检索结果-内蒙古大学图书馆

Level Curve Tracking via Robust RL-Guided Model Predictive Control

IEEE/CAA Journal of Automatica Sinica 2024年第12期11卷 2512-2514页

作者： Zhuo Li Yunlong Guo Gang Wang Wei Chen the State Key Laboratory of Autonomous Intelligent Unmanned Systems School of AutomationBeijing Institute of TechnologyBeijing 100081China the Beijing Institute of Technology Chongqing Innovation Center Chongqing 401120China

Dear Editor,This letter investigates the level curve tracking problem of unknown scalar fields using an unmanned aerial vehicle(UAV)and presents a robust reinforcement learning(RL)-guided model predictive control(MPC)scheme for the ***,we formulate the MPC trajectory tracking problem,wherein an RL-based trajectory planning algorithm provides the reference trajectory to guide the UAV towards the desired concentration.

关键词： letter desired scheme

来源：评论

学校读者我要写书评

暂无评论

Composite Anti-Disturbance Control of Hidden Semi-Markov Jump systems via Disturbance Observer

引用

Journal of systems Science & Complexity 2023年第6期36卷 2255-2273页

作者： MEN Yunzhe SUN Jian National Key Lab of Autonomous Intelligent Unmanned Systems School of AutomationBeijing Institute of TechnologyBeijing100081China Beijing Institute of Technology Chongqing Innovation Center Chongqing401120China

This paper focuses on the disturbance suppression issue of hidden semi-Markov jump systems leveraging composite *** system consists of a semi-Markov layer and an observed mode sequence layer,and it is subject to a matched disturbance generated by an exogenous system and a mismatched disturbance that is norm *** proposal is to design a composite controller based on a disturbance observer to counteract and attenuate the disturbances *** constructing a special Lyapunov function comparison point,the exponential stability is analyzed with the stability criterion in the form of linear matrix inequality is *** simulation examples are provided to demonstrate the practical merits of the composite controller relative to the single H_(∞)control.

关键词： Composite control disturbance observer ε-error hidden semi-Markov jump systems

来源：评论

学校读者我要写书评

暂无评论

An adaptive large neighborhood search for the multi-point dynamic aggregation problem

引用

Control Theory and Technology 2024年第3期22卷 360-378页

作者： Shengyu Lu Bin Xin Jie Chen Miao Guo School of Automation Beijing Institute of TechnologyBeijing 100081China National Key Lab of Autonomous Intelligent Unmanned Systems Beijing 100081China Department of Control Science and Engineering Tongji UniversityShanghai 201804China

The multi-point dynamic aggregation(MPDA)problem is a challenging real-world *** the MPDA problem,the demands of tasks keep changing with their inherent incremental rates,while a heterogeneous robot fleet is required to travel between these tasks to change the time-varying state of each *** robots are allowed to collaborate on the same task or work separately until all tasks are *** is challenging to generate an effective task execution plan due to the tight coupling between robots abilities and tasks'incremental rates,and the complexity of robot *** effectiveness consideration,we use the variable length encoding to avoid redundancy in the solution *** creatively use the adaptive large neighborhood search(ALNS)framework to solve the MPDA *** the proposed algorithm,high-quality initial solutions are generated through multiple problem-specific solution construction *** heuristics are also used to fix the broken solution in the novel integrated decoding-construction repair process of the ALNS *** results of statistical analysis by the Wilcoxon rank-sum test demonstrate that the proposed ALNS can obtain better task execution plans than some state-of-the-art algorithms in most MPDA instances.

关键词： Adaptive large neighborhood search(ALNS) Multi-point dynamic aggregation(MPDA) Heuristic solution construction Multi-robot collaboration

来源：评论

学校读者我要写书评

暂无评论

Asymptotic Output Tracking Control of a Class of Linear systems by Finite-and-Quantized Output Feedback

引用

无人系统（英文） 2024年第2期12卷 249-260页

作者： Jian Guo Yanjun Zhang Ji-Feng Zhang Key Lab of Systems and Control Institute of Systems ScienceAcademy of Mathematics and Systems ScienceChinese Academy of SciencesBeijing 100190China School of Mathematics Sciences University of Chinese Academy of SciencesBejing 100149China School of Automation Beijing Institute of TechnologyBeijing 100081China State Key Lab of Autonomous Intelligent Unmanned Systems Beijing Institute of TechnologyBeijing 100081China

This paper presents a novel finite-and-quantized output feedback asymptotic tracking control method for a general class of continuous-time linear time-invariant ***,we construct a finite quantizer with time-varying thresholds and design a pole placement control law that exclusively utilizes the finite-and-quantized output signal and an external reference ***,we establish the boundedness of all closed-loop signals and prove the asymptotic convergence of the output tracking error to *** proposed method combines the advantages of classical pole placement control technique and finite quantization feedback *** not only reduces the requirement for feedback information compared with existing tracking control methods but also effectively handles unstable poles and zeros in controlled systems,thereby achieving asymptotic output ***,we provide a representative example to validate the effec-tiveness and new features of our proposed method.

关键词： Continuous-time asymptotic output tracking pole placement control quantized-output feedback

来源：评论

学校读者我要写书评

暂无评论

Modular Design and Implementation of Formation Motion Planning System for Multi-unmanned Vehicles 7th

Modular Design and Implementation of Formation Motion Planni...

引用

7th Chinese Conference on Swarm Intelligence and Cooperative Control, CCSICC 2023

作者： Song, Yijing Lyu, Jingshuo Wei, Shaozhun Fang, Hao Yang, Qingkai School of Automation Beijing Institute of Technology Beijing100081 China National Key Lab of Autonomous Intelligent Unmanned Systems Shanghai China

ISBN: (纸本)9789819733392

This article develops a motion planning system that combines path planning and formation control for multi-unmanned vehicles. The system adopts a modular design method, including three parts: path planning, formation control, and communication. The overall navigation system employs a leader-following strategy. Considering the ambient environment, the leader vehicle generates an optimal trajectory and corresponding velocity control commands by using the Time Elastic Band (TEB) path planning technique. The control module uses the distributed control scheme for altering the followers’ velocity, aiming to follow the leader vehicle and form the expected formation. The communication module uses UDP communication strategy to transmit parameter information among vehicles. Finally, based on the proposed motion planning system, we conducted formation obstacle avoidance experiments in ROS to verify the effectiveness of the designed structure. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Fixed-time Sliding Mode Consensus Control for Nonlinear Multi-agent systems with External Disturbances 43

Fixed-time Sliding Mode Consensus Control for Nonlinear Mult...

引用

43rd Chinese Control Conference, CCC 2024

作者： He, Yingmei Xin, Bin Yang, Yixi Cheng, Shuai Beijing Institute of Technology School of Automation Beijing100081 China National Key Lab of Autonomous Intelligent Unmanned Systems Beijing100081 China

ISBN: (纸本)9789887581581

This paper studies the consensus tracking problem of nonlinear multi-agent systems with external disturbances and proposes a new fixed-time sliding mode consensus control method based on disturbance observer. A new fixed-time disturbance observer is constructed, which accelerates the estimation speed of disturbances. Based on the observer, a disturbance resistant fixed-time sliding mode consensus control protocol is designed to help the state tracking errors of the multi-agent systems converge to a small neighborhood of zero within a fixed time. The comparative simulation results demonstrate the effectiveness of the proposed strategy. © 2024 Technical Committee on Control Theory, Chinese Association of automation.

关键词： Sliding mode control

来源：评论

学校读者我要写书评

暂无评论

A Multi-Dimensional Dynamic Evaluation Method for the Intelligence of unmanned Aerial Vehicle Swarm

A Multi-Dimensional Dynamic Evaluation Method for the Intell...

引用

2023 IEEE International Conference on unmanned systems, ICUS 2023

作者： Quan, Wei Jia, Linpeng Zhang, Zhao Chen, Chen Wang, Lingda School of Automation Beijing Institute of Technology The National Key Lab of Autonomous Intelligent Unmanned Systems Beijing China

ISBN: (纸本)9798350316308

With the emergence of unmanned system and swarm intelligence technology, how to describe and evaluate the intelligence of unmanned aerial vehicle swarm (UAVS) has become a challenging topic. An intelligence description framework is established involving the mission execution complexity and mission performance indexes. Multiple dimensions index system is built to express the internal intelligence behavior of the UAVS. To dynamically evaluate the intelligence capability of UAVS from multi-dimension, a dynamic indexes framework based on data yard and combined weighting method is proposed. Intelligence performance under multiple dynamic execution periods and complexities are synthesized to evaluate the intelligence capability. Aiming at discussing UAVS intelligence across missions, the evaluated intelligence capability is transformed to intelligence level by the designed intelligence classification framework and the standard swarm intelligence. An intelligence evaluation instance is provided to verify the effectiveness of the proposed method. The intelligence evaluation framework and method can fully consider the dynamic performance and mission execution complexities of the swarm system, and evaluate the intelligent capabilities of UAVS from multiple dimensions. © 2023 IEEE.

关键词： unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Adaptive Multi-Swarm Differential Evolution Algorithm for UAV Path Planning

Adaptive Multi-Swarm Differential Evolution Algorithm for UA...

引用

2023 IEEE International Conference on unmanned systems, ICUS 2023

作者： Wu, Tongyu Meng, Kai Chen, Chen School of Automation Beijing Institute of Technology National Key Lab of Autonomous Intelligent Unmanned Systems Beijing China

ISBN: (纸本)9798350316308

Path planning for unmanned aerial vehicles (UAVs) remains a crucial prerequisite for UAV application in various fields. However, due to the complexity of the model, several state-of-the-art methods may encounter challenges in finding feasible solutions or be prone to getting stuck in local optima, especially in the complex 3D battlefield environment. An adaptive multi-swarm differential evolution algorithm (AMSDE) is put forward to address these problems. First, we employ the ϵ-level comparison to ensure the feasibility of the solution. Second, we design an adaptive swarm partitioning technique to avoid crossover evolution between sub-swarms caused by random partitioning. Third, the hierarchical update mechanism is implemented to guide each sub-swarm's search. It facilitates effective communication between sub-swarms and keeps the balance of exploration and exploitation. Experiment results have shown that AMSDE is competitive compared with other excellent algorithms, proving its capability to generate higher-quality paths for UAVs. © 2023 IEEE.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

FVFH: An Improved Navigation Algorithm for UGVs in the Complex Disaster Environment

FVFH: An Improved Navigation Algorithm for UGVs in the Compl...

引用

2023 China automation Congress, CAC 2023

作者： Xu, Nengwei Yang, Kun Chen, Chen School of Automation The National Key Lab of Autonomous Intelligent Unmanned Systems Beijing Institute of Technology Beijing China

ISBN: (纸本)9798350303759

The problem of navigation by unmanned ground vehicles (UGVs) in disaster areas is widely investigated. An environmental simulation model of disaster areas is established in order to solve this problem. The Focus Vector Field Histogram (FVFH) navigation algorithm for UGVs is designed: 1) A screening mechanism for the moving direction of the UGV is proposed;2) The dynamic constraints of realistic UGVs are considered. The performance of the algorithm is tested on the Gym and CoppeliaSim platforms. The experimental results show that the FVFH algorithm can effectively shorten the planning time and navigation paths, and overcome special terrain obstacles with a high navigation success rate. Thus, the FVFH algorithm is helpful for navigation in complex disaster environment. © 2023 IEEE.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning for Multi-Period Facility Location: pk-median Dynamic Location Problem 24

Deep Reinforcement Learning for Multi-Period Facility Locati...

引用

32nd ACM SIGSPATIAL International Conference on Advances in Geographic Information systems, ACM SIGSPATIAL 2024

作者： Miao, Changhao Zhang, Yuntian Wu, Tongyu Deng, Fang Chen, Chen National Key Lab of Autonomous Intelligent Unmanned Systems Beijing100081 China School of Automation Beijing Institute of Technology Beijing100081 China

ISBN: (纸本)9798400711077

Facility location is a crucial aspect of spatial optimization with broad applications in urban planning. Specifically, the multi-period problem involves spatial and temporal information, making it challenging to solve. Existing research mainly focuses on heuristic methods, which depend on complex hand-crafted techniques. In this paper, we propose a novel method based on Deep Reinforcement Learning (DRL) to solve pk-median Dynamic Location Problem (DLP-pk). Different from classical heuristic methods, our method avoids intricate designs and considers the temporal impacts of decisions. We are the first to apply DRL to the multi-period facility location problem. Our method adopts the encoder-decoder architecture and utilizes a specialized structure to capture the temporal features across different periods. On the one hand, we introduce the Gated Recurrent Units (GRU) to encode temporal information, including dynamic coverage and dynamic costs. On the other hand, we design an attention-based decoder that allows the model to capture long-term dependencies in decision-making. Experimental results from small-size to large-size demonstrate that our method can quickly provide high-quality solutions without relying heavily on expert knowledge, offering opportunities for efficiently solving multi-period facility location problems. Additionally, our method is up to two orders of magnitude faster than the exact solver Gurobi and demonstrates great generalization abilities. © 2024 Copyright held by the owner/author(s).

关键词： Deep reinforcement learning

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：