检索结果-内蒙古大学图书馆

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

Collaborative recognition of feasible region with aerial and ground robots through DPCN

Collaborative recognition of feasible region with aerial and...

引用

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

作者： Li, Yunshuang Huang, Zheyuan Chen, Zexi Wang, Yue Xiong, Rong Institute of Cyber-Systems and Control Zhejiang University State Key Laboratory of Industrial Control Technology Zhejiang China

ISBN: (纸本)9781665436786

Ground robots always get collision in that only if they get close to the obstacles, can they sense the danger and take actions, which is usually too late to avoid the crash, causing severe damage to the robots. To address this issue, we present a collaborative system with aerial and ground robots to gain precise recognition of feasible region. Taking the aerial robots' advantages of having large scale variance of view points of the same route which the ground robots is on, the collaboration work provides global information of road segmentation for the ground robot, thus enabling it to obtain feasible region and adjust its pose ahead of time. Under normal circumstance, the transformation between these two devices can be obtained by GPS yet with much error, directly causing inferior influence on recognition of feasible region. Thereby, we utilize the state-of-the-art research achievements in matching heterogeneous sensor measurements called deep phase correlation network(DPCN), which has excellent performance on heterogeneous mapping, to refine the transformation. The network is light-weighted and promising for better generalization. We use Aero-Ground dataset which consists of heterogeneous sensor images and aerial road segmentation images. The results show that our collaborative system has great accuracy, speed and stability. © 2021 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

A novel hierarchical charging algorithm for the AGV dispatching problem in a multi-robot system 18

A novel hierarchical charging algorithm for the AGV dispatch...

引用

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

作者： Niu, Haoyi Wu, Weimin Zhang, Tao Zhejiang University State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control Hangzhou China

ISBN: (纸本)9781665440486

Charging problem for the AGVs (automated guided vehicles) in a multi-robot system based on a real-world intelligent warehouse aims to maximize the transportation efficiency of AGVs considering the charging process. For this purpose, a hierarchical charging algorithm is presented by taking into account both the continuity of transportation and the charging efficiency. A multi-level threshold scheme is designed to reduce the impact of the charging process on AGV scheduling. The numerical experiment results indicate that at the same charging rate, the number of completed tasks by AGVs can be increased from 18 to 28 an hour compared with traditional charging algorithm thus the efficiency can be improved from 34.62% to 51.86% correspondingly, which shows the superior performance of the presented algorithm. © 2021 IEEE.

关键词： Multipurpose robots

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Algorithm to Solve Periodic Vehicle Dispatching Problem with Heterogeneous Vehicles in Logistics Transportation 18

A Hybrid Algorithm to Solve Periodic Vehicle Dispatching Pro...

引用

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

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

ISBN: (纸本)9781665440486

The vehicle dispatching problem (VDP) is researching how to arrange vehicles' transportation, which has been addressed by many scholars. In the field of logistics transportation, the vehicle dispatching problem is presented in a special form, that is, the periodic vehicle dispatching problem (PVDP) with heterogeneous vehicles. In order to solve this problem and improve the efficiency of vehicles, a round recombination algorithm (RRA) with two operators are designed in this paper. And a hybrid algorithm consisting of RRA and simulated annealing algorithm is also proposed to improve RRA. Three groups of experiments are carried out to test the performance of designed algorithms in different scenarios. The results of these experiments prove the effectiveness of RRA. The results also show the superiority of hybrid algorithm to RRA. © 2021 IEEE.

关键词： Simulated annealing

来源：评论

学校读者我要写书评

暂无评论

A Collision Avoidance Algorithm for Idle Robots in Multi-robot System 18

A Collision Avoidance Algorithm for Idle Robots in Multi-rob...

引用

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

作者： Xing, Zichao Wu, Weimin Wang, Xingkai 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) play vital roles in manufacturing systems and logistics systems. In order to improve the efficiency of MRSs, we propose an idle robot collision avoidance algorithm(IRCAA) for idle robots to give way for working robots. In the proposed method, idle robots stop in place for new tasks without returning to robot stations. Once an idle robot gets in the way of working robots, IRCAA will find an avoidance point (AP) for the idle robot to give way. Additionally, no new block or deadlock occurs when the idle robot arrives at the AP. The proposed method in this paper is effective and able to improve the efficiency of MRSs, which is verified by both simulation experiments and actual industrial projects. © 2021 IEEE.

关键词： Multipurpose robots

来源：评论

学校读者我要写书评

暂无评论

Design of recognition algorithm for multiclass digital display instrument based on convolution neural network

引用

Biomimetic Intelligence & Robotics 2023年第3期3卷 67-74页

作者： Xuanzhang Wen Yuxia Wang Qiuguo Zhu Jun Wu Rong Xiong Anhuan Xie Polytechnic Institute Zhejiang UniversityHangzhou 310015China College of Control Science and Engineering Zhejiang UniversityHangzhou 310027China State Key Laboratory of Industrial Control and Technology Zhejiang UniversityHangzhou 310027China Zhejiang Lab Hangzhou 311121China

Digital display instrument identification is a crucial approach for automating the collection of digital display *** this study,we propose a digital display area detection CTPNpro algorithm to address the problem of recognizing multiclass digital display *** developed a multiclass digital display instrument recognition algorithm by combining the character recognition network constructed using a convolutional neural network and bidirectional variable-length long short-term memory(LSTM).First,the digital display region detection CTPNpro network framework was designed based on the CTPN network architecture by introducing feature fusion and residual ***,the digital display instrument identification network was constructed based on a convolutional neural network using twoway LSTM and Connectionist temporal classification(CTC)of indefinite ***,an automatic calibration system for digital display instruments was built,and a multiclass digital display instrument dataset was constructed by sampling in the *** compared the performance of the CTPNpro algorithm with other methods using this dataset to validate the effectiveness and robustness of the proposed algorithm.

关键词： Multiclass display instrument Digital display area detection Character recognition Convolutional neural network Characteristics of the fusion

来源：评论

学校读者我要写书评

暂无评论

Research on Coupled Task Allocation and Scheduling of Multi-type Robots 18

Research on Coupled Task Allocation and Scheduling of Multi-...

引用

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

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

ISBN: (纸本)9781665440486

Task allocation problem and scheduling problem have always been hot topics in the robotics research field. Both of them can be divided into many categories. Among all these categories, coupled task allocation and scheduling problem (CTASP) is a quite difficult problem, especially for of multi-type robots. However, few researches are conducted on this area. Usually, the CTASP is studied for multi-type robots with fixed execution sequence in the reported literature. However, this paper will study the CTASP for multi-type robots with flexible execution sequence. A two-dimension genetic algorithm (TDGA) is designed to solve this type of problem, combined with rank minimal heuristic (RMH) algorithm to provide an elite strategy. The simulation experiment proves that TDGA can solve this kind of problems efficiently, and the efficiency of hybrid genetic algorithm has been further improved. © 2021 IEEE.

关键词： Robots

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning for Adaptive Planner Parameter Tuning: A Perspective on Hierarchical Architecture

arXiv

引用

arXiv 2025年

作者： Lu, Wangtao Wei, Yufei Xu, Jiadong Jia, Wenhao Li, Liang Xiong, Rong Wang, Yue State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control Zhejiang University Hangzhou China College of Information and Engineering Zhejiang University of Technology Hangzhou310023 China

Automatic parameter tuning methods for planning algorithms, which integrate pipeline approaches with learning-based techniques, are regarded as promising due to their stability and capability to handle highly constrained environments. While existing parameter tuning methods have demonstrated considerable success, further performance improvements require a more structured approach. In this paper, we propose a hierarchical architecture for reinforcement learning-based parameter tuning. The architecture introduces a hierarchical structure with low-frequency parameter tuning, mid-frequency planning, and high-frequency control, enabling concurrent enhancement of both upper-layer parameter tuning and lower-layer control through iterative training. Experimental evaluations in both simulated and real-world environments show that our method surpasses existing parameter tuning approaches. Furthermore, our approach achieves first place in the Benchmark for Autonomous Robot Navigation (BARN) Challenge. Copyright © 2025, The Authors. All rights reserved.

关键词： 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：