Proceedings of the 6th International Conference on Control Engineering and Artificial Intelligence最新文献

筛选

英文中文

Reinforcement learning based indoor, collaborative autonomous mobility　基于强化学习的室内协同自主移动

Proceedings of the 6th International Conference on Control Engineering and Artificial Intelligence Pub Date : 2022-03-11 DOI: 10.1145/3522749.3523066

Hang Liu, A. Hyodo, Shintaro Suzuki

{"title":"Reinforcement learning based indoor, collaborative autonomous mobility　","authors":"Hang Liu, A. Hyodo, Shintaro Suzuki","doi":"10.1145/3522749.3523066","DOIUrl":"https://doi.org/10.1145/3522749.3523066","url":null,"abstract":"By connecting building operations, building automation can be realized using mobile devices and AI processor. Aiming for improving living condition and reducing workloads, we designed a cyber-physical system to operate multiple infrastructure efficiently, which enables an indoor autonomous mobility. We customize a navigation map owing the 3D space information of the building, then an optimal driving route is calculated by an intelligent path planner to calculate. Two technical novelties are proposed: (1) intra-building sensors connecting to the central system are deployed to monitor certain vehicle's surroundings change at which spatial heights. The central with building's 3D model draws several customized maps at those heights. (2) based on the customized map, we use two-stage training scheme for path planner, which first and second stages utilize DQN and NEAT, respectively. It uses a refined network model for better, faster updating its structure and parameter. The proposed scheme is proven to reduce driving time consumption more than $20%$ and accelerates training period more than $30%$ compared to conventional algorithms.","PeriodicalId":361473,"journal":{"name":"Proceedings of the 6th International Conference on Control Engineering and Artificial Intelligence","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124470287","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

Texture-suppression-based surface defect detection of milled aluminum ingot 基于织构抑制的铣削铝锭表面缺陷检测

Proceedings of the 6th International Conference on Control Engineering and Artificial Intelligence Pub Date : 2022-03-11 DOI: 10.1145/3522749.3523070

Ying Liang, Ke Xu

{"title":"Texture-suppression-based surface defect detection of milled aluminum ingot","authors":"Ying Liang, Ke Xu","doi":"10.1145/3522749.3523070","DOIUrl":"https://doi.org/10.1145/3522749.3523070","url":null,"abstract":"The surface quality of aluminum ingot has a great influence on the subsequent rolling process, so defect detection is a critical step after milling. However, it is a challenging task, owing to multi-direction and multi-scale of milling texture pattern, and sometimes uneven distribution of texture primitives. In this paper, a novel texture-suppression-based defect detection method combined with wavelet decomposition and relative total variation (RTV) for milled surface is proposed. In order to adaptively decide the scale factor of RTV which is vital in texture-structure separation, we first resort to mine intrinsic priors of defect and milling grains in the detail sub images derived from the wavelet decomposition. Secondly, based on the mined prior rules, a detail sub image is automatically selected from different decomposition levels and the corresponding scale factor for RTV is also determined. Then, by feeding the selected sub image into the RTV model, the texture is suppressed and the main structures that containing defects are extracted. Compared with taking the original image as the input, the wavelet preprocessed sub image effectively weakens the influence of the scale and direction change of texture pattern, and greatly improves the time efficiency of RTV. Finally, through the simple gradient calculation and binarization of the structure image, the defects are segmented. The experimental results show that the proposed method is robust and effective to detect various surface defects of steel ingot with complex milling texture.","PeriodicalId":361473,"journal":{"name":"Proceedings of the 6th International Conference on Control Engineering and Artificial Intelligence","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123152859","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 CNN-based Fog Node Data Processing Method and Application in Wearable Heart Detection Equipment 基于cnn的雾节点数据处理方法及其在可穿戴心脏检测设备中的应用

Proceedings of the 6th International Conference on Control Engineering and Artificial Intelligence Pub Date : 2022-03-11 DOI: 10.1145/3522749.3523084

Hai-ya Wu, Yuyun Kang, Baiyang Wang, Dongyue Huo, Dongping Chen

引用次数: 0

首页上一页