检索结果-内蒙古大学图书馆

Event-Triggered Near-Optimal control for Unknown Discrete-Time Nonlinear systems Using Parallel control

IEEE TRANSACTIONS ON CYBERNETICS 2023年第3期53卷 1890-1904页

作者： Lu, Jingwei Wei, Qinglai Zhou, Tianmin Wang, Ziyang Wang, Fei-Yue Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 100049 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Tsinghua Univ Dept Automat Beijing 100084 Peoples R China

This article uses parallel control to investigate the problem of event-triggered near-optimal control (ETNOC) for unknown discrete-time (DT) nonlinear systems. First, to achieve parallel control, an augmented nonlinear system (ANS) with an augmented performance index (API) is proposed to introduce the control input into the feedback system. The control stability relationship between the ANS and the original system is analyzed, and it is shown that, by choosing a proper API, optimal control of the ANS with the API can be seen as near-optimal control of the original system with the original performance index (OPI). Second, based on parallel control, a novel event-triggered scheme is proposed, and then a novel ETNOC method is developed using the time-triggered optimal value function of the ANS with the API. The control stability is proved, and an upper bound, which is related to the design parameter, is provided for the actual performance index in advance. Then, to implement the developed ETNOC method for unknown DT nonlinear systems, a novel online learning algorithm is developed without reconstructing unknown systems, and neural network (NN) and adaptive dynamic programming (ADP) techniques are employed in the developed algorithm. The convergence of the signals in the closed-loop system (CLS) is shown using the Lyapunov approach, and the assumption of boundedness of input dynamics is not required. Finally, two simulations justify the theoretical conjectures.

关键词： Nonlinear systems Optimal control control systems Performance analysis Stability criteria Iterative algorithms Heuristic algorithms Adaptive dynamic programming (ADP) event-triggered control near-optimal control parallel control reinforcement learning (RL) unknown nonlinear systems

来源：评论

学校读者我要写书评

暂无评论

Completely Stealthy FDI Attack Against state Estimation in Networked control systems

引用

IEEE TRANSACTIONS ON CIRCUITS AND systemS II-EXPRESS BRIEFS 2023年第3期70卷 1114-1118页

作者： Liu, Yifa Cheng, Long Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 100049 Peoples R China Peng Cheng Lab Dept Math & Theories Shenzhen 518055 Peoples R China

An effective false data injection attack should cause enough damage to the system while avoiding being spotted by detection methods. This brief proposes an extremely stealthy attack strategy, which can make the residual almost always unchanged to invalidate both the widely used chi(2) detector and the advanced summation detector and can eventually cause unbound state deviations. Compared with the existing attack methods, the proposed attack strategy can reduce the sum of cumulative residual increments by 85.39% while causing 9817001 times of the state deviations in the numerical simulations.

关键词： Detectors Sensors Networked control systems Symbols Observers Mathematical models Estimation error False data injection attack estimation complete stealthiness detection networked control systems

来源：评论

学校读者我要写书评

暂无评论

Event-triggered near-optimal tracking control based on adaptive dynamic programming for discrete-time systems

引用

NEUROCOMPUTING 2023年第1期537卷 187-197页

作者： Wang, Ziyang Lee, Joonhyup Wei, Qinglai Zhang, Anting Xilingol Vocat Coll Dept Mech & Elect Engn Xilinhot 026000 Peoples R China Tsinghua Univ Dept Automat Beijing 100084 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

Frequent state monitoring and controller updates can enhance the precision of tracking control, while simultaneously overburdening the communication network transmission. In this paper, For the purpose of saving communication costs, we propose event-triggered control algorithms for the optimal tracking control problem. First, we reconstruct the discrete-time nonlinear system into a converted system. Then, the adaptive dynamic programming algorithm is employed to find the optimal controller off-line, and the event-triggered scheme is used to reduce the communication costs online. Novel triggering conditions with fewer assumptions are designed to implement the event-triggered scheme. Different from existing works, the event-triggered scheme can be introduced not only into the converted system but also into the actual system, which is more practical because the actual controller is what one can only access in practice. In addition, with the developed algorithms, the tracking error can be proved to be stable at the origin, in other words, the actual system can be guaranteed to track the desired trajectory. Algorithms developed in this paper are implemented by three neural networks, the model network, the action network and the critic network. Finally, examples are presented to verify the effectiveness and rationality of the algorithms.(c) 2023 Elsevier B.V. All rights reserved.

关键词： Optimal control Adaptive dynamic programming Event-triggered control Neural network

来源：评论

学校读者我要写书评

暂无评论

Soft Contrastive Learning With Q-Irrelevance Abstraction for Reinforcement Learning

引用

IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL systemS 2023年第3期15卷 1463-1473页

作者： Liu, Minsong Li, Luntong Hao, Shuai Zhu, Yuanheng Zhao, Dongbin Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 100049 Peoples R China Beihang Univ Sch Software Beijing 100191 Peoples R China

The difference between training and testing environments is a huge challenge to generalizing reinforcement learning (RL) algorithms. We propose a soft contrastive learning with a coarser approximate Q-irrelevance abstraction for RL (SCQRL) to increase RL generalization. Specifically, we specify the coarser approximate Q-irrelevance abstraction as the feature of the state with a theoretical analysis for better generalization ability. We construct a positive and negative sample selection mechanism based on the Q value for contrastive learning to achieve efficient representation learning. Considering the selection error of positive and negative samples, we design soft contrastive learning and combine it with RL in the form of an auxiliary task to propose SCQRL. The generalization experiments on several Procgen environments demonstrate that SCQRL outperforms the excellent generalized RL algorithm.

关键词： Contrastive learning generalization reinforcement learning (RL) representation learning

来源：评论

学校读者我要写书评

暂无评论

Performance Improvement of a High-Speed Swimming Robot for Fish-Like Leaping

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2022年第2期7卷 1936-1943页

作者： Chen, Di Wu, Zhengxing Zhang, Pengfei Tan, Min Yu, Junzhi Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 100049 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Peking Univ Coll Engn BIC ESAT State Key Lab Turbulence & Complex SystDept Adv Beijing 100871 Peoples R China

Many aquatic animals are able to leap out of water effortlessly, however, it is still exceedingly challenging for a swimming robot. Inspired by the fast-swimming mechanism of fish, in this letter, we develop an untethered high-speed swimming robot with the integration of high-frequency oscillation and compliant passive components for performance improvements in swimming speed, efficiency and even fish-like leaping motion. The stiffness optimization of compliant components is conducted via experiments. As a result, both swimming speed and efficiency have been significantly improved and the robot surprisingly reaches a swimming speed of 1.88 m/s corresponding to 7.1 body lengths per second (BL/s). That is, the compliant components' stiffness is of great importance to the performance improvement of a swimming robot at high-frequency oscillation. Additionally, the leaping motion is successfully performed with the optimized swimming robot and the maximum height of center of mass (CM) can reach up to 0.23 m. A simplified model is developed to analyze the leaping height with different speeds and body lengths, which suggests that the robot with small size leaps out of water more easily. The obtained results in this letter will offer some significant insights into the design and optimization for a high-speed swimming robot, as well as the cross-domain motions between water and air.

关键词： Biologically-inspired robots mechanism design compliant joints and mechanisms high-speed swimming fish-like leaping motion

来源：评论

学校读者我要写书评

暂无评论

Software-Defined Active LiDARs for Autonomous Driving: A Parallel Intelligence-Based Adaptive Model

IEEE TRANSACTIONS ON INTELLIGENT VEHICLES

引用

IEEE TRANSACTIONS ON INTELLIGENT VEHICLES 2023年第8期8卷 4047-4056页

作者： Liu, Yuhang Sun, Boyi Tian, Yonglin Wang, Xingxia Zhu, Yin Huai, Rouxing Shen, Yu Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 100049 Peoples R China Univ Chinese Acad Sci Dept Comp Sci & Technol Beijing 100049 Peoples R China Chinese Acad Sci State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Chinese Acad Sci Inst Automat Beijing Engn Res Ctr Intelligent Syst & Technol Beijing 100190 Peoples R China North Automat Control Technol Inst Taiyuan 030006 Peoples R China Beijing Huairou Acad Parallel Sensing Beijing 101407 Peoples R China

LiDAR is an indispensable sensor for autonomous driving that can provide precise 3D information about the environment. Among various types of LiDARs, mechanical LiDARs are the most commonly used on vehicles that uniformly perceive the scene utilizing rotating motors. However, accurate perception of foreground objects is considered as the most important task in automotive LiDARs, therefore the current operating mode of mechanical LiDARs wastes a significant amount of sensing resources on the useless background. Besides, the development of LiDAR hardware and software systems is currently split into two independent segments, lacking real-time interaction between physical entities and digital models in cyberspace. To address these issues, we propose software-defined active LiDARs for autonomous driving based on parallel intelligence. Active LiDARs redefine LiDAR's hardware operation through software systems to achieve adaptive sensing resource allocation, constituting a closed loop between physical space and cyberspace. During the working process, it calculates scenario heatmaps with the constructed high-definition maps (HD maps) in cyberspace at first. Then it takes prescriptive control of physical LiDARs based on heatmaps to improve sensing resource utilization. We build two adaptive LiDAR models in CARLA and construct a hardware prototype in the parallel sensing platform, DAWN. Active Point Cloud (APC), a new dataset collected in CARLA, is proposed and a 3D object detection task is selected to demonstrate the effectiveness of active LiDARs. Our experimental results show that active LiDARs can both improve raw data quality and model performance compared with mechanical LiDARs, especially for the perception of distant objects.

关键词： Software-defined active LiDARs parallel intelligence adaptive sensing resources allocation

来源：评论

学校读者我要写书评

暂无评论

Line-of-sight based three-dimensional path following control for an underactuated robotic dolphin

引用

Science China(Information Sciences) 2021年第1期64卷 215-226页

作者： Jincun LIU Zhenna LIU Junzhi YU State Key Laboratory for Turbulence and Complex System Department of Mechanics and Engineering ScienceBIC-ESATCollege of EngineeringPeking University Department of Electrical and Automation Shandong Labor Vocational and Technical College State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of Sciences

This paper investigates the three-dimensional(3-D) path following control problem for an underactuated robotic dolphin. With a comprehensive consideration of the mechanical constraint and swimming principle of the robotic dolphin, a decoupling motion strategy is proposed to produce yaw and pitch maneuvers simultaneously. Then, kinematics and dynamics models for 3-D dolphin-like swimming are established,followed by simulations of the path following control. Furthermore, a novel lookahead based 3-D line-ofsight(LOS) guidance law is developed and implemented to obtain desired attitude angles with its simplicity,intuitiveness, and small computational footprint. Finally, simulation results illustrate the feasibility and effectiveness of the proposed path following control methods.

关键词： robotic dolphin path following 3-D LOS guidance law decoupling motion

来源：评论

学校读者我要写书评

暂无评论

ACP-Net: Asymmetric Center Positioning Network for Real-Time Text Detection

引用

KNOWLEDGE-BASED systemS 2024年 305卷

作者： Zhu, Boyuan Liu, Fagui Chen, Xi Tang, Quan Chen, C. L. Philip South China Univ Technol 342 Outer Ring East Rd Guangzhou 510006 Peoples R China Peng Cheng Lab 2 Xingke 1st St Shenzhen 518055 Nanshan Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst 95 Zhongguancun East Rd Beijing 100190 Peoples R China

Scene text detection is crucial across numerous application fields. However, despite the emphasis on real-time performance in scene text detection, most existing detection models utilize the Feature Pyramid Network (FPN) for feature extraction, often disregarding its inherent limitations. Integrating high-resolution multi-channel features into FPN requires substantial computational resources. While FPN treats local and global features equally and is stable in various applications, its suitability for text-specific features is questionable. To this end, we propose the Asymmetric Center Positioning Network (ACP-Net) to replace FPN, achieving accuracy and real-time text detection in complex scenarios. ACP-Net features an asymmetric feature structure with independent branches for global and local information, along with an adaptive weighted fusion module to capture long-range dependencies effectively. In addition, a text center positioning module enhances text feature understanding by learning feature centers. Comprehensive evaluations across various terminals confirmed ACP-Net's superior accuracy and speed.

关键词： Text Detection Real-Time Asymmetric Center Positioning Network

来源：评论

学校读者我要写书评

暂无评论

Long-term cardiovascular outcomes of biodegradable polymer drug eluting stents in patients with diabetes versus non-diabetes mellitus: a meta-analysis

引用

CARDIOVASCULAR DIABETOLOGY 2023年第1期22卷 1-10页

作者： Wang, Hong Zu, Quannan Tang, Hairong Lu, Ming Chen, Rongfa Yang, Zhiren Peoples Hosp Guangxi Zhuang Autonomous Reg Dept Cardiol Nanning 530021 Guangxi Peoples R China Tianjin Univ Coll Management & Econ Tianjin 300072 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

BackgroundToday, diabetes mellitus (DM) has become a worldwide concern. DM is a major risk factor for the development of cardiovascular diseases (CVD). Eligible patients with CVD are treated invasively by percutaneous coronary intervention (PCI) whereby a stent is implanted inside the coronary vessel with the particular lesion to allow sufficient blood flow. Newer scientific research have shown that even though associated with a lower rate of re-stenosis, first-generation drug eluting stents (DES) were associated with a higher rate of late stent thrombosis. Recently, newer stents, namely biodegradable polymer DES (BP-DES) have been developed to overcome the safety issues of earlier generation DES. In this analysis we aimed to systematically compare the long term (& GE;12 months) adverse cardiovascular outcomes observed in DM versus non-DM patients who were implanted with *** central, MEDLINE (Subset PubMed), EMBASE, Web of Science, http://*** and Google scholar were searched for relevant publications involving BP-DES in patients with DM versus non-DM and their associated adverse cardiovascular outcomes. The mean follow-up time period ranged from 12 to 120 months. Data analysis was carried out with the latest version of the RevMan software (version 5.4). Based on the Mantel-Haenszel test, risk ratios (RR) with 95% confidence intervals (CI) were calculated and used to represent the results following *** (7) studies with a total number of 10,246 participants were included in this analysis. Stents which were implanted during PCI were BP-DES. Participants were enrolled from the year 2006 to 2013. Our current results showed that in patients who were implanted with BP-DES, the risks of major adverse cardiac events (RR: 1.30, 95% CI: 1.18-1.43;P = 0.00001), myocardial infarction (RR: 1.48, 95% CI: 1.14-1.93;P = 0.003), all-cause mortality (RR: 1.70, 95% CI: 1.29-2.23;P = 0.0002), cardiac death (RR: 1.93, 95% CI: 1.28-2

关键词： Biodegradable polymer drug eluting stents Durable polymer drug eluting stents Percutaneous coronary intervention Diabetes mellitus Cardiovascular diseases Stent thrombosis Revascularization

来源：评论

学校读者我要写书评

暂无评论

Asynchronous fault detection for delayed semi-markov jump systems with mismatched mode-dependent nonlinearities

引用

INFORMATION SCIENCES 2022年 587卷 679-691页

作者： Ma, Chao Fu, Hang Wu, Wei Univ Sci & Technol Beijing Sch Mech Engn Beijing 100083 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

This paper deals with fault detection problem of delayed semi-Markov jump systems with disturbances. More specifically, the asynchronous phenomenon is taken into account between modes of linear and nonlinear dynamics. Accordingly, an efficient solution of fault detection is developed based on asynchronous mode-dependent fault filter with condi-tional probability. On the basis of constructing appropriate Lyapunov-Krasovskii functions, sufficient criteria are established such that H-infinity performance can be satisfied for filter error with residual signal. Furthermore, the devised filter gains are computed in terms of convex optimization. Eventually, the applicability of our proposed design is verified by an illustra-tive example. (C) 2021 Elsevier Inc. All rights reserved.

关键词： Asynchronous fault detection Semi-Markov jump systems Mismatched mode-dependent nonlinearities Time-varying delay

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：