检索结果-内蒙古大学图书馆

2022 International Conference on Culture-Oriented Science and Technology, CoST 2022

作者： Ren, Hui Li, Mengnan Shen, Xiaochen School of Information and Commmunication Engineering Communication University of China Beijing100024 China Key Laboratory of Acoustic Visual Technology and Intelligent Control System Beijing100024 China Beijing100024 China

ISBN: (数字)9781665462488

ISBN: (纸本)9781665462488

In order to solve the problem of rapid switching of space equipment in the cultural complex, this paper combines Moth-Flame optimization Algorithm (MFO) and Dynamic Window Approach (DWA) to realize the hybrid path planning of handling robots in dynamic environments. Compared with the mainstream algorithms, the Moth-Flame optimization algorithm has the best performance. Different paths were classified and judged, and the global path planning based on MFO was proposed. The intersection of the dynamic obstacle and the global path were detected, and the dynamic window approach was used for local path planning in the road section where the collision occurs. Finally the combination of the global path planning and the local dynamic obstacle avoidance was realized. The effect of the hybrid path planning algorithm in the complex environment of the cultural complex had been verified. © 2022 IEEE.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Task Order Filing Generation Algorithm Based on Multidimensional Association Rules and Similarity Matching

Task Order Filing Generation Algorithm Based on Multidimensi...

引用

2024 International Conference Optoelectronic information and Optical Engineering, OIOE 2024

作者： Zhang, Xinyue Lv, Weimin Wei, Dingjiang Yang, Dongsheng Yang, Lin Naval Aviation University Yantai China No. 91593 of PLA Sanya China The Laboratory for Military-Civilian Integration Emergency Command and Control Jinan University Guangzhou China School of Public Management/Emergency Management Jinan University Guangzhou China Key Laboratory of Information System Engineering National University of Defense Technology Changsha China School of Information and Intelligent Engineering University of Sanya Academician Guoliang Chen Team Innovation Center University of Sanya Sanya China

ISBN: (数字)9781510688209

ISBN: (纸本)9781510688193

This paper examines the potential for leveraging the order dispatch algorithm in the commercial domain to enhance the intelligent allocation of military combat tasks, thereby improving the speed and accuracy of command decision-making in the context of intelligent warfare. The study proposes an "order-based" command and control model, which aims to overcome the efficiency bottleneck and information lag problem in traditional combat task allocation. The algorithmic design incorporates multi-dimensional association rules and similarity matching algorithms to guarantee the optimal matching of combat tasks and resources, thereby achieving the objectives of rapid response, efficient resource utilization, and enhanced combat effectiveness. This paper focuses on the challenges and advantages of this model in the context of naval warfare. It highlights the strategic value of order-based command and control in non-direct confrontation missions, such as reconnaissance, patrol, and intelligence gathering. The utilization of the "combat cloud," artificial intelligence, and a highly integrated command network enables the precise allocation of resources and the rapid execution of tasks. This, in turn, enhances the ISR capability, network-centered warfare effectiveness, and cross-domain synergistic warfare capability in naval warfare. The study also delineates the specific implementation process of the algorithm, which includes multi-dimensional association rule mining and similarity matching based on historical cases, with the objective of generating optimal combat scenarios and ensuring the effective execution of task orders. © 2025 SPIE.

关键词： Naval warfare

来源：评论

学校读者我要写书评

暂无评论

Grain Depot Wearable Device Detection Model Based on YOLOv5

Grain Depot Wearable Device Detection Model Based on YOLOv5

引用

Intelligent Management and Software Engineering (IMSE), International Conference on

作者： Jianjun Wu Yimeng Lian Qing Wen Tong Then Yuhua Zhu Zhihui Li College of Information Science and Engineering Henan University of Technology Zhengzhou China Key Laboratory of Grain Information Processing and Control Henan University of Technology Zhengzhou China

Standardized wearing of helmets and ventilators is the focus of grain depot safety management, which can effectively prevent safety accidents such as falling objects hurting people and fumigation poisoning. This paper is based on the deep learning algorithm to detect the wearing specifications of grain depot operations. Firstly, collect images by simulating the operation scene of the grain depot, recording video frames on the spot, etc. Use Labellmag software to mark the personnel wearing and not wearing the device, and create the original data set; Then, a grain depot wear standard monitoring model based on YOLOv5 is constructed. Add CBAM Attention to improve the network’s attention to local and global features and the ability to extract small target location information. In the post-processing stage, DIOU-NMS is optimized as the screening scheme of the target boxes to reduce the rate of missed detection rate of adjacent targets. Through the contrast experiment, the results show that the improved model mAP(mean average precision) is increased from 92.6% to 93.9%, and finally the detection model meeting the detection accuracy and real-time requirements is obtained.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Integrated Neural Unmanned system for Multi-Domain Perception and Decision-Making

An Integrated Neural Unmanned System for Multi-Domain Percep...

引用

2022 IEEE International Conference on Robotics and Biomimetics, ROBIO 2022

作者： Liu, Qiming Xu, Neng Zhang, Jinpeng Wang, Hesheng Shanghai Jiao Tong University Department of Automation Shanghai200240 China Shanghai Jiao Tong University SJTU Paris Elite Institute of Technology Shanghai200240 China Second Academy of China Aerospace Beijing100854 China Key Laboratory of Marine Intelligent Equipment and System Ministry of Education Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Department of Automation Key Laboratory of System Control and Information Processing of Ministry of Education Shanghai200240 China

ISBN: (纸本)9781665481090

Most recent intelligent systems study the perception or policy modules independently but ignore the inter-connection between them, which results in low information efficiency and high network redundancy, in the end, leads to the incomplete utilization of network potential and poor system-level end-to-end intelligence. This paper proposes an integrated end-to-end network that adapts to multi-domain inputs and multi-function outputs. 'Integration' is defined in this paper in mainly three aspects: network structure level, optimization level, and functional level. The integrated network architecture is capable of fusing multiple raw sensory inputs and outputting multiple perceptions and decisions simultaneously. We first implement the integrated system in a virtual simulation environ-ment and investigate the domain transformation methods to real world. Comprehensive experiment results in both virtual and real environments show that our proposed system can behave normally under exploration, target-driven navigation and target shooting tasks. © 2022 IEEE.

关键词： Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Semi-Global Leaderless Consensus of Linear Multi-agent systems with Actuator and Communication Constraints

引用

Journal of systems Science & Complexity 2020年第4期33卷 882-902页

作者： WANG Jian SHI Liangren GUAN Xinping Department of Automation and Key Laboratory of System Control and Information Processing of Ministry of EducationShanghai Jiao Tong UniversityShanghai 200240China Shanghai Key Laboratory of Navigation and Location-based Services and Academy of Information Technology and Electrical EngineeringShanghai Jiao Tong UniversityShanghai 200240China

This paper studies the leaderless consensus problems of multi-agent systems with input saturation and intermittent communication over directed networks. Both the state feedback and the output feedback consensus algorithms are developed based on low gain feedback approach. The convergence of the trajectories of all agents can be achieved by these proposed algorithms, if the communication topology has a directed spanning tree, and the intermittent communication period T and time rate ρ are larger than their associated threshold values. Simulation examples are provided to verify the theoretical results.

关键词： agent directed communication

来源：评论

学校读者我要写书评

暂无评论

Invariant Tensor Modeling and Functional Matrix Coding of Flight Dynamics for Nonlinear Aircraft control

Invariant Tensor Modeling and Functional Matrix Coding of Fl...

引用

Chinese control and Decision Conference, CCDC

作者： Tangwen Yin Department of Automation Shanghai Jiao Tong University Shanghai China Key Laboratory of System Control and Information Processing Ministry of Education Shanghai China

ISBN: (纸本)9781665478977

Flight trajectory consistence is an important factor influencing mission performance and safety. However, the lack of in-situ flight dynamics with high fidelity remains a challenge to enhance stability and controllability for aircraft maneuver in space, because modeling and coding of predictive system response in control synthesis is difficult to be mathematically formulated and computationally implemented. Here we generalize the invariant tensor modeling of flight dynamics so that its functional matrix coding is adapted to the multivariable nonlinear control of aircraft with augmented stability and controllability; and we verify that the nonlinear functional parameters in control synthesis with unobservable external forces and moments can improve the consistence of flight trajectory. Results demonstrate that the planned flight trajectory can be consistently fulfilled using the nonlinear control synthesized through tensor modeling and matrix coding. In conclusion, invariant tensor modeling facilitates the functional matrix coding of flight dynamics with six degrees of freedom, which can be applied to build the feedback through dimensional analysis for augmented stability and controllability, such that collaborative optimization of nonlinear functional parameters establishes the multivariable nonlinear control to improve the consistence of flight trajectory for sustained performance and continuing safety.

关键词： Analytical models Tensors Atmospheric modeling Computational modeling controllability Encoding Stability analysis

来源：评论

学校读者我要写书评

暂无评论

A New Hybrid Adaptive Self-Loading Fxlms and Cnn-Gru Net for Active Time-Varying Noise control

SSRN

引用

SSRN 2024年

作者： Zhu, Wenzhao Luo, Lei Key Laboratory of Intelligent Control and Neural Information Processing Education Ministry of China Yanshan University Qinhuangdao066004 China Key Laboratory of Optoelectronic Technology and Systems Education Ministry of China Chongqing University Chongqing400044 China

Active noise control (ANC) provides a lightweight and quick-to-deploy noise attenuation solution compared to traditional passive noise control. However, time-varying noise caused by the changing acoustic environment usually occurs in moving spaces, such as a car cabin, which further deteriorates the robustness of the adaptive filter and even deep networks in the ANC system. To use a deep ANC neural network with great denoising performance in a complex time-varying noise environment and reduce the interference of uncertain noise on the stability of the network, a new hybrid adaptive self-loading filtered-x least mean square (ASL-FxLMS) and convolutional neural network-gate recurrent unit (CNN-GRU) network is proposed. First, based on the CNN-LSTM structure, an improved CNN-GRU network with a multi-head attention mechanism is proposed to enhance attenuation performance for complicated periodical components in the time-varying noise and decrease the computing load as much as possible. In addition, an improved time-delay estimator is applied to improve the real-time ANC performance of CNN-GRU. Meanwhile, an adaptive self-loading FxLMS algorithm has been developed to deal with the uncertain components of time-varying noise. Moreover, to achieve balance attenuation, robustness, and tracking performance, the ASL-FxLMS and CNN-GRU are connected by a convex combination structure. Furthermore, theoretical analysis and simulations are also conducted to show the effectiveness of the proposed method. © 2024, The Authors. All rights reserved.

关键词： Active noise control

来源：评论

学校读者我要写书评

暂无评论

Efficient Frame Optimization Scheme for PSAM Assisted Transmission over Rician Fading Channel

Efficient Frame Optimization Scheme for PSAM Assisted Transm...

引用

information Communication and Software Engineering (ICICSE), IEEE International Conference on

作者： Yuqian Yan Zhongyang Yu Mengmeng Xu Hengzhou Xu Hai Zhu Chunhua Zhu School of Computer Science Henan University of Engineering Zhengzhou China Key Laboratory of Grain Information Processing Control (Henan University of Technology) Ministry of Education Zhengzhou China

ISBN: (数字)9798350351699

ISBN: (纸本)9798350351705

In this paper, we discuss the commonly used pilot-symbol-assisted-modulation (PSAM) assisted transmission and its corresponding frame optimization problem over Rician fading channel. Specifically, we design a generalized PSAM (G-PSAM) format based on the standard PSAM (S-PSAM) format and derive its approximate joint data-aided & non-data-aided Cramér-Rao bound (DA&NDA CRB) when the pilot-aided channel estimation is considered. Then, with the approximate DA&NDA CRB and the classical control-variate method (CVM), an efficient optimization scheme of the G-PSAM format is proposed, which is asymptotically optimal in terms of the mean-square error (MSE) estimation performance. Simulation results reveal the superiority of the optimized G-PSAM (OG-PSAM) format over the S-PSAM format for both short-packet and long-packet transmissions. Also, a practical example of the joint DA&NDA aided carrier synchronization is provided.

关键词： Fading channels Simulation Rician channels Estimation Channel estimation Mean square error methods Synchronization

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Safe controller Synthesis for Deterministic systems: A Posteriori Method With Validation Tests

arXiv

引用

arXiv 2023年

作者： Chen, Yu Shang, Chao Huang, Xiaolin Yin, Xiang Department of Automation Key Laboratory of System Control and Information Processing Shanghai Jiao Tong University Shanghai200240 China The Department of Automation Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China

In this work, we investigate the data-driven safe control synthesis problem for unknown dynamic systems. We first formulate the safety synthesis problem as a robust convex program (RCP) based on notion of control barrier function. To resolve the issue of unknown system dynamic, we follow the existing approach by converting the RCP to a scenario convex program (SCP) by randomly collecting finite samples of system trajectory. However, to improve the sample efficiency to achieve a desired confidence bound, we provide a new posteriori method with validation tests. Specifically, after collecting a set of data for the SCP, we further collect another set of independent validate data as posterior information to test the obtained solution. We derive a new overall confidence bound for the safety of the controller that connects the original sample data, the support constraints, and the validation data. The efficiency of the proposed approach is illustrated by a case study of room temperature control. We show that, compared with existing methods, the proposed approach can significantly reduce the required number of sample data to achieve a desired confidence bound. Copyright © 2023, The Authors. All rights reserved.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Learning the continuous-time optimal decision law from discrete-time rewards

引用

National Science Open 2024年第5期3卷 130-147页

作者： Ci Chen Lihua Xie Kan Xie Frank Leroy Lewis Yilu Liu Shengli Xie School of Automation Guangdong University of TechnologyGuangdong Key Laboratory of IoT Information TechnologyGuangzhou 510006China Key Laboratory of Intelligent Information Processing and System Integration of IoT Ministry of EducationGuangzhou 510006China School of Electrical and Electronic Engineering Nanyang Technological UniversitySingapore 639798Singapore 111 Center for Intelligent Batch Manufacturing Based on IoT Technology Guangzhou 510006China UTA Research Institute the University of Texas at ArlingtonFort Worth 76118USA Department of Electrical Engineering and Computer Science University of TennesseeKnoxville 37996USA Oak Ridge National Laboratory Oak Ridge 37830USA Guangdong-HongKong-Macao Joint Laboratory for Smart Discrete Manufacturing Guangzhou 510006China

The concept of reward is fundamental in reinforcement learning with a wide range of applications in natural and social *** an interpretable reward for decision-making that largely shapes the system's behavior has always been a challenge in reinforcement *** this work,we explore a discrete-time reward for reinforcement learning in continuous time and action spaces that represent many phenomena captured by applying physical *** find that the discrete-time reward leads to the extraction of the unique continuous-time decision law and improved computational efficiency by dropping the integrator operator that appears in classical results with integral *** apply this finding to solve output-feedback design problems in power *** results reveal that our approach removes an intermediate stage of identifying dynamical *** work suggests that the discrete-time reward is efficient in search of the desired decision law,which provides a computational tool to understand and modify the behavior of large-scale engineering systems using the optimal learned decision.

关键词： continuous-time state and action decision law learning discrete-time reward dynamical systems reinforcement learning

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：