检索结果-内蒙古大学图书馆

36th Chinese control and Decision conference (CCDC)

作者： Deng, Zhengqi Huo, Xin Du, Qinlong Liu, Qingquan Harbin Inst Technol Control & Simulat Ctr Harbin 150080 Peoples R China

ISBN: (纸本)9798350387780;9798350387797

Motion control systems are widely used in many fields of industry. Conventional control schemes are highly dependent on the system model to be designed. The performance of design would be greatly reduced, when the system exists unknown disturbances or uncertainty. Therefore, some scholars pointed out that the dependency on the system models can be eliminated by data-driven design schemes. In this paper, the reinforcement learning-based methods are included, which appeal to attentions gradually. The disturbances rejection problem for motion control systems is studied based on reinforcement learning. Considering the continuity of state space and action space, a method based on deep reinforcement learning algorithm is proposed to reject the periodic disturbances. Proposed deep deterministic policy gradient (DDPG) and twin delayed deep deterministic policy gradient (TD3) based algorithms are compared in simulation. The simulation results show that the periodic disturbances of the motion control systems can be rejected effectively with the proposed reinforcement learning controller.

关键词： Motion control systems data-driven control Reinforcement learning (RL) Deep deterministic policy gradient (DDPG) Twin delayed deep deterministic policy gradient (TD3)

来源：评论

学校读者我要写书评

暂无评论

Parameter optimization design of MFAC based on Reinforcement learning 12

Parameter optimization design of MFAC based on Reinforcement...

引用

ieee 12th data driven control and learning systems conference (DDCLS)

作者： Liu, Shida Jia, Xiongbo Ji, Honghai Fan, Lingling North China Univ Technol Sch Elect & Control Engn Beijing 100000 Peoples R China Beijing Informat Sci & Technol Univ Sch Automat Beijing 100192 Peoples R China

ISBN: (纸本)9798350321050

In this paper, we focus on parameter optimization for model-free adaptive control, which is currently lacking. Therefore, a novel data-driven model-free adaptive control method based on Reinforcement learning (RL-MFAC) is proposed for a class of dis-crete-time single-input and single-output nonlinear systems. In RL-MFAC, a dynamic linearization method is adopted, and the concept of pseudo-partial derivative (PPD) is introduced to design the controller. Moreover, the reward and punishment mech-anism of Reinforcement learning (RL) was used to optimize the parameters of MFAC in the controller design, such that the controller not only has good robustness, but also can solve the problem that MFAC needs to reset the optimal parameters on different control objects. The feature of the RL-MFAC is that the self-learning ability of RL is used to optimize the parameters of MFAC controller, and only the input/output (I/O) measurement data of the system is used. Furthermore, in the Python envi-ronment, two different nonlinear systems are used as objects for numerical simulation. The simulation results show that the performance of the MFAC controller is significantly improved in terms of overshoot and vibration prevention during regulation after the parameters are optimized by RL which proves the effectiveness of the proposed method.

关键词： Reinforcement learning data-driven control Parameter Optimization

来源：评论

学校读者我要写书评

暂无评论

A data-driven Image-Based Visual Servoing Scheme for Redundant Manipulators With Unknown Structure and Singularity Solution

引用

ieee TRANSACTIONS ON systems MAN CYBERNETICS-systems 2024年第10期54卷 6230-6241页

作者： Xie, Zhengtai Zheng, Yu Jin, Long Lanzhou Univ Sch Informat Sci & Engn Lanzhou 730000 Peoples R China Chinese Acad Sci Shenyang Inst Automat State Key Lab Robot Shenyang 110016 Peoples R China Tencent Tencent Robot 10 Shenzhen 518057 Guangdong Peoples R China

For the image-based visual servoing (IBVS) of a manipulator with an unknown structure, the unavailability of the robot Jacobian matrix impedes the accurate control of the manipulator. To solve this issue, this article proposes a data-driven IBVS (DDIBVS) scheme combining model-free learning, matrix inversion estimation, feature tracking, and joint limits. On the one hand, a data-driven learning algorithm is designed, which enables an estimated end-effector velocity to approach the real one and outputs an estimated robot Jacobian matrix. On the other hand, we consider the desired velocity information of the visual feature to improve the tracking accuracy and design an auxiliary parameter to estimate the inversion operation and address the singularity problem. On this basis, a neural dynamic controller (NDC) is developed, which possesses learning, estimation, and control capabilities. Subsequently, the effectiveness, practicability, and superiority of the proposed method are evaluated through simulations and experiments conducted on a 7-degree-of-freedom (DOF) manipulator for visual servoing tasks.

关键词： Robots Manipulators Cameras Visual servoing Jacobian matrices Robot kinematics Visualization Image-based visual servoing (IBVS) inversion estimation singularity solution unknown structure

来源：评论

学校读者我要写书评

暂无评论

data-driven Spatial Adaptive Terminal Iterative learning Predictive control for Automatic Stop control of Subway Train With Actuator Saturation

引用

ieee TRANSACTIONS ON INTELLIGENT TRANSPORTATION systems 2023年第10期24卷 11453-11465页

作者： Zheng, Jianmin Hou, Zhongsheng Beijing Jiaotong Univ Sch Elect & Informat Engn Adv Control Syst Lab Beijing 100044 Peoples R China Qingdao Univ Sch Automat Qingdao 266071 Peoples R China

A data-driven spatial adaptive terminal iterative learning predictive control (SATILPC) scheme with actuator saturation is proposed for automatic stop control of the subway train. Considering the outstanding repetitive operation pattern and the unavailable accurate model of a subway train, the unknown train dynamics is firstly transformed into a nonlinear discrete form in spatial domain via the spatial differential operator. Since the train automatic stop control (TASC) only concentrates on the tracking performances of the terminal position and terminal speed, an iterative dynamic linearization approach considering the terminal operation point is devised to formulate the relationship of the train input and output (I/O) into a linear affine form. Then, a terminal iterative learning prediction mechanism is introduced to reconstruct the developed train data model to forecast the future train behaviors through rolling optimization process. As a result, by removing the constraints on the unimportant points, the optimal control input (braking force) can be obtained by minimizing the objective function through terminal I/O data. Further, actuator saturation is considered to address the passenger comfort and the reliable operation of the train. The proposed SATILPC approach is a pure data-driven iterative learning control scheme and no model information is involved in the whole design processes. By utilizing a newly space-based contraction mapping method, the convergence of the proposed approach is strictly proved. Finally, the simulation results further demonstrate the feasibility of the proposed algorithm.

关键词： Public transportation Resistance Force data models Aerodynamics Spatial databases Iterative learning control data-driven control spatial adaptive iterative learning control terminal iterative learning control predictive control train automatic stop control

来源：评论

学校读者我要写书评

暂无评论

Preassigned Time Prescribed Performance Tracking control for High-Order Nonlinear systems with Time-Varying Powers 13

Preassigned Time Prescribed Performance Tracking Control for...

引用

13th ieee data driven control and learning systems conference, DDCLS 2024

作者： Tian, Wei Jiang, Yan School of Electrical Engineering Guangxi University Nanning China

ISBN: (纸本)9798350361674

This paper studies prescribed performance control of high-order nonlinear systems with unknown time-varying pow-ers. A state feedback control is designed to guarantee the prescribed tracking performance as the power of the systems are unknown time-varying functions and the nonlinearities are unknown. The tracking error between output and reference signal can converge to a predefined region in settling time. The effectiveness of the proposed scheme is verified by an example. © 2024 ieee.

关键词： State feedback

来源：评论

学校读者我要写书评

暂无评论

Group Consensus for Second-order Linear Multi-agent systems with Intermittent control 12

Group Consensus for Second-order Linear Multi-agent Systems ...

引用

ieee 12th data driven control and learning systems conference (DDCLS)

作者： Wu, Zhaoqin Li, Weixun Du, Xiangyang Xiao, Jingyu Zhang, Limin Tianjin Univ Technol & Educ Coll Sci Tianjin 300222 Peoples R China Zhongyuan Univ Technol Sch Elect & Informat Engn Zhengzhou 450007 Peoples R China

ISBN: (纸本)9798350321050

This paper focused on the tracking group consensus problem in a second-order multi-agent system, which is based on a multigroup network structure under the constraint of non-periodic intermittent communication. We proposed a new intermittent consensus protocol and performed a convergence analysis using Lyapunov stability theory and algebraic graph theory. The convergence analysis mainly adopts two assumptions on which the protocol relies, which are that the communication interval is time-varying and the inter-group relations. Based on these assumptions, sufficient conditions for achieving group consensus in a second-order multi-agent system with non-periodic intermittent communication are derived. To verify the conclusions drawn from the mathematical analysis, the paper finally used MATLAB to perform numerical simulations to verify the validity and correctness of the results.

关键词： Multi-agent systems group consensus intermittent communication leader-following control

来源：评论

学校读者我要写书评

暂无评论

The Input-Mapping-Based Online learning Sliding Mode control Strategy With Low Computational Complexity

引用

ieee TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING 2025年 22卷 7670-7678页

作者： Yu, Yaru Ma, Aoyun Li, Dewei Xi, Yugeng Gao, Furong Shanghai Jiao Tong Univ Dept Automat Shanghai 200240 Peoples R China Shanghai Jiao Tong Univ Key Lab Syst Control & Informat Proc Minist Educ China Shanghai 200240 Peoples R China Hong Kong Univ Sci & Technol Dept Chem & Biol Engn Hong Kong Peoples R China

The data-driven sliding mode control (SMC) method proves to be highly effective in addressing uncertainties and enhancing system performance. In our previous work, we implemented a co-design approach based on an input-mapping data-driven technique, which effectively improves the convergence rate through historical data compensation. However, this approach increases computational complexity in multi-input and multi-output (MIMO) systems due to the dependency of the number of online optimization variables on system dimensions. To improve applicability, this paper introduces a novel input-mapping-based online learning SMC strategy with low computational complexity. First, a new sliding mode surface is established through online convex combination of pre-designed offline surfaces. Then, an input-mapping-based online learning sliding mode control (IML-SMC) strategy is designed, utilizing a reaching law with adaptively adjusted convergence and switching coefficients to minimize chattering. The input-mapping technique employs the mapping relationship between historical input and output data for predicting future system dynamics. Accordingly, an optimization problem is formulated to learn from the past dynamics of the uncertain system online, thereby enhancing system performance. The optimization problem in this paper features fewer variables and is independent of system dimension. Additionally, the stability of the proposed method is theoretically validated, and the advantages are demonstrated through a MIMO system. Note to Practitioners-The design of control strategies that reduce the impact of mismatches between practical systems and models on system performance, while also ensuring applicability, is crucial. To address this issue, this paper proposes a low-complexity IML-SMC strategy. This strategy uses historical real input-output information and the mapping relationship with future dynamics to compensate for the impact of unknown dynamics and improve the system's conv

关键词： Computational complexity Optimization Uncertainty Convergence Sliding mode control System performance Robustness MIMO communication Computational modeling Switches Sliding mode control (SMC) input-mapping technique convex combined sliding mode surface low computational complexity

来源：评论

学校读者我要写书评

暂无评论

Reinforcement learning-driven Adaptive Prefetch Aggressiveness control for Enhanced Performance in Parallel System Architectures

引用

ieee TRANSACTIONS ON PARALLEL AND DISTRIBUTED systems 2025年第5期36卷 977-993页

作者： Yang, Huijing Fang, Juan Hou, Yumin Su, Xing Xiong, Neal N. Beijing Univ Technol Coll Comp Sci Beijing 100124 Peoples R China Sul Ross State Univ Dept Comp Math & Phys Sci Alpine TX 79830 USA

In modern parallel system architectures, prefetchers are essential to mitigating the performance challenges posed by long memory access latencies. These architectures rely heavily on efficient memory access patterns to maximize system throughput and resource utilization. Prefetch aggressiveness is a central parameter in managing these access patterns;although increased prefetch aggressiveness can enhance performance for certain applications, it often risks causing cache pollution and bandwidth contention, leading to significant performance degradation in other workloads. While many existing prefetchers rely on static or simple built-in aggressiveness controllers, a more flexible, adaptive approach based on system-level feedback is essential to achieving optimal performance across parallel computing environments. In this paper, we introduce an Adaptive Prefetch Aggressiveness control (APAC) framework that leverages Reinforcement learning (RL) to dynamically manage prefetch aggressiveness in parallel system architectures. The APAC controller operates as an RL agent, which optimizes prefetch aggressiveness by dynamically responding to system feedback on prefetch accuracy, timeliness, and cache pollution. The agent receives a reward signal that reflects the impact of each adjustment on both performance and memory bandwidth, learning to adapt its control strategy based on workload characteristics. This data-driven adaptability makes APAC particularly well-suited for parallel architectures, where efficient resource management across cores is essential to scaling system performance. Our evaluation with the ChampSim simulator demonstrates that APAC effectively adapts to diverse workloads and system configurations, achieving performance gains of 6.73$\%$% in multi-core systems compared to traditional Feedback Directed Prefetching (FDP). By improving memory bandwidth utilization, reducing cache pollution, and minimizing inter-core interference, APAC significantly enhances pre

关键词： Prefetching systems architecture Bandwidth Pollution Accuracy System performance Real-time systems Random access memory Resource management Adaptive systems data prefetchers memory bandwidth prefetcher aggressiveness controller parallel system architectures reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Survey on Path Planning for Mobile Robot systems 12

A Survey on Path Planning for Mobile Robot Systems

引用

ieee 12th data driven control and learning systems conference (DDCLS)

作者： Gao, Hejia Liu, Dongliang Hu, Juqi J. Anhui Univ Sch Artificial Intelligence Hefei 230601 Peoples R China

ISBN: (纸本)9798350321050

During the past three decades, it is witnessed that a lot of intense interests and quick advancements have been poured down to the field of robot vehicles. Multiple types of robots, like sweeping robots, greeting robots and robotic toys have become more and more common in people's daily life. As a core part of robot technology, path planning is to find a fast and safe route from the initial position to the target destination. Motivated by making convenience for scholars who are ambitious to study the path planning technologies, this paper has conducted a round review on this topic. Throughout this paper, the path planning technologies of robot vehicles have been divided into three categories, namely, traditional, intelligent and other approaches. After the main concerns of path planning are concluded for the mobile robot vehicles, the future research directions are subsequently discussed.

关键词： Mobile robots Autonomous vehicles Path planning Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

ESO-Based data driven Set-Point learning control for Nonlinear batch Processes with PD-Type Feedback control Structure Subject to Nonrepetitive Uncertainties* 13

ESO-Based Data Driven Set-Point Learning Control for Nonline...

引用

13th ieee data driven control and learning systems conference, DDCLS 2024

作者： Ahmad, Naseem Hao, Shoulin Liu, Tao Gong, Yihui Zhang, Jiyan Wang, Haixia Zhu, Yong Dalian University of Technology Key Lab. of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education Dalian116024 China Institute of Advanced Control Technology Dalian University of Technology Dalian116024 China School of Biomedical Engineering Dalian University of Technology Dalian116024 China

ISBN: (纸本)9798350361674

In this paper, an extended state observer (ESO) based data-driven set-point learning control (DDSPLC) scheme is proposed for nonlinear batch processes configured with an inherent PD-type control loop, so as to actively suppress the adverse effect of nonrepetitive external disturbances and nonidentical initial resetting conditions, by only utilizing the available process input/output data. The controlled process is firstly reformulated as an iterative dynamic linearization data model (IDLDM) with an extra generalized disturbance, where the unknown pseudo partial derivative and the generalized disturbance are, respectively, estimated by a projection-like algorithm and iterative ESO along the batch direction. By virtue of the estimated PPD and generalized disturbance, a set-point learning updating law with adaptive learning gain is then developed to optimize the tracking performance from batch-to-batch, by tuning the set-point command of the closed-loop PD-type control. Robust convergence analysis for the established closed-loop learning system is analyzed rigorously. The effectiveness and superiority of the proposed scheme are verified by an illustrative example. © 2024 ieee.

关键词： State estimation

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：