检索结果-内蒙古大学图书馆

learning for predictive control: A Dual Gaussian Process approach

AUTOMATICA 2025年 177卷

作者： Liu, Yuhan Wang, Pengyu Toth, Roland Eindhoven Univ Technol Dept Elect Engn Control Syst Grp Eindhoven Netherlands Korea Adv Inst Sci & Technol Dept Aerosp Engn Flight Dynam & Control Lab Daejeon South Korea Inst Comp Sci & Control Syst & Control Lab Budapest Hungary

An important issue in model-based control design is that an accurate dynamic model of the system is generally nonlinear, complex, and costly to obtain. This limits achievable control performance in practice. Gaussian Process (GP) based estimation of system models is an effective tool to learn unknown dynamics directly from input/output data. However, conventional GP-based control methods often ignore the computational cost associated with accumulating data during the operation of the system and how to handle forgetting in continuous adaption. In this paper, we present a novel Dual Gaussian Process (DGP) based Model Predictive control (MPC) strategy that enables efficient use of online learning based predictive control without the danger of catastrophic forgetting. The bio-inspired DGP structure is a combination of a long-term GP and a short-term GP, where the long-term GP is used to keep the learnt knowledge in memory and the short-term GP is employed to rapidly compensate unknown dynamics during online operation. A novel recursive online update strategy for the shortterm GP is proposed to successively improve the learnt model during online operation without a "dictionary"update and re-computation of the Gram matrix at each time step. Effectiveness of the proposed strategy is demonstrated via numerical simulations. (c) 2025 Published by Elsevier Ltd.

关键词： learning-based control Data-driven model Dual Gaussian process Model predictive control Machine learning

来源：评论

学校读者我要写书评

暂无评论

A learning-based Scheme for Safe Deployment of Tethered Space Robot

引用

IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS 2025年第2期61卷 2941-2955页

作者： Jin, Ao Zhang, Fan Shen, Ganghui Ma, Yifeng Huang, Panfeng Northwestern Polytech Univ Res Ctr Intelligent Robot Sch Automat Xian 710072 Peoples R China Shaanxi Prov Innovat Team Intelligent Robot Techno Xian 710699 Peoples R China

This work focuses on the problem of collision avoidance with space debris for large-scale deployment of a tethered space robot (TSR). To this end, a general scheme that contains offline training and online execution is presented for safe deployment of a TSR. Specifically, inspired by the contraction theory, a feedback controller is learned from data to guarantee the superior tracking performance in the offline phase. Furthermore, the "tube" where state of the TSR would stay within is optimized simultaneously. In the online execution phase, when the space debris are detected, the motion planner generates a nominal trajectory by considering safety constraints. Then, in the presence of disturbances, the feedback controller learned offline tracks this nominal trajectory safely without collisions. The proposed scheme allows for the comprehensive utilization of prior knowledge for designing the tracking controller in the offline phase, thereby enhancing the online tracking performance. Finally, the numerical simulations demonstrate effectiveness of the proposed framework.

关键词： Space vehicles Robots Collision avoidance Aerospace electronics Trajectory Space debris Tracking Aerospace and electronic systems Safety Space missions learning-based control tethered space robot (TSR) tethered system

来源：评论

学校读者我要写书评

暂无评论

Multi-USV cooperative target encirclement through learning-based distributed transferable policy and experimental validation

引用

OCEAN ENGINEERING 2025年 318卷

作者： Zhang, Chenming Zeng, Rijie Lin, Bin Zhang, Yibo Xie, Wei Zhang, Weidong Shanghai Jiao Tong Univ Dept Automat Shanghai 200240 Peoples R China Minist Educ Key Lab Syst Control & Informat Proc Shanghai 200240 Peoples R China

Coordinated strategies for unmanned surface vehicles (USVs) to encircle an escaping target is a key research focus in maritime operations. In this paper, we propose a distributed, transferable multi-agent reinforcement learning (MARL) algorithm to address this challenge. The algorithm achieves the target encirclement for multi-agent swarm based on limited observational information, while there are random obstacles in the scenario. A centralized training decentralized execution (CTDE) deep reinforcement learning (DRL) framework is introduced. Also, the framework facilitates transfer of policies to larger swarms. To balance individual and collective benefits, we propose a knowledge-embedded compound reward function. Nonlinear mapping terms are added to the reward function to meet the requirements of the encirclement task at different stages. Furthermore, to improve training effectiveness, we implement a parallel training method and a multi- agent policy-sharing (MAPS) mechanism for isomorphic agents. Multiple tests indicate the effectiveness of the proposed algorithm. We developed a framework for deploying the learning-based policies in real-world scenarios. The MARL-based algorithm proposed in this paper has been successfully deployed in an indoor pool.

关键词： Unmanned surface vehicles (USVs) Motional target encirclement learning-based control Real-time obstacle avoidance Maritime intelligent navigation

来源：评论

学校读者我要写书评

暂无评论

Adaptive Planning and control with Time-Varying Tire Models for Autonomous Racing Using Extreme learning Machine

Adaptive Planning and Control with Time-Varying Tire Models ...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Kalarial, Dvij Lin, Qin Dolan, John M. Carnegie Mellon Univ Robot Inst Pittsburgh PA 15213 USA Cleveland State Univ Comp Sci Dept Cleveland OH 44115 USA

ISBN: (纸本)9798350384581;9798350384574

Autonomous racing is a challenging problem, as the vehicle needs to operate at the friction or handling limits in order to achieve minimum lap times. Autonomous race cars require highly accurate perception, state estimation, planning, and control. Adding to this complexity is the need to accurately identify vehicle model parameters governing lateral tire slip effects, which can evolve over time due to factors such as tire wear and tear. Current approaches to this problem typically either propose offline model identification methods or rely on initial parameters within a narrow range (typically within 15-20% of the actual values). However, these approaches fall short in accounting for significant changes in tire models that can occur during actual races, particularly when pushing the vehicle to its handling limits. We present a unified framework that not only learns the tire model in real time from collected data but also adapts the model to environmental changes, even when the model parameters exhibit substantial deviations. The friction estimation, obtained as a byproduct from the learning results, facilitates the selection of the optimal racing line from a library for adaptive speed planning. We validate our approach through testing in simulators, encompassing a 1:43 scale race car and a full-size car, and also through experiments with a physical F1/10 autonomous race car.

关键词： learning-based control adaptive motion planning and control extreme learning machine autonomous racing

来源：评论

学校读者我要写书评

暂无评论

Coordination of Lateral Vehicle control Systems Using learning-based Strategies

引用

ENERGIES 2021年第5期14卷 1291-1291页

作者： Nemeth, Balazs Eotvos Lorand Res Network ELKH Inst Comp Sci & Control SZTAKI 13-17 Kende Utca H-1111 Budapest Hungary

The paper proposes a novel learning-based coordination strategy for lateral control systems of automated vehicles. The motivation of the research is to improve the performance level of the coordinated system compared to the conventional model-based reconfigurable solutions. During vehicle maneuvers, the coordinated control system provides torque vectoring and front-wheel steering angle in order to guarantee the various lateral dynamical performances. The performance specifications are guaranteed on two levels, i.e., primary performances are guaranteed by Linear Parameter Varying (LPV) controllers, while secondary performances (e.g., economy and comfort) are maintained by a reinforcement-learning-based (RL) controller. The coordination of the control systems is carried out by a supervisor. The effectiveness of the proposed coordinated control system is illustrated through high velocity vehicle maneuvers.

关键词： coordinated control design autonomous vehicles learning-based control

来源：评论

学校读者我要写书评

暂无评论

Switch-based Iterative learning control for Tracking Iteration Varying References 21st

Switch-Based Iterative Learning Control for Tracking Iterati...

引用

21st IFAC World Congress on Automatic control - Meeting Societal Challenges

作者： Balta, Efe C. Tilbury, Dawn M. Barton, Kira Univ Michigan Dept Mech Engn Ann Arbor MI 48109 USA

Iterative learning control (ILC) is a control strategy that improves the performance of repetitive systems by enabling near-perfect reference tracking. Iteration-invariant reference signals have been a fundamental assumption for most existing ILC developments. This assumption poses limitations on many applications of ILC where the iteration-varying reference is known to the controller a priori. This work presents a switch-based ILC scheme that combines the performance of standard ILC with guarantees on the error for switched reference signals. The proposed controller is formulated and its performance is analyzed. A simulation case study is provided at the end to illustrate the performance. Copyright (C) 2020 The Authors.

关键词： Repetitive systems iterative learning control (ILC) learning-based control

来源：评论

学校读者我要写书评

暂无评论

Toward Data-Driven Optimal control: A Systematic Review of the Landscape

引用

IEEE ACCESS 2022年 10卷 32190-32212页

作者： Prag, Krupa Woolway, Matthew Celik, Turgay Univ Witwatersrand Sch Comp Sci & Appl Math ZA-200 Johannesburg South Africa Univ Johannesburg Fac Engn & Built Environm ZA-2006 Johannesburg South Africa Univ Witwatersrand Sch Elect & Informat Engn ZA-2000 Johannesburg South Africa Univ Witwatersrand Wits Inst Data Sci ZA-2000 Johannesburg South Africa

This literature review extends and contributes to research on the development of data-driven optimal control. Previous reviews have documented the development of model-based and data-driven control in isolation and have not critically reviewed reinforcement learning approaches for adaptive data-driven optimal control frameworks. The presented review discusses the development of model-based to model-free adaptive controllers, highlighting the use of data in control frameworks. In data-driven control frameworks, reinforcement learning methods may be used to derive the optimal policy for dynamical systems. Attractive characteristics of these methods include not requiring a mathematical model of complex systems, their inherent adaptive control capabilities, being an unsupervised learning technique and their decision-making abilities, which are both an advantage and motivation behind this approach. This review considers previous reviews on these topics, including recent work on data-driven control methods. In addition, this review shows the use of data to derive system dynamics, determine the control policy using feedback information, and tune fixed controllers. Furthermore, the review summarises various data-driven methods and their corresponding characteristics. Finally, the review provides a taxonomy, a timeline and a concise narrative of the development of model-based to model-free data-driven adaptive control and underlines the limitations of these techniques due to the lack of theoretical analysis. Areas of further work include theoretical analysis on stability and robustness for data-driven control systems, explainability of black-box policy learning techniques and an evaluation of the impact of the extension of system simulators to include digital twins.

关键词： control systems Mathematical models Adaptation models Data models Adaptive control Optimal control Tuning Data-driven control adaptive control model-free model-based model predictive control optimal control learning-based control systematic review

来源：评论

学校读者我要写书评

暂无评论

Collaborative twin actors framework using deep deterministic policy gradient for flexible batch processes

引用

NEURAL NETWORKS 2025年 188卷

作者： Wang, Xindong Liu, Zidong Chen, Junghui China Univ Petr East China Coll New Energy Qingdao 266580 Shandong Peoples R China Chung Yuan Christian Univ R&D Ctr Membrane Technol Taoyuan 32032 Taiwan Chung Yuan Christian Univ Dept Chem Engn Taoyuan 32032 Taiwan

Due to its inherent efficiency in the process industry for achieving desired products, batch processing is widely acknowledged for its repetitive nature. Batch-to-batch learning control has traditionally been esteemed as a robust strategy for batch process control. However, the presence of flexible operating conditions in practical batch systems often leads to a lack of prior learning information, hindering learning control from optimizing performance. This article presents a novel approach to flexible batch process control using deep reinforcement learning (DRL) with twin actors. Specifically, a collaborative twin-actor-based deep deterministic policy gradient (CTA-DDPG) method is proposed to generate control policies and ensure safe operation across varying trial lengths and initial conditions. This approach involves the sequential construction of two sets of actor-critic networks with a shared critic. The first set explores meta-policy during an offline stage, while the second set enhances control performance using a supplementary agent during an online stage. To ensure robust policy transfer and efficient learning, a policy integration mechanism and a spatial-temporal experience replay strategy are incorporated, facilitating transfer stability and learning efficiency. The performance of CTA-DDPG is evaluated using both numerical examples and nonlinear injection molding process for tracking control. The results demonstrate the effectiveness and superiority of the proposed method in achieving desired control outcomes.

关键词： Collaborative actors Deep reinforcement learning Flexible batch process learning-based control

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement learning for Intelligent Energy Management Systems of Hybrid-Electric Powertrains: Recent Advances, Open Issues, and Prospects

引用

IEEE TRANSACTIONS ON TRANSPORTATION ELECTRIFICATION 2024年第4期10卷 9877-9903页

作者： Li, Yuecheng He, Hongwen Khajepour, Amir Chen, Yong Huo, Weiwei Wang, Hao Beijing Informat Sci & Technol Univ Sch Mech & Elect Engn Beijing 100192 Peoples R China Beijing Inst Technol Natl Engn Res Ctr Elect Vehicles Beijing 100081 Peoples R China Univ Waterloo Dept Mech & Mechatron Engn Mechatron Vehicle Syst Lab Waterloo ON N2L 3G1 Canada McMaster Univ McMaster Automot Resource Ctr Dept Mech Engn Hamilton ON L8P 0A6 Canada

The hybrid-electric powertrain presents an immediate solution to energy and environmental challenges encountered within the realm of transportation. Targeting the optimization of hybrid-electric powertrains, deep reinforcement learning (DRL) has been intensively and increasingly investigated to develop intelligent energy management systems in the context of augmented vehicular and traffic information. After a brief introduction to the Markov decision process and DRL, this article presents a comprehensive survey of the recent advancements in DRL-based energy management. The survey categorizes the progress based on the various roles that DRL plays in energy management systems, highlighting the flexibility and advantages of integrating DRL for achieving energy efficiency, safety, and reliable performance. Furthermore, the study concludes with an analysis of open issues and future prospects, including the learning and application of DRL-based energy management strategies, the development of novel DRL algorithms, and the integration of DRL-based energy management in intelligent and sustainable transportation contexts.

关键词： Energy management Mechanical power transmission Transportation Reviews Batteries Fuel cells Energy management systems Deep reinforcement learning (DRL) energy management hybrid-electric powertrain learning-based control real-world deployment

来源：评论

学校读者我要写书评

暂无评论

Regret Analysis of learning-based MPC With Partially Unknown Cost Function

引用

IEEE TRANSACTIONS ON AUTOMATIC control 2024年第5期69卷 3246-3253页

作者： Dogan, Ilgin Shen, Zuo-Jun Max Aswani, Anil Univ Calif Berkeley Ind Engn & Operat Res Berkeley CA 94720 USA Univ Hong Kong Fac Engn Hong Kong Peoples R China Univ Hong Kong Fac Business & Econ Hong Kong Peoples R China

The exploration-exploitation tradeoff is an inherent challenge in data-driven adaptive control. Though this tradeoff has been studied for multiarmed bandits (MABs) and reinforcement learning for linear systems, it is less well studied for learning-based control of nonlinear systems. A significant theoretical challenge in the nonlinear setting is that there is no explicit characterization of an optimal controller for a given set of cost and system parameters. We propose the use of a finite-horizon oracle controller with full knowledge of parameters as a reasonable surrogate to an optimal controller. This allows us to develop policies in the context of learning-based model-predictive control (MPC) and conduct a control-theoretic analysis using techniques from MPC and optimization theory to show that these policies achieve low regret with respect to this finite-horizon oracle. Our simulations exhibit the low regret of our policy on a heating, ventilation, and air-conditioning model with partially unknown cost function.

关键词： Cost function Costs Linear systems HVAC control systems Adaptation models Ventilation learning-based control model-predictive control (MPC) nonmyopic exploitation restless bandits

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：