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： 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

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

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

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

Immoral post detection using a one-dimensional convolutional neural network-based LSTM network

引用

Multimedia Tools and Applications 2025年 1-20页

作者： Saqia, Bibi Khan, Khairullah Rahman, Atta Ur Khan, Aurangzeb Jain, Deepak Kumar Department of Computer Science University of Science and Technology Bannu28100 Pakistan Riphah Institute of Systems Engineering Riphah International University Islamabad46000 Pakistan Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education Dalian University of Technology Dalian116024 China Symbiosis Institute of Technology Symbiosis International University Pune India

In text mining and Natural Language Processing (NLP), extracting emotions from textual data is gaining rapid attraction. The proliferation of online content and the freedom of expression on social media platforms has compelled the advancement of more sophisticated methods for the automatic identification of unwanted content. The One-Dimensional Convolutional Neural Network (1D-CNN) performs best for feature extraction, while the Long Short-Term Memory Network (LSTM) is well-known for extracting sequential features and classification of textual data. This study proposes a novel solution by combining 1D-CNN with LSTM. Utilizing a context-aware model, this study aims to enhance the detection of immoral posts, including hate speech and other forms of immoral content on social media platforms. Various posts are extracted from social media, which are then processed using Glove word embedding models. It depicts the word representations in the text, which yields the form of a real-valued vector determining the words' meaning. The 1D convolution utilizes a filter window over the input time-series data to extract features. Relying on the acquired parameters of the filters, they act as feature extractors. This feature extraction technique allows the model to distinguish detailed patterns and nuances from the textual contents of posts. The sequential processing capabilities of the LSTM network enable an in-depth examination of the text, capturing temporal relationships and context, which is critical for successful content categorization. To validate the proposed model, we utilized a benchmark dataset, called the Twitter dataset. The proposed model achieved the highest accuracy of 95.37% and outperforms state-of-the-art works. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Convolutional neural networks

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

Improved Hybrid Gaussian Process Regression Model for state-of-Health Estimation of Li-ion Batteries

Improved Hybrid Gaussian Process Regression Model for State-...

引用

Chinese Automation Congress (CAC)

作者： Tao An Zhitao Liu Chizhou Yan Ke Xu 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)9798350368604

ISBN: (纸本)9798350368611

Accurate state-of-health (SOH) estimation con-tributes to the healthy and stable operation of the Li-ion batteries. This paper proposes an improved hybrid Gaussian process regression (GPR) method incorporating physical information for the high-accuracy estimation of battery SOH. The estimation process considers the effects of temperature, discharge rate, and depth of discharge (DOD) on the battery health, and the relevant features of the electrode degradation process are extracted for battery SOH estimation. The kernel function of GPR comprehensively considers the mechanical characteristics of battery degradation and can effectively track the battery degra-dation process. The validation experiments were conducted on the A123 LFP/Graphite battery dataset. Sufficient comparative experiments have validated the accuracy and robustness of the proposed method.

关键词： Lithium-ion batteries Electrodes Degradation Accuracy Estimation Gaussian processes Feature extraction Robustness Batteries Kernel

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

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

Safe Efficient Policy Optimization Algorithm for Unsignalized Intersection Navigation

引用

IEEE/CAA Journal of Automatica Sinica 2024年第9期11卷 2011-2026页

作者： Xiaolong Chen Biao Xu Manjiang Hu Yougang Bian Yang Li Xin Xu State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body the College of Mechanical and Vehicle EngineeringHunan UniversityChangsha 410082China State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body the College of Mechanical and Vehicle EngineeringHunan UniversityChangsha 410082 Wuxi Intelligent Control Research Institute(WICRI)of Hunan University Wuxi 214115China College of Intelligence Science and Technology Institute of Unmanned SystemsNational University of Defense TechnologyChangsha 410073China

Unsignalized intersections pose a challenge for autonomous vehicles that must decide how to navigate them safely and *** paper proposes a reinforcement learning(RL)method for autonomous vehicles to navigate unsignalized intersections safely and *** method uses a semantic scene representation to handle variable numbers of vehicles and a universal reward function to facilitate stable learning.A collision risk function is designed to penalize unsafe actions and guide the agent to avoid them.A scalable policy optimization algorithm is introduced to improve data efficiency and safety for vehicle learning at *** algorithm employs experience replay to overcome the on-policy limitation of proximal policy optimization and incorporates the collision risk constraint into the policy optimization *** proposed safe RL algorithm can balance the trade-off between vehicle traffic safety and policy learning *** intersection scenarios with different traffic situations are used to test the algorithm and demonstrate its high success rates and low collision rates under different traffic *** algorithm shows the potential of RL for enhancing the safety and reliability of autonomous driving systems at unsignalized intersections.

关键词： Autonomous driving decision-making reinforcement learning(RL) unsignalized intersection

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：