检索结果-内蒙古大学图书馆

Targets capture by distributed active swarms via bio-inspired reinforcement learning

Science China(Physics,Mechanics & Astronomy) 2025年第1期68卷 206-217页

作者： Kun Xu Yue Li Jun Sun Shuyuan Du Xinpeng Di Yuguang Yang Bo Li Institute of Biomechanics and Medical Engineering Applied Mechanics LaboratoryDepartment of Engineering MechanicsTsinghua UniversityBeijing 100084China Institute of Nuclear and New Energy Technology Tsinghua UniversityBeijing 100084China Shanghai Aerospace Control Technology Institute Shanghai 201109China Shanghai Key Laboratory of Aerospace Intelligent Control Technology Shanghai 201109China College of Automation Engineering Nanjing University of Aeronautics and AstronauticsNanjing 210016China

Natural swarms arranged from cells to herds are usually decentralized but display intriguing collective intelligence in coordinating individuals across large scales to efficiently achieve their common *** from nature may provide new strategies for controlling collective dynamics of synthetic swarms to accomplish specific ***,we present a bioinspired computational framework that steers distributed active swarms to collectively capture and merge targets via reinforcement *** exploit collective milling structures of natural herds to cage the targets,and adopt a switching control policy inspired by sperms’chiral dynamics to optimize the trajectories of individuals,through which the active swarms can selforganize to enclose single or multiple distant targets in a dynamical,adaptive and scalable *** exists a critical swarm size,beyond which the excessive competition between agents would generate large mechanical forces,leading to capture instability but enabling the transition from short-distance to long-distance merging capture of multiple *** work provides physical insights into distributed active swarms and could offer a multilevel,decentralized strategy toward controlling swarm robotics in wide applications such as bio-medical devices,machine immunity,and target clearance.

关键词： swarm intelligence robotics multi-tasks artificial intelligence bionics

来源：评论

学校读者我要写书评

暂无评论

An Optimal control-Based Distributed Reinforcement Learning Framework for A Class of Non-Convex Objective Functionals of the Multi-Agent Network

引用

IEEE/CAA Journal of Automatica Sinica 2023年第11期10卷 2081-2093页

作者： Zhe Chen Ning Li Department of Automation Shanghai Jiao Tong UniversityShanghai 200240 Key Laboratory of System Control and Information Processing Ministry of Education of ChinaShanghai 200240 Shanghai Engineering Research Center of Intelligent Control and Management Shanghai 200240China Department of Automation Tsinghua UniversityBeijing 100084China IEEE

This paper studies a novel distributed optimization problem that aims to minimize the sum of the non-convex objective functionals of the multi-agent network under privacy protection, which means that the local objective of each agent is unknown to others. The above problem involves complexity simultaneously in the time and space aspects. Yet existing works about distributed optimization mainly consider privacy protection in the space aspect where the decision variable is a vector with finite dimensions. In contrast, when the time aspect is considered in this paper, the decision variable is a continuous function concerning time. Hence, the minimization of the overall functional belongs to the calculus of variations. Traditional works usually aim to seek the optimal decision function. Due to privacy protection and non-convexity, the Euler-Lagrange equation of the proposed problem is a complicated partial differential ***, we seek the optimal decision derivative function rather than the decision function. This manner can be regarded as seeking the control input for an optimal control problem, for which we propose a centralized reinforcement learning(RL) framework. In the space aspect, we further present a distributed reinforcement learning framework to deal with the impact of privacy protection. Finally, rigorous theoretical analysis and simulation validate the effectiveness of our framework.

关键词： Distributed optimization multi-agent optimal control reinforcement learning(RL)

来源：评论

学校读者我要写书评

暂无评论

Aerial refueling scheduling of multi-receiver and multi-tanker under spatial-temporal constraints for forest firefighting

引用

Chinese Journal of Aeronautics 2024年第5期37卷 71-91,I0001页

作者： Jing HUANG Jiaqi XING Jinrui REN Quan QUAN Youmin ZHANG Department of Information and Control Engineering Xi’an University of TechnologyXi’an 710048China Jiujiang Measuring Test Technology Research Institute Jiujiang 332000China School of Automation Science and Electrical Engineering Beihang UniversityBeijing 100191China School of Automation Xi’an University of Posts&TelecommunicationsShaanxiXi’an 710121China Department of Mechanical Industrial and Aerospace EngineeringConcordia UniversityMontreal H3G 1M8Canada

Forest fires pose a significant threat to human life and property,so the utilization of unmanned aircraft systems provides new ways for forest *** the constrained load capacities of these aircraft,aerial refueling becomes crucial to extend their operational time and *** order to address the complexities of firefighting missions involving multi-receiver and multi-tanker deployed from various airports,first,a fuel consumption calculation model for aerial refueling scheduling is established based on the receiver ***,two distinct methods,including an integrated one and a decomposed one,are designed to address the challenges of establishing refueling airspace and allocating tasks for *** methods aim to optimize total fuel consumption of the receivers and tankers within the aerial refueling scheduling *** optimization problem is established as nonlinear optimization models along with *** integrated method seamlessly combines refueling rendezvous point scheduling and tanker task allocation into unified *** has a complete solution space and excels in optimizing total fuel *** decomposed method,through the separation of rendezvous point scheduling and task allocation,achieves a reduced computational ***,this comes at the cost of sacrificing optimality by excluding specific feasible ***,numerical simulations are carried out to verify the feasibility and effectiveness of the proposed *** simulations yield insights crucial for the practical engineering application of both the integrated and decomposed methods in real-world *** comprehensive approach aims to enhance the efficiency of forest firefighting operations,mitigating the risks posed by forest fires to human life and property.

关键词： Aerial refueling Scheduling Planning Spatial-temporal constraint Firefighting

来源：评论

学校读者我要写书评

暂无评论

An Improved Method for Approximating the Infinite-Horizon Value Function of the Discrete-Time Switched LQR Problem

引用

Journal of Systems Science & Complexity 2024年第1期37卷 22-39页

作者： HOU Tan LI Yuanlong LIN Zongli Department of Automation Shanghai Jiao Tong UniversityShanghai 200240China Key Laboratory of System Control and Information Processing Ministry of Education of ChinaShanghai 200240China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai 200240China Charles L.Brown Department of Electrical and Computer Engineering University of VirginiaCharlottesvilleVA 22904-4743USA

This paper considers the problem of approximating the infinite-horizon value function of the discrete-time switched LQR *** particular,the authors propose a new value iteration method to generate a sequence of monotonically decreasing functions that converges exponentially to the value *** method facilitates us to use coarse approximations resulting from faster but less accurate algorithms for further value iteration,and thus,the proposed approach is capable of achieving a better approximation for a given computation time compared with the existing *** numerical examples are presented in this paper to illustrate the effectiveness of the proposed method.

关键词： Optimal control switched linear systems switched LQR problem.

来源：评论

学校读者我要写书评

暂无评论

Dynamic Programming vs Q-learning for Feedback Motion Planning of Manipulators 5

Dynamic Programming vs Q-learning for Feedback Motion Planni...

引用

5th International Congress on Human-Computer Interaction, Optimization and Robotic Applications, HORA 2023

作者： Yildiran, Ugur Yildiz Technical University Control and Automation Engineering Department İstanbul Turkey

ISBN: (纸本)9798350337525

Reinforcement Learning (RL) based methods have became popular for control and motion planning of robots, recently. Unlike sampling based motion planners, optimal policies computed by them provide feedback motion plans which eliminates the need for re-computing (optimal) trajectories when a robot starts from a different initial configuration each time. In related studies, an optimal policy (actor) and the associated value function (critic) are usually calculated preforming training in a simulation environment. During training, RL allows learning by interactions with the environment in a physically realistic manner. However, in a simulation system, it is possible to make physically unimplementable moves. Thus, instead of RL, one can make use of Dynamic Programming approaches such as Value Iteration for computing optimal policies, which does not require an exploration component and known to have better convergence properties. In addition, dimension of a value function is smaller than that of a Q-fuction, thereby lessening the severity of the curse of dimensionality. Motivated by these facts, the aim of this paper is to employ Value Iteration algorithm for motion planning of robot manipulators and elaborate its effectiveness compared to a popular RL method, Q-learning. © 2023 IEEE.

关键词： Manipulators

来源：评论

学校读者我要写书评

暂无评论

Parks-McClellan Algorithm-Based Active Damping Strategy Applied to Grid-Connected Inverters 8

Parks-McClellan Algorithm-Based Active Damping Strategy Appl...

引用

8th Southern Power Electronics Conference and the 17th Brazilian Power Electronics Conference, SPEC / COBEP 2023

作者： Filho, José De Arimatéia O. Bressanini, Gabriel Lucas Curi Busarello, Tiago Davi De Oro Arenas, Luis Silva, Paulo Fernando Morales Paredes, Helmo Kelis Sorocaba Brazil Department of Control Automation and Computing Engineering Blumenau Brazil

ISBN: (纸本)9798350321128

In recent years, grid-connected inverters have gained wide prominence, primarily attributed to the surge in distributed energy resources. To ensure the reliable operation of these inverters, it is crucial to adequately damp the resonance peak of the LCL filter at the inverter output. By achieving this, the grid-connected inverter guarantees the system's stability while minimizing the harmonic content in the current injected into the distribution grid. To address this issue, this paper proposes the utilization of digital differentiators in conjunction with optimized wideband differentiators, which are designed using the Parks-McClellan (PM) algorithm. These differentiators are applied specifically to the LCL filter capacitor voltage to dampen the resonance peak effectively. Simulation results univocally demonstrate the effectiveness of the proposed approach. © 2023 IEEE.

关键词： Active damping capacitor voltage digital differentiator LCL-filter Parks-McClellan algorithm

来源：评论

学校读者我要写书评

暂无评论

Process Monitoring Based on Temporal Feature Agglomeration and Enhancement

引用

IEEE/CAA Journal of Automatica Sinica 2023年第3期10卷 825-827页

作者： Xiao Liang Weiwu Yan Yusun Fu Huihe Shao Department of Automation the School of Electronic Information and Electrical EngineeringShanghai Jiao Tong UniversityShanghai 200240China Department of Automation the School of Electronic Information and Electrical EngineeringShanghai Jiao Tong UniversityShanghai 200240 Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai 200240China

Dear Editor,This letter proposes a process-monitoring method based on temporal feature agglomeration and enhancement,in which a novel feature extractor called contrastive feature extractor(CFE)extracts the temporal and relational features among process *** the feature representations are enhanced by maximizing the separation among different classes while minimizing the scatter within each class.

关键词： among while letter

来源：评论

学校读者我要写书评

暂无评论

Sequential Convex Program for Variable Speed Pump Scheduling in Water Distribution Systems 15

Sequential Convex Program for Variable Speed Pump Scheduling...

引用

15th International Conference on Electronics, Computers and Artificial Intelligence, ECAI 2023

作者： Dai, Pham Duc Thuyloi University Department of Control Engineering and Automation Hanoi Viet Nam

ISBN: (纸本)9798350321388

Operation of water distribution systems (WDSs) to reduction of water leakage can be achieved by properly operating variable speed pumps (VSPs). This practical problem can be casted into a nonlinear program (NLP) where decision variables are relative speeds of pumps while the state variables are flows and nodal heads. The formulated NLP consists of both convex and non-convex constraints, for this reason, we proposed to apply the sequential convex programming technique (SCP) for solving the NLP. The advantage of the SCP method lies in the fact that instead of solving the non-convex NLP, we solve sequential convex NLPs and, in this case, it requires less number of iterates for solution convergence than solving the problem directly by using standard NLP solvers. The effectiveness of the approach was demonstrated on two WDSs for optimal VSP scheduling problem © 2023 IEEE.

关键词： Water distribution systems

来源：评论

学校读者我要写书评

暂无评论

An Efficient Mixed Integer Nonlinear Program Model for Optimal Positions of Pressure Reducing Valves in Water Distribution Systems 15

An Efficient Mixed Integer Nonlinear Program Model for Optim...

引用

15th International Conference on Electronics, Computers and Artificial Intelligence, ECAI 2023

作者： Dai, Pham Duc Thuyloi University Department of Control Engineering and Automation Hanoi Viet Nam

ISBN: (纸本)9798350321388

Water loss happens in all water distribution systems (WDSs). To deal with such the problems, pressure management strategy should be applied to lessen the water leakage flow. The optimal pressure management is formulated to minimize the total of excessive pressures in all demand supplying nodes. In mathematical formulation, it is a mixed-integer nonlinear program (MINLP). The existing MINLP model having been used until now for optimizing PRV locations is proven to be hard for MINLP algorithms based gradient methods and therefore is only suitable for small-scale WDSs with a limited number of demand patterns. In this paper, an efficient non-smooth constraints are proposed to model whether PRVs are installed on links for the optimal PRV localization problem. Since these constraints can be approximated by relaxed forms of complementarity inequalities, high quality MINLP solution can be achieved in a reasonable computation time. To demonstrate the efficacy of our new modeling approach, comparison of the performance of the newly formulated MINLP with the existing one for solving optimal PRV locating problems for a real WDS are taken. The results have shown that with our new MINLP model, better MINLP solution can be attained even for WDSs with multiple demand patterns. © 2023 IEEE.

关键词： Water distribution systems

来源：评论

学校读者我要写书评

暂无评论

A Comparison of Local Planner Algorithms for a ROS-based Omnidirectional Mobile Robot 8

A Comparison of Local Planner Algorithms for a ROS-based Omn...

引用

8th International Conference on Robotics and automation engineering, ICRAE 2023

作者： Imamoglu, Mehmed Rafi Sumer, Ecem Temeltas, Hakan Istanbul Technical University Department of Control and Automation Engineering Istanbul Turkey

ISBN: (纸本)9798350327656

The topic of local planner algorithms applicable to omnidirectional mobile robots is yet to thoroughly investigated. This study investigates the performance of the most commonly implemented local planner algorithms for omnidirectional mobile robots by conducting a comparative analysis between the Dynamic Window Approach (DWA) and the Timed Elastic Band (TEB) algorithms. The evaluation was conducted within real-world settings, specifically targeting the challenges of parking maneuvers, dynamic obstacle avoidance and turning maneuvers. Performance metrics, tailored to each scenario, were employed to assess the algorithms. The results demonstrate that the TEB method outperforms the DWA in the tested conditions. © 2023 IEEE.

关键词： Mobile robots

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：