada

To improve support system for subjects with respiratory ailments, this work analyses the respiratory patterns from spirometer and surface electromyography (sEMG). The patterns are integrated with risk and biochemical systems model to optimise the clinical decision support system (CDSS). The work considers terminal events for the spirometer and sEMG. The events and their associated patterns are correlated and projected on a hyperspace prior implementing it in decision support system. The proposed method shows that the different characteristics of breathing indicate some essential hidden information which when used as 4D scattered projection, optimises the decision making in CDSS. The analysis shows the effectiveness of bimodal respiratory patterns for different breathing capacities, which is promising for the modelled conditions.

关键词：

Data-driven approximation of control invariant set for linear system based on convex piecewise linear fitting

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Xu, Jun Chen, Fanglin School of Mechanical Engineering and Automation Harbin Institute of Technology Shenzhen518055 China The Key Laboratory of System Control and Information Processing Ministry of Education Shanghai200240 China The Department of Computer Engineering Harbin Institute of Technology Shenzhen518055 China

control invariant set is critical for guaranteeing safe control and the problem of computing control invariant set for linear discrete-time system is revisited in this paper by using a data-driven approach. Specifically, sample points on convergent trajectories of linear MPC are recorded, of which the convex hull formulates a control invariant set for the linear system. To approximate the convex hull of multiple sample points, a convex piecewise linear (PWL) fitting framework has been proposed, which yields a polyhedral approximation with predefined complexity. A descent algorithm for the convex PWL fitting problem is also developed, which is guaranteed to converge to a local optimum. The proposed strategy is flexible in computing the control invariant set in high dimension with a predefined complexity. Simulation results show that the proposed data-driven approximation can compute the approximated control invariant set with high accuracy and relatively low computational cost. © 2022, CC0.

关键词： Linear systems

HiCRISP: An LLM-based Hierarchical Closed-Loop Robotic Intelligent Self-Correction Planner

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Ming, Chenlin Lin, Jiacheng Fong, Pangkit Wang, Han Duan, Xiaoming He, Jianping The Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China The Department of Computer Science University of Illinois Urbana-Champaign IL United States The Department of Engineering Science University of Oxford Oxford United Kingdom

The integration of Large Language Models (LLMs) into robotics has revolutionized human-robot interactions and autonomous task planning. However, these systems are often unable to self-correct during the task execution, which hinders their adaptability in dynamic real-world environments. To address this issue, we present an LLM-based Hierarchical Closed-loop Robotic Intelligent Self-correction Planner (HiCRISP), an innovative framework that enables robots to correct errors within individual steps during the task execution. HiCRISP actively monitors and adapts the task execution process, addressing both high-level planning and low-level action errors. Extensive benchmark experiments, encompassing virtual and real-world scenarios, showcase HiCRISP’s exceptional performance, positioning it as a promising solution for robotic task planning with LLMs. Copyright © 2023, The Authors. All rights reserved.

关键词： Benchmarking

RGB-D Co-attention Network for Semantic Segmentation 15th

学校读者我要写书评

暂无评论

RGB-D Co-attention Network for Semantic Segmentation

15th Asian Conference on Computer Vision, ACCV 2020

作者： Zhou, Hao Qi, Lu Wan, Zhaoliang Huang, Hai Yang, Xu National Key Laboratory of Science and Technology of Underwater Vehicle Harbin Engineering University Harbin China The Chinese University of Hong Kong Hong Kong China State Key Laboratory of Management and Control for Complex System Institute of Automation Chinese Academy of Sciences Beijing China

ISBN: (纸本)9783030695248

Incorporating the depth (D) information for RGB images has proven the effectiveness and robustness in semantic segmentation. However, the fusion between them is still a challenge due to their meaning discrepancy, in which RGB represents the color but D depth information. In this paper, we propose a co-attention Network (CANet) to capture the fine-grained interplay between RGB’ and D’ features. The key part in our CANet is co-attention fusion part. It includes three modules. At first, the position and channel co-attention fusion modules adaptively fuse color and depth features in spatial and channel dimension. Finally, a final fusion module integrates the outputs of the two co-attention fusion modules for forming a more representative feature. Our extensive experiments validate the effectiveness of CANet in fusing RGB and D features, achieving the state-of-the-art performance on two challenging RGB-D semantic segmentation datasets, i.e., NYUDv2, SUN-RGBD. © 2021, Springer Nature Switzerland AG.

关键词： Semantic Segmentation