检索结果-内蒙古大学图书馆

2024 China Automation Congress, CAC 2024

作者： Li, Haolin Yi, Peng Wei, Dixiao Bai, Wenyan The Department of Control Science and Engineering Tongji University Shanghai201804 China Shanghai Research Institute for Intelligent Autonomous Systems Tongji University Shanghai201203 China National Key Laboratory of Autonomous Intelligent Unmanned Systems Frontiers Science Center for Intelligent Autonomous Systems Ministry of Education China Beijing Aerospace Automatic Control Institute Beijing100854 China

ISBN: (纸本)9798350368604

The problem of confrontation games between multi-agent teams has attracted considerable interest, and the question of how to ensure effective coordination of heterogeneous agents in dynamic and adversarial environments remains a significant challenge. In this paper, we present a decision-making methodology for a confrontation game between two teams, which is based on large language models (LLMs). The game is designed as a competitive Seek-and-Take task comprising three distinct robot types: reconnaissance, grabbing, and blocking robots. The LLMs enhance the robot team’s decision-making efficiency, delivering high-level commands that significantly improve coordination and adversarial performance. The game is initially formalized as a partially observable Markov decision process. Subsequently, a systematic construction of the LLM agents is provided, enabling real-time decisions based on the state information of a heterogeneous robot team (HRT). Detailed prompt design and the "Zero-shot-CoT" procedure are provided, and a cue word iteration method with reflections is proposed as a means of enhancing the decision-making efficiency of the LLMs and generating optimal collaboration strategies. Finally, the efficacy of the methodology is validated through experimentation with multiple LLMs in a multi-robot simulation environment. The results demonstrate that LLMs improve the efficiency and adaptability of decision-making in dynamic environments by serving as a core decision module, generating optimal strategies through real-time analysis. © 2024 IEEE.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Hetero-Source Sensors Localization Based on High-Precision Map

Hetero-Source Sensors Localization Based on High-Precision ...

引用

Chinese Intelligent Automation Conference, CIAC 2023

作者： Cui, Zhuofan Tao, Junyi He, Bin Zhang, Yu State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University Hangzhou China Key Laboratory of Collaborative Sensing and Autonomous Unmanned Systems of Zhejiang Province Hangzhou China

ISBN: (纸本)9789819961863

High-precision maps and localization techniques are important modules in robot systems. However, the existing simultaneous localization and mapping methods using the same sensors in both localization and mapping tasks suffers from high costs and inflexibility. Therefore, the method of implementing a low-cost visual sensor to achieve indoor localization with the pre-obtained high-precision point cloud maps is proposed in this paper. To find a similar area represented by point cloud of the maps and the sensors, a localization strategy based on ICP for point cloud matching is completed on the premise of giving a rough initial pose. Meanwhile, visual odometry is integrated into the localization framework to conquer the localization failure caused by repeated point cloud features in indoor environments. The sub-meter level localization accuracy in the indoor building environment is achieved in the experiments. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2023.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Downsampling Assessment for LiDAR SLAM

Downsampling Assessment for LiDAR SLAM

引用

Chinese Intelligent Automation Conference, CIAC 2023

作者： Zhang, Jiabao Zhang, Yu State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University Hangzhou China Key Laboratory of Collaborative Sensing and Autonomous Unmanned Systems of Zhejiang Province Hangzhou China

ISBN: (纸本)9789819961863

LiDAR has become a widely used sensor in many autonomous areas, and LiDAR SLAM is one of essential applications. With the tendency of lightweight structure and the improvement of LiDAR resolution, downsampling points from LiDAR raw data has been utilized in some system. In this paper, we focus on the influence of point downsampling, especially on location and mapping, and propose a benchmark method to evaluate the LiDAR SLAM system based on downsampling property. Three criteria including RPE Degeneration, ATE Degeneration, and Precision Maintenance Rate are defined for assessment. Then, groups of experiments using this evaluation method are conducted, with a comparison and discussion of system characteristics, which may contribute to subsequent development of LiDAR SLAM system. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2023.

关键词： Optical radar

来源：评论

学校读者我要写书评

暂无评论

Adaptive dynamic surface control for quadrotor-slung load transportation system with uncertainties

引用

Science China(Technological Sciences) 2023年第10期66卷 2917-2929页

作者： DING Feng HUANG Jian SUN Chong AI Yong XU WenXia YANG ChenGuang School of Computer Science South-Central Minzu UniversityWuhan 430074China Key Laboratory of Ministryof EducationforImage Processing and Intelligent ControlHubei Key Laboratoryof Brain-inspired Intelligent Systems School of Artificial Intelligence and Automation Huazhong University of Science and TechnologyWuhan 430074China School of Computer Science and Engineering Wuhan Institute of TechnologyWuhan 430205China Key Laboratory of Ministry of Education for Autonomous Systems and Networked Control Guangdong Engineering Technology Research Center of Control of Intelligent SystemsCollege of Automation Science and EngineeringSouth China University of TechnologyGuangzhou 510640China

Quadrotors play a significant role in our lives and are transforming our *** cable-suspended loads is an unavoidable quadrotor application trend and a hot research topic in the control ***,the load swing and unpredictability pose significant challenges to the quadrotor's *** this paper,an anti-swing controller with an inner-outer control strategy for the quadrotor-slung load transportation system is *** facilitate the controller design,the outer position dynamics are restructured in the form of ***,a virtual controller is created to force the underactuated states to the dynamic surface to ensure the position subsystem's *** improve robustness,an adaptive law is used to eliminate the effects of uncertain cable ***,a dynamic surface controller for the inner attitude subsystem is presented to drive the actual force to the virtual *** is demonstrated that the control strategy can stabilize the quadrotor despite mass and cable length *** results are provided to demonstrate the efficacy and durability of the proposed method.

关键词： quadrotor-slung load transportation system dynamic surface control adaptive law cascade system model uncertainties

来源：评论

学校读者我要写书评

暂无评论

Point Cloud Classification Using Content-Based Transformer via Clustering in Feature Space

引用

IEEE/CAA Journal of Automatica Sinica 2024年第1期11卷 231-239页

作者： Yahui Liu Bin Tian Yisheng Lv Lingxi Li Fei-Yue Wang the State Key Laboratory for Management and Control of Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190 the School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100190 IEEE the Transportation and Autonomous Systems Institute(TASI)and the Department of Electrical and Computer Engineering Purdue School of Engineering and TechnologyIndiana University-Purdue University Indianapolis(IUPUI)Indianapolis 46202 USA

Recently, there have been some attempts of Transformer in 3D point cloud classification. In order to reduce computations, most existing methods focus on local spatial attention,but ignore their content and fail to establish relationships between distant but relevant points. To overcome the limitation of local spatial attention, we propose a point content-based Transformer architecture, called PointConT for short. It exploits the locality of points in the feature space(content-based), which clusters the sampled points with similar features into the same class and computes the self-attention within each class, thus enabling an effective trade-off between capturing long-range dependencies and computational complexity. We further introduce an inception feature aggregator for point cloud classification, which uses parallel structures to aggregate high-frequency and low-frequency information in each branch separately. Extensive experiments show that our PointConT model achieves a remarkable performance on point cloud shape classification. Especially, our method exhibits 90.3% Top-1 accuracy on the hardest setting of ScanObjectN N. Source code of this paper is available at https://***/yahuiliu99/PointC onT.

关键词： Content-based Transformer deep learning feature aggregator local attention point cloud classification

来源：评论

学校读者我要写书评

暂无评论

Cooperative Output Regulation of Heterogeneous systems over Directed Graphs:A Dynamic Adaptive Event-Triggered Strategy

引用

Journal of systems Science & Complexity 2023年第3期36卷 909-921页

作者： SU Hang CHENG Bin LI Zhongkui State Key Laboratory for Turbulence and Complex Systems and Department of Mechanics and Engineering Science College of EngineeringPeking UniversityBeijing 100871China Department of Control Science and Engineering College of Electronics and Information EngineeringTongji UniversityShanghai 201804China Frontiers Science Center for Intelligent Autonomous Systems Shanghai 201210China

This paper investigates the cooperative output regulation problem of heterogeneous linear multi-agent systems over directed graphs with the constraint of communication *** that there exists an exosystem whose state information is not available to all agents,the authors develop distributed adaptive event-triggered observers for the followers based on relative information between neighboring *** should be pointed out that,two kinds of time-varying gains are introduced to avoid relying on any global information associated with the network,and dynamic triggering conditions are designed to get rid of continuous *** the basis of the designed observers,the authors devise a local controller for each *** with the existing related works,the main contribution of the current paper is that the cooperative output regulation problem for general directed graphs is solved requiring neither global information nor continuous communications.

关键词： Adaptive control consensus cooperative output regulation directed graph event-triggered control multi-agent systems

来源：评论

学校读者我要写书评

暂无评论

Predefined time attitude control for quadrotor UAV with output constraints and input saturation

Predefined time attitude control for quadrotor UAV with outp...

引用

2024 China Automation Congress, CAC 2024

作者： Li, Shuo Pei, Hailong Key Laboratory of Autonomous Systems and Networked Control Ministry of Education Guangdong Engineering Technology Research Center of Unmanned Aerial Vehicle Systems College of Automation Science and Enginneering South China University of Technology Guangzhou510640 China Key Laboratory of Autonomous Systems and Networked Control Ministry of Education Guangdong Engineering Technology Research Center of Unmanned Aerial Vehicle Systems School of Automation Science and Enginneering South China University of Technology Guangzhou510640 China

ISBN: (纸本)9798350368604

In this paper, we examine the predefined time flight control of a quadrotor UAV with output constraints and input saturation. The attitude tracking error of UAV is constrained by the tan-type barrier Lyapunov function. The undesirable effects of the saturated input limitations are addressed by introducing an auxiliary system. Then a predefined time tracking control strategy is designed and the stability of the scheme is analyzed. Eventually, the simulation results show the method allows the angular tracking error to converge to the specified range in a predefined time. © 2024 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

MMH-FE:AMulti-Precision and Multi-Sourced Heterogeneous Privacy-Preserving Neural network Training Based on Functional Encryption

引用

Computers, Materials & Continua 2025年第3期82卷 5387-5405页

作者： Hao Li Kuan Shao Xin Wang Mufeng Wang Zhenyong Zhang The State Key Laboratory of Public Big Data College of Computer Science and TechnologyGuizhou UniversityGuiyang550025China Key Laboratory of Computing Power Network and Information Security Ministry of EducationShandong Computer Science CenterQilu University of Technology(Shandong Academy of Sciences)Jinan250014China China Industrial Control Systems Cyber Emergency Response Team Beijing100040China

Due to the development of cloud computing and machine learning,users can upload their data to the cloud for machine learning model ***,dishonest clouds may infer user data,resulting in user data *** schemes have achieved secure outsourced computing,but they suffer from low computational accuracy,difficult-to-handle heterogeneous distribution of data from multiple sources,and high computational cost,which result in extremely poor user experience and expensive cloud computing *** address the above problems,we propose amulti-precision,multi-sourced,andmulti-key outsourcing neural network training ***,we design a multi-precision functional encryption computation based on Euclidean ***,we design the outsourcing model training algorithm based on a multi-precision functional encryption with multi-sourced ***,we conduct experiments on three *** results indicate that our framework achieves an accuracy improvement of 6%to 30%.Additionally,it offers a memory space optimization of 1.0×2^(24) times compared to the previous best approach.

关键词： Functional encryption multi-sourced heterogeneous data privacy preservation neural networks

来源：评论

学校读者我要写书评

暂无评论

Distributed robust matrix-scaled consensus control of perturbed multi-agent systems

引用

control Theory and Technology 2024年第4期22卷 623-637页

作者： Bin Cheng Gang Li Kun An Chunhui Yu Department of Control Science and Engineering Tongji UniversityShanghai201804China Shanghai Research Institute for Intelligent Autonomous Systems Shanghai201210China The Key Laboratory of Road and Traffic Engineering of the Ministry of Education Tongji UniversityShanghai201804China Shanghai Sunshine Rehabilitation Center Shanghai201613China

Distributed matrix-scaled consensus is a kind of generalized cooperative control problem and has broad applications in the field of social network and *** paper addresses the robust distributed matrix-scaled consensus of perturbed multi-agent systems suffering from unknown *** discontinuous protocols are first proposed to drive agents to achieve cluster consensus and suppress the effect of *** protocols with time-varying gains obeying differential equations are also designed,which are completely distributed and rely on no global *** the boundary layer technique,smooth protocols are proposed to avoid the unexpected chattering effect due to discontinuous *** a cost,under the designed smooth protocols,the defined matrix-scaled consensus error tends to a residual set rather than zero,in which the residual bound is arbitrary small by choosing proper ***,distributed dynamic event-based matrix-scalar consensus controllers are also proposed to avoid continuous *** examples are provided to further verify the designed algorithms.

关键词： Matrix-scaled consensus Perturbed multi-agent systems Adaptive control Distributed control Event-triggered control

来源：评论

学校读者我要写书评

暂无评论

An Integrated Model of Train Timetable and Speed Profile for Single Bi-directional Track

An Integrated Model of Train Timetable and Speed Profile for...

引用

International Conference on Artificial Intelligence and autonomous Transportation, AIAT 2024

作者： Wu, Wenxing Xun, Jing Liu, Xiaoyu Fu, Minxue State Key Laboratory of Advanced Rail Autonomous Operation Beijing Jiaotong University Beijing China Delft Center for Systems and Control Delft University of Technology Delft2628CD Netherlands

ISBN: (纸本)9789819639762

In this paper, we consider the integrated model of train timetable and speed profile for a single bi-directional track. This problem aims to schedule train passes along single track from opposite directions to avoid conflicts. It is assumed that there are different types of stations along the track, and trains can only pass each other simultaneously at stations that have sidings. Focusing on the operation scenario, we propose an integrated model of train timetable and speed profile optimization. To address the nonlinear constraints generated by the meeting conflicts in the single bi-directional operation, the Big-M method is used to transform the constraints into linear constraints incorporating binary integer variables such as meeting and train priority. Thus, a mixed integer linear programming (MILP) model is constructed, which can be solved using the Gurobi solver. The model is formulated with two objective functions: one aims to minimize the time deviation of trains running in pairs considering passenger satisfaction, and the other is to minimize the total train travel time. The proposed model is applied to solve the problem based on a single-line urban railway and the feasibility of the model is verified. The results show that the total train travel time is effectively reduced by 29.8%. © Beijing Paike Culture Commu. Co., Ltd. 2025.

关键词： Travel time

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：