检索结果-内蒙古大学图书馆

PELS Students and Young Professionals Symposium (SYPS), IEEE

作者： Dingbang Huang Zhijian Fang Sheng Zhang Xuan Li Zihao Wei Liangwei Jin School of Automation China University of Geosciences Wuhan China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex SystemsWuhan China Wuhan China

With the outbreak of environmental problems and energy crisis, human beings are exploring new energy sources more and more deeply. As the installed capacity of energy storage devices increases and the coverage of distributed energy storage systems becomes more and more extensive, the power grid puts forward higher requirements on its fault ride-through capability. To address this problem, this paper investigates the short-circuit fault ride-through technology of grid-forming inverter systems and proposes a control scheme for switching between grid-forming and grid-following systems. The scheme can switch to grid-following control model when a fault occurs in the grid, and then switch back to grid-forming system when the short-circuit fault is repaired, thus ensuring the stable operation of the power system and controlling the current value during the short-circuit fault to prevent over-current situation. Finally, the effectiveness of the proposed control strategy is further verified by combining MATLAB/Simulink simulations and experiments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Human-AI Trust by Describing AI decision-Making Behavior

Enhancing Human-AI Trust by Describing AI Decision-Making Be...

引用

IEEE International Conference on Unmanned systems (ICUS)

作者： Zhouwei Lou Haikun Wei Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education School of Automation Southeast University Nanjing China

Air combat game is a highly complex and dynamic decision-making problem that is crucial for ensuring national security and improving combat efficiency. In recent years, artificial intelligence (AI) technologies such as deep reinforcement learning have made significant progress in the air combat game field, surpassing human experts' capabilities. However, the decision-making process of AI algorithms often lacks transparency and interpretability, resulting in low trust in them, which limits their promotion and application in practical scenarios. To enhance human-AI trust, this paper proposes a decision explanation method based on natural language generation. As the most direct means of information transmission, natural language can help people quickly understand the behavior and intent of AI algorithms. Taking a one-on-one air combat game as an experimental scenario, this paper constructs a combat dataset mapping temporal states to behavioral explanations and designs an attention-based Encoder-decoder architecture (AED) capable of generating natural language descriptions of current AI decision-making behavior based on a period of combat data. Experimental results show that AED can accurately describe the decision-making behavior of AI algorithms and help improve the level of human-AI trust.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Real-Time Visual-Inertial Monocular Odometry by Fusing Point and Line Features

A Real-Time Visual-Inertial Monocular Odometry by Fusing Poi...

引用

第40届中国控制会议

作者： Chengwei Li Liping Yan Yuanqing Xia Key Laboratory of Intelligent Control and Decision of Complex Systems School of Automation Beijing Institute of Technology

In this paper, a monocular visual-inertial odometry that utilize both point and line features is deduced. Compared with point features, line features provide more geometric information of the environment, which are more reliable in textureless scenes. However, extracting line segment features from the image are very time consuming, which will affect the real-time performance of the system. To deal with this problem, EDLines line segment detector is introduced to replace the LSD *** properties of lines are utilized to reject the mismatching of line segment feature. Pl ¨ucker coordinates and orthonormal representation of lines are used to represent 3 D lines. Afterwards, we optimize the state by minimizing a cost function consists of pre-integrated IMU residuals and visual feature re-projection residuals in a sliding window optimization framework. The proposed odometry was tested on the public datasets. The results demonstrate that the presented system can operate in real time with high accuracy.

关键词： visual-inertial odometry(VIO) point and line feature visual simultaneous localization and mapping(SLAM)

来源：评论

学校读者我要写书评

暂无评论

Data-Driven control for Nonlinear Multi-Agent systems Using Reinforcement Learning

Data-Driven Control for Nonlinear Multi-Agent Systems Using ...

引用

Youth Academic Annual Conference of Chinese Association of automation (YAC)

作者： Renzhi Liu Hongru Ren Hui Ma Hongyi Li Renquan Lu School of Automation Guangdong-Hong Kong Joint Laboratory for Intelligent Decision and Cooperative Control and Guangdong Provincial Key Laboratory for Intelligent Decision and Cooperative Control Guangdong University of Technology Guangzhou China School of Mathematics and Statistics Guangdong University of Technology Guangzhou China School of Electronic and Information Engineering and Chongqing Key Laboratory of Generic Technology and System of Service Robots Southwest University Chongqing China

ISBN: (数字)9798350379228

ISBN: (纸本)9798350390780

In this paper, a new reinforcement learning-based model-free adaptive control algorithm is introduced for discrete-time nonlinear multi-agent systems with unknown dynamics, while the equivalent dynamic linearization algorithm is applied to design the optimal controller. The strategy for Q-Learning and the actor-critic neural network are specifically redesigned to achieve consensus control in multi-agent systems. The proposed reinforcement learning algorithm can adjust the dynamic linearization parameters in real-time only based on input and output data. The stability of the closed-loop system is proven by Lyapunov theorem. Furthermore, the method’s effectiveness is verified by a numerical simulation.

关键词： Adaptation models Target tracking Q-learning Heuristic algorithms Numerical simulation Stability analysis Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Autonomous Tracking control for Four-Wheel Independent Steering Robot Based on Improved Pure Pursuit

引用

Journal of Beijing Institute of Technology 2020年第4期29卷 466-473页

作者： Jing Li Qingbin Wu Junzheng Wang Hui Qin Jiehao Li Key Laboratory of Intelligent Control and Decision of Complex Systems School of AutomationBeijing Institute of TechnologyBeijing 100081China Key Laboratory of Servo Motion System Drive and Control Ministry of Industry and Information TechnologySchool of AutomationBeijing Institute of TechnologyBeijing 100081China

Autonomous tracking control is one of the fundamental challenges in the field of robotic autonomous navigation,especially for future intelligent *** this paper,an improved pure pursuit control method is proposed for the path tracking control problem of a four-wheel independent steering *** on the analysis of the four-wheel independent steering model,the kinematic model and the steering geometry model of the robot are *** the path tracking control is realized by considering the correlation between the look-ahead distance and the velocity,as well as the lateral error between the robot and the reference *** experimental results demonstrate that the improved pure pursuit control method has the advantages of small steady-state error,fast response and strong robustness,which can effectively improve the accuracy of path tracking.

关键词： autonomous tracking control four-wheel independent steering robot pure pursuit lateral error

来源：评论

学校读者我要写书评

暂无评论

Online adaptive Q-learning method for fully cooperative linear quadratic dynamic games

引用

Science China(Information Sciences) 2019年第12期62卷 164-177页

作者： Xinxing LI Zhihong PENG Lei JIAO Lele XI Junqi CAI School of Automation Beijing Institute of Technology State Key Laboratory of Intelligent Control and Decision of Complex Systems

A model-based offline policy iteration(PI) algorithm and a model-free online Q-learning algorithm are proposed for solving fully cooperative linear quadratic dynamic games. The PI-based adaptive Q-learning method can learn the feedback Nash equilibrium online using the state samples generated by behavior policies, without sending inquiries to the system model. Unlike the existing Q-learning methods, this novel Q-learning algorithm executes both policy evaluation and policy improvement in an adaptive *** prove the convergence of the offline PI algorithm by proving its equivalence to Newton's method while solving the game algebraic Riccati equation(GARE). Furthermore, we prove that the proposed Q-learning method will converge to the Nash equilibrium under a small learning rate if the method satisfies certain persistence of excitation conditions, which can be easily met by suitable behavior policies. Our simulation results demonstrate the good performance of the proposed online adaptive Q-learning algorithm.

关键词： adaptive dynamic programming reinforcement learning Q-learning fully cooperative linear quadratic dynamic games policy iteration off-policy

来源：评论

学校读者我要写书评

暂无评论

intelligent control of Networked Flow Production Subject to Input Delay and Parameter Perturbation

Intelligent Control of Networked Flow Production Subject to ...

引用

Chinese control Conference (CCC)

作者： Liheng Wan Peiyuan Li Zuolin Deng Panshuo Li Guangdong Provincial Key Laboratory of Intelligent Decision and Cooperative Control School of Automation Guangdong University of Technology Guangzhou P.R. China

The flow production, which combines several manufacturing units and operates the periodic tasks, can be modelled as periodic piecewise linear systems. Based on it, the non-fragile control of networked periodic piecewise linear systems under input delay and parameter perturbation, is studied in this paper. The exponential stabilization conditions under input delay are proposed via Lyapunov-Krasovskii functional and free weighting matrices, which reduce the conservativeness of conditions. Furthermore, controller gain perturbation, and asynchronous switching due to input delay, are first investigated jointly for periodic piecewise linear systems. The non-fragile stabilizing controllers are designed for additive and multiplicative perturbation of controller gains, respectively. The controller gains can be obtained by iterative linear matrix inequality (ILMI) approach. Numerical examples are given to verify the proposed methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Position and attitude control of Quadrotor UAV based on a new sliding mode control strategy

Position and attitude control of Quadrotor UAV based on a ne...

引用

第42届中国控制会议

作者： Yinghua Wu Ancai Zhang Guangyuan Pan Yingxue Du Zhi Liu School of Automation and Electrical Engineering Linyi University Key Laboratory of Complex Systems and Intelligent Computing in Universities of Shandong Linyi University

A Quadrotor unmanned aerial vehicle(UAV) is a typical underactuated nonlinear mechanical system with six degrees of freedom(DOF) and four *** paper develops a new sliding mode control(SMC) strategy to solve the position and attitude control problem for this multi-DOF underactuated ***,the dynamic motion equation model of the Quadrotor UAV is established.S econd,the first and fourth inputs are designed by using the traditional SMC method and a novel Gaussian geometric function reaching *** then,we design the second and third inputs based on a hierarchical SMC *** the stability of sliding mode surfaces are analyzed using Lyapunov *** designed four sliding controllers guarantee the flight control objective of the Quadrotor UAV to be *** the Gaussian reaching law used in the design of controllers can effectively reduce the chattering phenomena in the sliding mode *** examples verify the effectiveness of our developed control strategy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Information Fusion of Topological Structure and Node Features in Graph Neural Network

Information Fusion of Topological Structure and Node Feature...

引用

第40届中国控制会议

作者： Hongwei Zhang Can Wang Yuanqing Xia Tijin Yan Key Laboratory of Intelligent Control and Decision of Complex Systems School of Automation Beijing Institute of Technology

Graph neural networks(GNNs) have shown great popularity and achieved promising performance on various graph-based tasks in the past years. However, there is little work that explores the information fusion mechanism, which plays an import role in GNNs. Besides, datasets in the real world often have noises, which make the information fusion difficult. In this paper, we give an information-theoretic explanation. Specifically, we focus on how the information from topological structures and node features fuses and how different information contributes to the downstream task. Furthermore, we propose a general framework named M-GCN to express the fusion process in GNNs. Graph embeddings and feature graph are introduced to extract the information from topological structure and node features separately in M-GCN. Extensive experiments are conducted on several benchmark datasets and experimental results show that our proposed models are more robust and outperform state-of-the-art methods.

关键词： Information Fusion Graph Neural Network Graph embedding

来源：评论

学校读者我要写书评

暂无评论

Non-cooperative Stochastic Target Encirclement by Anti-synchronization control via Range-only Measurement

arXiv

引用

arXiv 2025年

作者： Liu, Fen Yuan, Shenghai Meng, Wei Su, Rong Xie, Lihua Guangdong Provincial Key Laboratory of Intelligent Decision and Cooperative Control School of Automation Guangdong University of Technology Guangzhou510006 China School of Electrical and Electronic Engineering Nanyang Technological University Singapore639798 Singapore

This paper investigates the stochastic moving target encirclement problem in a realistic setting. In contrast to typical assumptions in related works, the target in our work is non-cooperative and capable of escaping the circle containment by boosting its speed to maximum for a short duration. Considering the extreme environment, such as GPS denial, weight limit, and lack of ground guidance, two agents can only rely on their onboard single-modality perception tools to measure the distances to the target. The distance measurement allows for creating a position estimator by providing a target position-dependent variable. Furthermore, the construction of the unique distributed anti-synchronization controller (DASC) can guarantee that the two agents track and encircle the target swiftly. The convergence of the estimator and controller is rigorously evaluated using the Lyapunov technique. A real-world UAV-based experiment is conducted to illustrate the performance of the proposed methodology in addition to a simulated Matlab numerical sample. Our video demonstration can be found in the URL https://***/JXu1gib99yQ. © 2025, CC BY.

关键词： Stochastic systems

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：