检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Wang, Shuze Mei, Yunpeng Cao, Hongjie Yuan, Yetian Wang, Gang Sun, Jian Chen, Jie National Key Lab of Autonomous Intelligent Unmanned Systems Beijing Institute of Technology Beijing100081 China Department of Control Science and Engineering Harbin Institute of Technology Harbin150001 China

Imitation learning (IL) has proven effective for enabling robots to acquire visuomotor skills through expert demonstrations. However, traditional IL methods are limited by their reliance on high-quality, often scarce, expert data, and suffer from covariate shift. To address these challenges, recent advances in offline IL have incorporated suboptimal, unlabeled datasets into the training. In this paper, we propose a novel approach to enhance policy learning from mixed-quality offline datasets by leveraging task-relevant trajectory fragments and rich environmental dynamics. Specifically, we introduce a state-based search framework that stitches state-action pairs from imperfect demonstrations, generating more diverse and informative training trajectories. Experimental results on standard IL benchmarks and real-world robotic tasks showcase that our proposed method significantly improves both generalization and performance. Videos are available on https://***/sbr. Copyright © 2025, The Authors. All rights reserved.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

Interception of a Single Intruding Unmanned Aerial Vehicle by Multiple Missiles Using the Novel EA-MADDPG Training Algorithm

引用

DRONES 2024年第10期8卷 524-524页

作者： Cai, He Li, Xingsheng Zhang, Yibo Gao, Huanli South China Univ Technol Sch Automat Sci & Engn Guangzhou 510641 Peoples R China Minist Educ Key Lab Autonomous Syst & Networked Control Guangzhou 510641 Peoples R China Guangdong Engn Technol Res Ctr Unmanned Aerial Veh Guangzhou 510641 Peoples R China

This paper proposes an improved multi-agent deep deterministic policy gradient algorithm called the equal-reward and action-enhanced multi-agent deep deterministic policy gradient (EA-MADDPG) algorithm to solve the guidance problem of multiple missiles cooperating to intercept a single intruding UAV in three-dimensional space. The key innovations of EA-MADDPG include the implementation of the action filter with additional reward functions, optimal replay buffer, and equal reward setting. The additional reward functions and the action filter are set to enhance the exploration performance of the missiles during training. The optimal replay buffer and the equal reward setting are implemented to improve the utilization efficiency of exploration experiences obtained through the action filter. In order to prevent over-learning from certain experiences, a special storage mechanism is established, where experiences obtained through the action filter are stored only in the optimal replay buffer, while normal experiences are stored in both the optimal replay buffer and normal replay buffer. Meanwhile, we gradually reduce the selection probability of the action filter and the sampling ratio of the optimal replay buffer. Finally, comparative experiments show that the algorithm enhances the agents' exploration capabilities, allowing them to learn policies more quickly and stably, which enables multiple missiles to complete the interception task more rapidly and with a higher success rate.

关键词： MADDPG optimal replay buffer equal reward setting action filter

来源：评论

学校读者我要写书评

暂无评论

Drone Swarm Robust Cooperative Formation Pursuit through Relative Positioning in a Location Denial Environment

引用

DRONES 2024年第9期8卷 455-455页

作者： Gao, Huanli Zhang, Aixin Li, Wei Cai, He South China Univ Technol Sch Automat Sci & Engn Guangzhou 510641 Peoples R China Minist Educ Key Lab Autonomous Syst & Networked Control Guangzhou 510640 Peoples R China Guangdong Engn Technol Res Ctr Unmanned Aerial Veh Guangzhou 510640 Peoples R China

This paper considers the pursuit problem of a moving target by a swarm of drones through a flexible-configuration formation. The drones are modeled by second-order systems subject to uncertain damping ratios, whereas the moving target follows a polynomial-type trajectory whose coefficient vectors are fully unknown. Due to location denial, drones cannot obtain their absolute positions, but they can obtain their positions relative to other neighboring drones and the target. To achieve a robust formation pursuit, a robust cooperative control protocol is synthesized, which comprises three key components, namely, the pseudo drone position estimator, the pseudo target position estimator, and the local internal model control (IMC) law. The pseudo drone position estimator and the pseudo target position estimator aim to recover for each drone the position of itself and the target, respectively, but are subject to some common unknown constant bias in a distributed manner. By subtracting the pseudo target position from the pseudo drone position, each drone can acquire its position relative to the target, which facilitates the design of a local IMC law to fulfill formation pursuit in the presence of system parametric uncertainties. Both pure numerical simulation and hardware-in-the-loop (HIL) simulation are performed to verify the effectiveness of the proposed control protocol.

关键词： cooperative control drone swarm formation pursuit location denial environment internal model control

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence-based Fault Detection and Diagnosis: Towards Application in a Chemical Process

Artificial Intelligence-based Fault Detection and Diagnosis:...

引用

Fault Detection, Supervision and Safety for Technical Processes (SAFEPROCESS), CAA Symposium on

作者： Yiqi Liu Zhi Li Hongtian Chen Key Laboratory of Autonomous Systems and Networked Control Ministry of Education The School of Automation Science & Engineering South China University of Technology Guangzhou China Department of Automation Shanghai Jiao Tong University Shanghai China

As the chemical processes become more and more complicated, it is crucial but also difficult to detect and diagnose faults in the system than ever. With the development of machine learning algorithms and cloud computing, to monitor chemical processes completely with the help of big data become true. However, most machine learning methods suffer from unexplainable problem. By employing Explainable Artificial Intelligence(XAI) techniques, this paper applies two kinds of unsupervised machine learning methods, One-Class Support Vector Machine and Depth-based Isolation Forest Feature Importance, to detect and diagnosis faults in a chemical process. By combining two different fault explanation methodologies, accuracy and reliability of the fault diagnosis results can be achieved by the validation in a simulated continuous stirred tank reactor.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A High-Performance Sensor-Based control for Complex Maneuvers of Ducted Fan Unmanned Aerial Vehicles

A High-Performance Sensor-Based Control for Complex Maneuver...

引用

Chinese control and Decision Conference, CCDC

作者： Chengji Liu Hailong Pei Zihuan Cheng Ministry of Education Unmanned Aerial Vehicle Systems Eng. Tech. Research Center of Guangdong Key Lab. of Autonomous Systems and Networked Control South China University of Technology Guangzhou China

ISBN: (纸本)9781665478977

This paper presents a sensor-based approach for control of ducted fan UAVs. In the inner-most loop control design that suffers from complex aerodynamics, we employ an Incremental Nonlinear Dynamics Inversion (INDI) controller such that only a simplified vehicle dynamics is needed while ensuring the robustness and response time. To account for the highly coupling effects of the longitudinal dynamics, we propose a sensor-based Total Energy control System (TECS), in which we take advantage of the accelerators to obtain non-conservative forces, liberating the design from dynamics model. The effectiveness of the approach is validated through simulation using a real model of a small ducted fan UAV.

关键词： Couplings Fans control design Atmospheric modeling Aerodynamics autonomous aerial vehicles Robustness

来源：评论

学校读者我要写书评

暂无评论

Robust Data-Driven control Against Actuator FDI for Unknown Linear systems

Robust Data-Driven Control Against Actuator FDI for Unknown ...

引用

International Conference on control and Automation (ICCA)

作者： Wenjie Liu Jian Sun Fang Deng Gang Wang Jie Chen National Key Lab of Autonomous Intelligent Unmanned Systems School of Automation Beijing Institute of Technology Beijing China Beijing Institute of Technology Chongqing Innovation Center Chongqing China Department of Control Science and Engineering Tongji University Shanghai China National Key Lab of Autonomous Intelligent Unmanned Systems Beijing Institute of Technology Beijing China

ISBN: (数字)9798350354409

ISBN: (纸本)9798350354416

This paper designs a data-driven controller for unknown linear systems whose actuators suffer from false data injection (FDI) attacks, using only noisy input-state data. To achieve this objective, a general FDI attack model is introduced, which imposes constraints only on the switching frequency of attack channels and the magnitude of attack matrices. A time-varying state feedback control law is designed based on offline and online input-state data, which adapts to the channel switching of FDI attacks. This is achieved by solving a data-based semi-definite programs (SDPs) on-the-fly such that stabilizing the set of subsystems consistent with both offline clean data and online attack-corrupted data. It is shown that under mild conditions on the attack and the noise, the feasibility of the proposed SDP guarantees that the controller stabilizes the attack-corrupted system. A numerical example is presented to validate the effectiveness of the proposed method.

关键词： Linear systems Switched systems Actuators State feedback Switching frequency Switches control systems

来源：评论

学校读者我要写书评

暂无评论

Extended State Observer Based Fault-Tolerant Predictive control for a Four-Mecanum Wheels Mobile Robot

Extended State Observer Based Fault-Tolerant Predictive Cont...

引用

IEEE International Conference on Cyber Technology in Automation, control, and Intelligent systems

作者： Binghao Yang Dongliang Wang Ziling Wen Wu Wei Wenji Li Zhun Fan Key Lab of Digital Signal and Image Processing of Guangdong Province Shantou University Guangdong China School of Department of Electronic and Information Engineering Shantou University Guangdong China Key Laboratory of Autonomous Systems and Networked Control Ministry of Education Guangzhou Guangdong China School of Automation Science and Engineering South China University of Technology Guangzhou Guangdong China

ISBN: (数字)9798331506056

ISBN: (纸本)9798331506063

The application of unmanned vehicles in industrial cargo transportation is becoming increasingly widespread, particularly playing a significant role in transporting heavy-duty goods. However, when performing such tasks, whether in single-vehicle transportation or multi-vehicle collaborative transportation, the occurrence of wheel failures can potentially lead to serious safety accidents. Therefore, this paper proposes a fault-tolerant control scheme, establishing a kinematic model considering disturbances and failures, and adopts model predictive control for trajectory tracking. Additionally, an extended state observer is introduced to observe system states and counteract disturbances. To address potential failure issues, a controller reconstruction strategy is proposed. Finally, the effectiveness and superiority of the controller is validated through numerical simulation and comparative experiment.

关键词： Fault tolerance Trajectory tracking Fault tolerant systems Wheels Transportation Kinematics Predictive models Safety State estimation Predictive control

来源：评论

学校读者我要写书评

暂无评论

Estimation of velocity potential of water waves using a Luenberger-like observer

引用

Science China(Information Sciences) 2020年第12期63卷 139-152页

作者： Yang YU Hai-Long PEI Cheng-Zhong XU Key Laboratory of Autonomous Systems and Networked Control Ministry of EducationSouth China University of Technology Unmanned Aerial Vehicle Systems Engineering Technology Research Center of Guangzhou South China University of Technology LAGEPP University Claude Bernard-Lyon 1

We propose a Luenberger-like observer for a water wave system. The water wave dynamics are assumed to be governed by the linearized water wave equation(LWWE). Our proposed observer estimates the velocity potential of water waves by measuring only the surface wave elevation. The information of the water-wave velocity field is then extracted from the gradient of the velocity potential. It is shown that the estimation error of the observer converges exponentially to zero as time tends to infinity. Furthermore,we numerically solve the LWWE and observer equation by the finite difference method. The efficiency of our proposed numerical scheme and the performance of the observer are validated by numerical simulation results.

关键词： linearized water wave equation LWWE Luenberger-like observer numerical simulations

来源：评论

学校读者我要写书评

暂无评论

A Robust Path Planning of Messenger UAV for Air-Ground Coordination Under Road Network Constraints

A Robust Path Planning of Messenger UAV for Air-Ground Coord...

引用

IEEE International Conference on Robotics and Biomimetics

作者： Yuyang Wang Bin Xin Yulong Ding Zhen Yin Bin He Shanghai Research Institute for Intelligent Autonomous Systems Tongji University Shanghai China School of Automation Beijing Institute of Technology Beijing China National Key Lab of Autonomous Intelligent Unmanned Systems Beijing China Department of Control Science and Engineering Tongji University Shanghai China

ISBN: (数字)9798331509644

ISBN: (纸本)9798331509651

This paper addresses the path planning problem for unmanned aerial vehicle (UAV), where a UAV serves as a messenger to periodically traverse over road-constrained ground vehicles (GVs) to relay information. The GVs may not move on the road network with the velocities agreed with the UAV due to their movement uncertainties. The UAV path planning problem can be formulated as the Dynamic Dubins Traveling Salesman Problem with Uncertain Neighborhood (DDTSPUN). To address the uncertainty in GVs motion, we define robust neighborhoods and corridors and prove that the UAV visiting these areas can revisit GVs reliably, thus transforming DDTSPUN into a Revisit-time-constrained Dubins Traveling Salesman Problem with Neighborhood (RDTSPN). To address the RDTSPN, we propose an online heuristic path planning algorithm. This algorithm incorporates a gradient-based method for visiting robust neighborhoods and a sampling-based search strategy along robust corridors to obtain the Dubins paths of UAV that achieve the robust visit for each GV. Finally, computational experiments demonstrate its advantage over other benchmark algorithms in obtaining the shortest path satisfying UAV curvature constraints, and ensuring robust access to all GVs.

关键词： Uncertainty Roads Surveillance Transforms Traveling salesman problems Benchmark testing autonomous aerial vehicles Search problems Path planning Vehicle dynamics

来源：评论

学校读者我要写书评

暂无评论

引用

IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING 2022年第4期19卷 3942-3952页

作者： Sun, Cheng-Yuan Yin, Yi-Zhen Kang, Hao-Bo Ma, Hong-Jun Northeastern Univ Coll Informat Sci & Engn Shenyang 110819 Peoples R China Chinese Acad Sci Shenyang Inst Automat Shenyang 110169 Liaoning Peoples R China South China Univ Technol Sch Automat Sci & Engn Guangzhou 510641 Peoples R China Minist Educ Key Lab Autonomous Syst & Networked Control Unmanned Aerial Vehicle Syst Engn Technol Res Ctr Guangzhou 510640 Peoples R China

For nearly a decade, quality-related fault detection algorithms have been widely used in industrial systems. However, the majority of these detection strategies rely on static assumptions of the operating environment. In this paper, taking the time series of variables into consideration, a dynamic kernel entropy component regression (DKECR) framework is proposed to address the instability of quality-related fault detection due to the existing dynamic characteristics. Compared with the typical kernel entropy component analysis method, the proposed method constructs the relationship between process states and quality states to further interpret the direct effect on the product taken by the fault. In the proposed approach, process measurements are converted to a lower-dimensional subspace with a specific angular structure that is more comprehensive than traditional subspace approaches. In addition, the angular statistics and their relevant thresholds are exploited to enhance the quality-related fault detection performance. Finally, the proposed method will be compared with three methods by means of a numerical example and two industrial scenarios to demonstrate its practicality and effectiveness.

关键词： Fault detection Kernel Monitoring Heuristic algorithms Nonlinear dynamical systems Entropy Principal component analysis Dynamic feature quality-related fault detection KECA DKECR

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：