发布求助
文献互助 智能选刊 最新文献

2021 6th International Conference on Robotics and Automation Engineering (ICRAE)最新文献

筛选
英文 中文
Automated Reinforcement Learning Based on Parameter Sharing Network Architecture Search 基于参数共享网络结构搜索的自动强化学习
2021 6th International Conference on Robotics and Automation Engineering (ICRAE) Pub Date : 2021-11-19 DOI: 10.1109/ICRAE53653.2021.9657793
Zhaolei Wang, Jun Zhang, Yue Li, Qinghai Gong, Wuyi Luo, Jikang Zhao
{"title":"Automated Reinforcement Learning Based on Parameter Sharing Network Architecture Search","authors":"Zhaolei Wang, Jun Zhang, Yue Li, Qinghai Gong, Wuyi Luo, Jikang Zhao","doi":"10.1109/ICRAE53653.2021.9657793","DOIUrl":"https://doi.org/10.1109/ICRAE53653.2021.9657793","url":null,"abstract":"The performance of machine learning depends on the choice of hyperparameters to a great extent. Only by choosing the appropriate hyperparameters can we learn the desired learning results. At present, the end-to-end learning algorithm is widely concerned in the academic circles, and realizes the agile design from the demand end to the execution end at the design task level, which can dramatically reduce the complexity of the design. However, there are still a large number of hyperparameters, which need to be tuned manually, increasing the difficulty of machine learning application. Thus, with the continuous development of high-performance parallel computing, automated machine learning method arises. In this paper, aiming at the automatic design of the hyperparameter, the neural network architecture of deep reinforcement learning in the field of motion control, LSTM recurrent neural network topology generation algorithm, parameter sharing based fast reinforcement learning and evaluation mechanism, and graph generator parameter learning algorithm based on policy gradient are combined. An automated search and optimization framework of neural network architecture in the deep reinforcement learning is proposed, realizing the automated generation of network architecture. Finally, the effectiveness of the proposed approach is verified by taking the lunar lander landing control problem as an example.","PeriodicalId":338398,"journal":{"name":"2021 6th International Conference on Robotics and Automation Engineering (ICRAE)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127063169","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Research on Key Technologies of Carrier-Based Aircraft Landing 舰载机着舰关键技术研究
2021 6th International Conference on Robotics and Automation Engineering (ICRAE) Pub Date : 2021-11-19 DOI: 10.1109/ICRAE53653.2021.9657814
Yin Haitao, Li Yan
{"title":"Research on Key Technologies of Carrier-Based Aircraft Landing","authors":"Yin Haitao, Li Yan","doi":"10.1109/ICRAE53653.2021.9657814","DOIUrl":"https://doi.org/10.1109/ICRAE53653.2021.9657814","url":null,"abstract":"The key technologies of carrier-based aircraft in the landing process include deck motion prediction and compensation, radar noise suppression, disturbance suppression of aft flow and wave-off decision. In this paper, the key technologies in the process of landing is summarized and generalized, including the methods of deck motion compensation and prediction, the current mainstream ideas of disturbance suppression of aft flow, the influence of radar noise on landing control, the comparison of existing suppression methods, and the wave-off decision technology in view of the situation that carrier-aircraft cannot land safely. The study provides a theoretical reference for the control of carrier-based aircraft landing.","PeriodicalId":338398,"journal":{"name":"2021 6th International Conference on Robotics and Automation Engineering (ICRAE)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130409452","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Robot Real-time Inspection Method for Compliance Inspection of Switchgear Circuit Breaker Trolley 开关柜断路器台车合规性检测的机器人实时检测方法
2021 6th International Conference on Robotics and Automation Engineering (ICRAE) Pub Date : 2021-11-19 DOI: 10.1109/ICRAE53653.2021.9657800
Kuang Yin, J. Fang, W. Mo, Hong-Bing Wang, Tie Zhang, Mingda Yang
{"title":"Robot Real-time Inspection Method for Compliance Inspection of Switchgear Circuit Breaker Trolley","authors":"Kuang Yin, J. Fang, W. Mo, Hong-Bing Wang, Tie Zhang, Mingda Yang","doi":"10.1109/ICRAE53653.2021.9657800","DOIUrl":"https://doi.org/10.1109/ICRAE53653.2021.9657800","url":null,"abstract":"For switchgear conformity inspection, a real-time wavelet transform inspection algorithm based on the robot's qualification inspection scheme is proposed. The torque signal after Kalman filter is windowed. The data in the window is decomposed and reconstructed by wavelet, and the last data at the end of the window is used as the output of real-time wavelet transform. When the wavelet reconstructed amplitude of the high-frequency part of the continuous torque signal exceeds the threshold, it is judged that switchgear is unqualified. The proposed method is verified by experiments. The experimental results show that the recognition rate of the proposed algorithm is 100%, and delay within 20ms. In the case of damped interference, the recognition rate still maintains 100%, and delay within 30ms. Compared with the traditional offline wavelet transform inspection algorithm, it has a wider application range, stronger robustness, and can protect equipment and products more effectively.","PeriodicalId":338398,"journal":{"name":"2021 6th International Conference on Robotics and Automation Engineering (ICRAE)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120953945","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Autonomous Reconnaissance and Attack Test of UAV Swarm Based on Mosaic Warfare Thought 基于拼接战思想的无人机群自主侦察攻击试验
2021 6th International Conference on Robotics and Automation Engineering (ICRAE) Pub Date : 2021-11-19 DOI: 10.1109/ICRAE53653.2021.9657810
Duo Qi, Jiaqiang Zhang, Xiaolong Liang, Zhe Li, Jialiang Zuo, Pengfei Lei
{"title":"Autonomous Reconnaissance and Attack Test of UAV Swarm Based on Mosaic Warfare Thought","authors":"Duo Qi, Jiaqiang Zhang, Xiaolong Liang, Zhe Li, Jialiang Zuo, Pengfei Lei","doi":"10.1109/ICRAE53653.2021.9657810","DOIUrl":"https://doi.org/10.1109/ICRAE53653.2021.9657810","url":null,"abstract":"Mosaic warfare is a new type of combat concept proposed by the U.S. army for the information, intelligent, and unmanned warfare in the future. Its goal is to form an asymmetric advantage over the major combat opponents. Based on the analysis of the background of mosaic warfare, this paper summarizes the basic characteristics of it and compares it with UAV swarm operation, and concludes the similarities between them. Finally, by completing an autonomous reconnaissance and attack test of UAV swarm, the role completed by the corresponding nodes in the task process are described, which makes the UAV swarm operation concept more vivid and clear. It also partially verifies the feasibility of mosaic warfare.","PeriodicalId":338398,"journal":{"name":"2021 6th International Conference on Robotics and Automation Engineering (ICRAE)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123875636","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 4
A Recognition Method for Multi-object Information Based on Multi-source Data Fusion 基于多源数据融合的多目标信息识别方法
2021 6th International Conference on Robotics and Automation Engineering (ICRAE) Pub Date : 2021-11-19 DOI: 10.1109/ICRAE53653.2021.9657822
Zhengfan Zhao, Rongxing Wu, G. Nie, Bin Liu, Xun Li
{"title":"A Recognition Method for Multi-object Information Based on Multi-source Data Fusion","authors":"Zhengfan Zhao, Rongxing Wu, G. Nie, Bin Liu, Xun Li","doi":"10.1109/ICRAE53653.2021.9657822","DOIUrl":"https://doi.org/10.1109/ICRAE53653.2021.9657822","url":null,"abstract":"The accuracy of object recognition is difficult to be improved by single information acquisition, we propose a recognition method for multi-object information based on multi-source data Fusion. By analyzing the high-level semantic features of RGB images and Depth images, feature fusion module is added, then, the calculation of parameters of the model is reduced based on the idea of residual learning. Combined with the GRU recursive neural network, a tighter feature sequence is to generated, which improved the accuracy of RGB-D object recognition. Finally, improved method has been experimented on multiple public data sets, the results show that the object recognition method in this paper integrates depth information, Compared with single RGB image, the recognition accuracy is significantly improved; Compared with other RGB-D-oriented deep learning methods, the recognition accuracy of the method in the article has been significantly improved by at least 2.5% in 2D3D dataset.","PeriodicalId":338398,"journal":{"name":"2021 6th International Conference on Robotics and Automation Engineering (ICRAE)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133176585","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Anode Current for Aluminum Electrolysis Cell Condition Identification Based on Improved Temporal Convolutional Network 基于改进时间卷积网络的铝电解槽状态识别阳极电流
2021 6th International Conference on Robotics and Automation Engineering (ICRAE) Pub Date : 2021-11-19 DOI: 10.1109/ICRAE53653.2021.9657819
Jiuliang Zhou, Xiaofang Chen, Shiwen Xie, Yongfang Xie
{"title":"Anode Current for Aluminum Electrolysis Cell Condition Identification Based on Improved Temporal Convolutional Network","authors":"Jiuliang Zhou, Xiaofang Chen, Shiwen Xie, Yongfang Xie","doi":"10.1109/ICRAE53653.2021.9657819","DOIUrl":"https://doi.org/10.1109/ICRAE53653.2021.9657819","url":null,"abstract":"The stable operation of the aluminum electrolysis cell is the basis for the safe and efficient production of the electrolytic aluminum industry, and the cell condition identification technology is an important means to ensure the normal operation of the aluminum electrolysis cell. The cell condition identification technology based on anode current signal has played an increasingly important role in identify and fine control large aluminum electrolysis cells. This paper proposes an improved temporal convolutional network, which uses the time characteristics of the current signal to classify the current sequence for cell condition identification. The classification result can help people identify and monitor the conditions of the electrolysis cell. In this paper, the proposed method is verified on the real current signal, which can be used to identify various cell conditions such as anode effect and anode sliding.","PeriodicalId":338398,"journal":{"name":"2021 6th International Conference on Robotics and Automation Engineering (ICRAE)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121061001","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Fault Diagnosis of Power Transformer Based on Stacked Sparse Auto-Encoders and Broad Learning System 基于堆叠稀疏自编码器和广义学习系统的电力变压器故障诊断
2021 6th International Conference on Robotics and Automation Engineering (ICRAE) Pub Date : 2021-11-19 DOI: 10.1109/ICRAE53653.2021.9657760
Chao Xu, Xiaolan Li, Zhenhao Wang, Jie Xie, Bo Yang, Beijia Zhao
{"title":"Fault Diagnosis of Power Transformer Based on Stacked Sparse Auto-Encoders and Broad Learning System","authors":"Chao Xu, Xiaolan Li, Zhenhao Wang, Jie Xie, Bo Yang, Beijia Zhao","doi":"10.1109/ICRAE53653.2021.9657760","DOIUrl":"https://doi.org/10.1109/ICRAE53653.2021.9657760","url":null,"abstract":"The power transformer is an important part of the power system, and the diagnosis of the power transformer plays an important role in its safe operation. In order to improve the reliability and accuracy of power transformer fault diagnosis, this paper uses the dissolved gas in power transformer oil to propose a fault diagnosis method based on stacked sparse auto-encoders(SSAE) and broad learning system(BLS). The sparse auto-encoder has a powerful data reconstruction ability, which can extract the essential characteristics of the fault data by reconstructing the original data, and improve the diagnostic accuracy. The broad learning system reconstructs the network through incremental learning, and uses the pseudo-inverse calculation method to quickly solve the hidden layer-output layer weight, avoiding the use of gradient update method, improving training speed and preventing local optimization. Using KNN classifier to realize the feature clustering and label classification of the target domain samples. The simulation results show that the proposed method can effectively identify the fault type of power transformers with a satisfactory accuracy.","PeriodicalId":338398,"journal":{"name":"2021 6th International Conference on Robotics and Automation Engineering (ICRAE)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131646704","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Design and Hydrodynamic Analysis of a Robotic Boxfish Using Lift-based and Drag-based Swimming Modes for Propulsion 基于升力和阻力的机器箱鱼的设计与水动力分析
2021 6th International Conference on Robotics and Automation Engineering (ICRAE) Pub Date : 2021-11-19 DOI: 10.1109/ICRAE53653.2021.9657765
Hongcheng Qiu, S. Bi, Bo Wang, Yueri Cai
{"title":"Design and Hydrodynamic Analysis of a Robotic Boxfish Using Lift-based and Drag-based Swimming Modes for Propulsion","authors":"Hongcheng Qiu, S. Bi, Bo Wang, Yueri Cai","doi":"10.1109/ICRAE53653.2021.9657765","DOIUrl":"https://doi.org/10.1109/ICRAE53653.2021.9657765","url":null,"abstract":"This paper presents a new design for a robotic boxfish with a 2-DOF pectoral fin each side and a 1-DOF caudal fin. The pectoral fin designed is able to simulate the fin-base pitching and the fin-foil flapping, suggesting a combination of lift-based and drag-based kinematics. Based on Lattice-Boltzmann Method, the hydrodynamic characteristics of prototype's rigid pectoral fin was numerically calculated, so as to analyze the effects of motion parameters such as the offset angles of oscillation, phase lags, and amplitudes. Experiments in which the prototype relying on its pectoral fins alone for propulsion showed that by combining the motion parameters, the robotic boxfish was able to achieve highly maneuverable movements such as straight or inverted swimming, upward floating, downward diving and in-situ turning.","PeriodicalId":338398,"journal":{"name":"2021 6th International Conference on Robotics and Automation Engineering (ICRAE)","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123083915","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 2
Development of Domain Knowledge Graph: A Case Study on Flotation Process 领域知识图谱的开发:以浮选过程为例
2021 6th International Conference on Robotics and Automation Engineering (ICRAE) Pub Date : 2021-11-19 DOI: 10.1109/ICRAE53653.2021.9657783
Cheng Hu, Shiwen Xie, Yongfang Xie, Xiaofang Chen
{"title":"Development of Domain Knowledge Graph: A Case Study on Flotation Process","authors":"Cheng Hu, Shiwen Xie, Yongfang Xie, Xiaofang Chen","doi":"10.1109/ICRAE53653.2021.9657783","DOIUrl":"https://doi.org/10.1109/ICRAE53653.2021.9657783","url":null,"abstract":"A growing number of researches about knowledge graph have been studied and improved recently, but they are rarely applied in industries. At present, due to the lack of data and the scattered knowledge distribution in industry, constructing industrial domain knowledge graph is expensive and of low quality. This paper proposes a domain knowledge graph construction framework based on multi-source knowledge extraction, entity disambiguation, relation completion, and assisted decision-making, taking the flotation process as a case to study. Firstly, design the ontology layer of the flotation field, obtain corpus by crawling technology according to key words, and complete knowledge extraction. Secondly, use similarity calculation to entity disambiguation. Finally, apply the domain knowledge graph to achieve industrial applications, such as intelligent recommendation and assisted-decision in the flotation process.","PeriodicalId":338398,"journal":{"name":"2021 6th International Conference on Robotics and Automation Engineering (ICRAE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128486635","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A New Boundary Optimal Control of Multi Joint Flexible Manipulator Based on LaSalle Analysis Method 基于LaSalle分析法的多关节柔性机械臂边界最优控制
2021 6th International Conference on Robotics and Automation Engineering (ICRAE) Pub Date : 2021-11-19 DOI: 10.1109/ICRAE53653.2021.9657775
Huiqing Liang, Dehua Zhang
{"title":"A New Boundary Optimal Control of Multi Joint Flexible Manipulator Based on LaSalle Analysis Method","authors":"Huiqing Liang, Dehua Zhang","doi":"10.1109/ICRAE53653.2021.9657775","DOIUrl":"https://doi.org/10.1109/ICRAE53653.2021.9657775","url":null,"abstract":"This paper presents a new boundary control method for flexible manipulator based on LaSalle analysis method, which is a nonlinear system with unknown parameters, external disturbances and integrity constraints. Through theoretical analysis and dynamic modeling using LaSalle analysis method, using appropriate parameters enables us to obtain higher practicability than using the exponential convergence method in the traditional distributed parameter control method, without applying the traditional Lyapunov stability analysis. In addition, the dependence of each parameter is also given. And the theoretical analysis and practical simulation are carried out, which show the effectiveness of the proposed algorithm.","PeriodicalId":338398,"journal":{"name":"2021 6th International Conference on Robotics and Automation Engineering (ICRAE)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127935583","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：481959085
Book学术官方微信