检索结果-内蒙古大学图书馆

2021 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2021

作者： Du, Haozhe Chen, Zhike Wang, Yufeng Huang, Zheyuan Wang, Yunkai Xiong, Rong Zhejiang University State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control Hangzhou China

ISBN: (纸本)9781665436786

Many tasks have demand on precise predictions of agents or moving objects. Previous prediction methods usually only focus on the kinematic model of moving objects or the environment. However, the target tasks of agents may influence the prediction of agents in great sense, especially in tasks of confrontation. Therefore traditional methods cannot work well in such scenes. In this paper, we propose a heterogeneous graph neural network method to deal with the multi-agent trajectory prediction problem. Our method can aggregate and pass messages representing environment and also agents' tasks due to the elaborate design of graph neural network structure. We validate our method on the Robocup Small Size League simulation platform which focuses on multi-agent coordination and confrontation in the form of soccer games. After making our own ZJUNlictSSL dataset, we predict the position of all robots on the pitch of certain time gaps based on the limited information we get from vision. The results prove that our method is of high prediction accuracy and low prediction error compared with conventional kinematic motion methods. Code is available here. © 2021 IEEE.

关键词： Simulation platform

来源：评论

学校读者我要写书评

暂无评论

A Two-Stage Congestion-Aware Routing Method for Automated Guided Vehicles in Warehouses 18

A Two-Stage Congestion-Aware Routing Method for Automated Gu...

引用

18th IEEE International Conference on Networking, Sensing and control, ICNSC 2021

作者： Chen, Xinyu Feng, Ligen Wang, Xingkai Wu, Weimin Hu, Ruifen Zhejiang University State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control Hangzhou China

ISBN: (纸本)9781665440486

With multi-AGV (automated guided vehicle) systems gradually employed in modern warehouses, the research on how to coordinate AGVs in an efficient way has attracted more scholars than ever. As the size of AGVs grows over time, the possibility of traffic congestion is increasing rapidly, especially in a limited space. Therefore, the congestion-aware routing method is one of the most vital and fundamental topics in multi-AGV control research. In this paper, a two-stage congestion-minimizing routing method is presented. The proposed method not only plans paths that avoid congested areas, but also changes paths in real time to cope with the volatile traffic situations. An experiment is carried out to test the effectiveness and efficiency of the proposed method, and the results are highly promising in terms of alleviating traffic congestion. © 2021 IEEE.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

Multi-stage decision-making skill learning for soccer robot

Multi-stage decision-making skill learning for soccer robot

引用

2021 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2021

作者： Chen, Zhike He, Zhiye Du, Haozhe Han, Chengrui Wang, Yunkai Chen, Zexi Xiong, Rong Institute of Cyber-Systems and Control Zhejiang University State Key Laboratory of Industrial Control Technology Hangzhou China

ISBN: (纸本)9781665436786

The application scenarios of robots are becoming more and more complex, leading to higher and higher demand on skills for robots. This paper proposes a method to learn complex skill by decomposing it into basic skills, then train them respectively as well as combination into a whole, where reinforcement learning are used both in basic skill learning and in the integration. The method proposed is validated on the RoboCup small soccer robot platform via the skill of chasing and shooting ball and tested in both simulation environment and real world. It is verified our method has achieved a higher success rate comparing with traditional methods. Code is available here. © 2021 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Research on Container Slot Planning for Coordinated Operation of Quay Cranes and Yard Cranes 18

Research on Container Slot Planning for Coordinated Operatio...

引用

18th IEEE International Conference on Networking, Sensing and control, ICNSC 2021

作者： Huang, Lili Wu, Weimin Zhejiang University State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control Hangzhou China

ISBN: (纸本)9781665440486

Given ship per-stowage plan and yard stacking status, this paper presents a method on container slot planning for coordinated operation of quay cranes (QC) and yard cranes (YC). A multi-objective programming model is established with the goal of maximizing the turnover rate of container terminal. Then, a heuristic construction algorithm is designed to obtain an initial stowage plan. In addition, an annealing genetic algorithm is proposed to optimize this initial solution. A wide variety of numerical experiments demonstrated that stowage plans made by this method are useful and applicable in practice. © 2021 IEEE.

关键词： Containers

来源：评论

学校读者我要写书评

暂无评论

Bayesian CNN-GRU with Attention Mechanism for Lithium-ion Battery state of Health Estimation

Bayesian CNN-GRU with Attention Mechanism for Lithium-ion Ba...

引用

Chinese control and Decision Conference, CCDC

作者： Tao An Zhitao Liu Chizhou Yan Ke Xu Shuxing Zhang Hongye Su State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control Zhejiang University Hangzhou China Wanxiang A123 Systems Corp. Hangzhou China

ISBN: (数字)9798350387780

ISBN: (纸本)9798350387797

Accurate estimation of the state of health (SOH) is crucial for ensuring the safe and stable operation of lithium-ion (Li-ion) batteries. This paper presents an approach called Bayesian CNN-GRU with Attention Mechanism (AM-BCG) to estimate the entire lifecycle health state of the battery. Effective feature extraction is performed during the SOH estimation to ensure accurate prediction. Specifically, domain knowledge- related temporal features of Li-ion battery degradation processes are extracted, while capacity difference curves are utilized as spatially relevant features for model inputs. The AM-BCG approach comprises parallel CNN-GRU networks with attention mechanism and bayesian neural networks (BNN). The parallel CNN-GRU networks extract generalized information from prior data, the attention mechanism increases the weight of essential features and reduces overfitting, and BNN provides uncertainty estimates. Experimental validation on the A123 67Ah LFP battery dataset confirms that the proposed method exhibits high robustness and accuracy in estimating battery SOH.

关键词： Lithium-ion batteries Attention mechanisms Accuracy Uncertainty Neural networks Estimation Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Battery Charge Dispatching in Multi-robot systems 18

Battery Charge Dispatching in Multi-robot Systems

引用

18th IEEE International Conference on Networking, Sensing and control, ICNSC 2021

作者： Xing, Zichao Wu, Weimin Niu, Haoyi Hu, Ruifen Zhejiang University State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control Hangzhou China

ISBN: (纸本)9781665440486

Multi-robot systems (MRSs) attract more and more attention due to their efficiency and safety. In a practical scenario, robots need to work for a long time without human intervention, which requires the robots do not run out of power. The battery charging strategy of most systems uses a fixed threshold or fixed periods to determine when robots should be charged. It does not consider the system task situation, nor the situation of charging station (CS) competition. This paper proposes an efficient charge dispatching strategy, which can ensure that a robot firstly completes a task quickly when it is scheduled to work and firstly be charged to be ready for a subsequent task when it is idle. For the case that multiple robots compete for the same CS, we designe a bidding strategy to determine which robot should be serviced. A rule-based charging strategy is used to compare with the proposed charge dispatching strategy in this paper. The results show that our method performs better in terms of stability and efficiency. © 2021 IEEE.

关键词： Multipurpose robots

来源：评论

学校读者我要写书评

暂无评论

Accurate and straightforward symplectic approach for fracture analysis of fractional viscoelastic media

引用

Applied Mathematics and Mechanics(English Edition) 2022年第3期43卷 403-416页

作者： Chenghui XU Sen LENG Zhenhuan ZHOU Xinsheng XU Zichen DENG MIIT Key Laboratory of Dynamics and Control of Complex Systems Department of Engineering MechanicsNorthwestern Polytechnical UniversityXi'an 710072China State Key Laboratory of Structure Analysis of Industrial Equipment Department of Engineering MechanicsDalian University of TechnologyDalian 116024Liaoning ProvinceChina

An accurate and straightforward symplectic method is presented for the fracture analysis of fractional two-dimensional(2D)viscoelastic *** fractional Kelvin-Zener constitutive model is used to describe the time-dependent behavior of viscoelastic *** the framework of symplectic elasticity,the governing equations in the Hamiltonian form for the frequency domain(s-domain)can be directly and rigorously *** the s-domain,the analytical solutions of the displacement and stress fields are constructed by superposing the symplectic eigensolutions without any trial function,and the explicit expressions of the intensity factors and J-integral are derived *** studies are provided to validate the accuracy and effectiveness of the present solutions.A detailed analysis is made to reveal the effects of viscoelastic parameters and applied loads on the intensity factors and J-integral.

关键词： symplectic approach viscoelastic material fractional Kelvin-Zener model crack fracture parameter

来源：评论

学校读者我要写书评

暂无评论

Adaptive cubature Kalman filter with the estimation of correlation between multiplicative noise and additive measurement noise

引用

Chinese Journal of Aeronautics 2022年第5期35卷 40-52页

作者： Quanbo GE Zhongcheng MA Jinglan LI Qinmin YANG Zhenyu LU Hong LI School of Electronics and Information Engineering Tongji UniversityShanghai 201804China Institute of Systems Science and Control Engineering School of AutomationHangzhou Dianzi UniversityHangzhou 310018China State Key Laboratory of Industrial Control Technology and the College of Control Science and EngineeringZhejiang UniversityHangzhou 310027China Jiangsu Key Laboratory of Meteorological Observation and Information Processing Nanjing University of Information Science and TechnologyNanjing 210044China Chinese Flight Test Establishment Xi’an 710089China

Mobile robots are often subject to multiplicative noise in the target tracking tasks,where the multiplicative measurement noise is correlated with additive measurement *** this paper,first,a correlation multiplicative measurement noise model is *** is able to more accurately represent the measurement error caused by the distance sensor dependence ***,the estimated performance mismatch problem of Cubature Kalman Filter(CKF)under multiplicative noise is *** improved Gaussian filter algorithm is introduced to help obtain the CKF algorithm with correlated multiplicative *** practice,the model parameters are unknown or inaccurate,especially the correlation of noise is difficult to obtain,which can lead to a decrease in filtering accuracy or even *** address this,an adaptive CKF algorithm is further provided to achieve reliable state estimation for the unknown noise correlation coefficient and thus the application of the CKF algorithm is ***,the estimated performance is analyzed theoretically,and the simulation study is conducted to validate the effectiveness of the proposed algorithm.

关键词： Adaptive CKF Correlated noise Estimation accuracy Multiplicative noise Performance analysis Target tracking

来源：评论

学校读者我要写书评

暂无评论

Obstacle Avoidance for Unicycle-Modelled Mobile Robots with Time-Varying control Barrier Functions

Obstacle Avoidance for Unicycle-Modelled Mobile Robots with ...

引用

Annual Conference of industrial Electronics Society

作者： Jihao Huang Zhitao Liu Jun Zeng Xuemin Chi Hongye Su State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control Zhejiang University Hangzhou China Cruise LLC USA

In this paper, we propose a safety-critical controller based on time-varying control barrier functions (CBFs) for a robot with an unicycle model in the continuous-time domain to achieve navigation and dynamic collision avoidance. Unlike previous works, our proposed approach can control both linear and angular velocity to avoid collision with obstacles, overcoming the limitation of confined control performance due to the lack of control variable. To ensure that the robot reaches its destination, we also design a control Lyapunov function (CLF). Our safety-critical controller is formulated as a quadratic program (QP) optimization problem that incorporates CLF and CBFs as constraints, enabling real-time application for navigation and dynamic collision avoidance. Numerical simulations are conducted to verify the effectiveness of our proposed approach.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adaptive Fuzzy control With Guaranteed Performance For Electric Vehicles

Adaptive Fuzzy Control With Guaranteed Performance For Elect...

引用

第35届中国控制与决策会议

作者： Weijun Huang Hongye Su Yang Zhu Ningbo Innovation Center Zhejiang University State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and ControlZhejiang University

In this paper,we propose a new adaptive fuzzy control scheme with a saturator for a class of constrainted uncertain unparametrizable nonlinear electric vehicle(EV) *** control scheme effectively addresses the nonlinearities and uncertainties in the EV systems without exact knowledge including variable hill climbing angle and other system parameters,and solves the constraints on the amplitude of input *** techniques of adaptive control,fuzzy logic system,and backstepping design are *** the scheme,the speed tracking error of the system converges to a preset interval asymptotically even in the presence of time-varying hill climbing angle and other system *** control algorithm is illustrated by the simulation results.

关键词：

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：