As expanding of laser welding application, it has paid attention on laser welding of ship structures. For this purpose, a study on laser wire welding based on robot and tracking sensor for ship structures has been carried out. After the basic investigation on influence of welding parameters on weld formation, optimal specification was determined. For tolerating the variable joint gap width, the gap adaptability of laser wire welding was investigated, and an adaptive wire filling model drawing a relationship between welding speed, gap width, reinforcement, wire speed and laser power was established. With the help of a laser version sensor in front of welding head, with which the gap width can be measured during welding, an adaptive laser wire welding for butt joints of 6~8mm thick ship steel plates could be realized. Meanwhile, by use of the same laser version sensor, a seam tracking with an accuracy of 0.05 mm in x-direction is also expectable.
{"title":"Robot-based adaptive laser wire welding of ship steel plates","authors":"Jian Huang, Kebing Zhang, Xiaopeng Zhu, Xin-Hua Tang","doi":"10.1109/ARSO.2016.7736276","DOIUrl":"https://doi.org/10.1109/ARSO.2016.7736276","url":null,"abstract":"As expanding of laser welding application, it has paid attention on laser welding of ship structures. For this purpose, a study on laser wire welding based on robot and tracking sensor for ship structures has been carried out. After the basic investigation on influence of welding parameters on weld formation, optimal specification was determined. For tolerating the variable joint gap width, the gap adaptability of laser wire welding was investigated, and an adaptive wire filling model drawing a relationship between welding speed, gap width, reinforcement, wire speed and laser power was established. With the help of a laser version sensor in front of welding head, with which the gap width can be measured during welding, an adaptive laser wire welding for butt joints of 6~8mm thick ship steel plates could be realized. Meanwhile, by use of the same laser version sensor, a seam tracking with an accuracy of 0.05 mm in x-direction is also expectable.","PeriodicalId":403924,"journal":{"name":"2016 IEEE Workshop on Advanced Robotics and its Social Impacts (ARSO)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125138961","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}
Pub Date : 2016-07-08DOI: 10.1109/ARSO.2016.7736284
Li Fang, Junnan Wang, R. Xiong
This paper introduces a coarse-to-fine approach for industrial meter detection. This work has two key contributions. First, our method describes a two-level cascaded regressor to directly regress the industrial meter's parameter representation with normalizing target images to the same pose and scale, avoiding searching in multi-scale space with sliding windows. Second, after normalization, our method proposes a post verifier to largely decrease the false positive rate while keeping the true positive rate relatively high. Considering real-time performance, our method runs at 15 frames/s without multi-thread acceleration, which is essential for practical application. Evaluating with various on-site data, this approach achieves 97.5% hit rate while keeping the false positive rate below 1.35%. What's more, when applying this detection method to meter reading, the accuracy of digits reading achieves 95.5%, and the accuracy of pointer indicator detection achieves 95.6%, while the average error of estimated pointer indicator reading is limited to 6.6% normalized by measure range. Our coarse-to-fine approach shows promising prospect in practical applications.
{"title":"A coarse-to-fine approach for industrial meter detection and its application","authors":"Li Fang, Junnan Wang, R. Xiong","doi":"10.1109/ARSO.2016.7736284","DOIUrl":"https://doi.org/10.1109/ARSO.2016.7736284","url":null,"abstract":"This paper introduces a coarse-to-fine approach for industrial meter detection. This work has two key contributions. First, our method describes a two-level cascaded regressor to directly regress the industrial meter's parameter representation with normalizing target images to the same pose and scale, avoiding searching in multi-scale space with sliding windows. Second, after normalization, our method proposes a post verifier to largely decrease the false positive rate while keeping the true positive rate relatively high. Considering real-time performance, our method runs at 15 frames/s without multi-thread acceleration, which is essential for practical application. Evaluating with various on-site data, this approach achieves 97.5% hit rate while keeping the false positive rate below 1.35%. What's more, when applying this detection method to meter reading, the accuracy of digits reading achieves 95.5%, and the accuracy of pointer indicator detection achieves 95.6%, while the average error of estimated pointer indicator reading is limited to 6.6% normalized by measure range. Our coarse-to-fine approach shows promising prospect in practical applications.","PeriodicalId":403924,"journal":{"name":"2016 IEEE Workshop on Advanced Robotics and its Social Impacts (ARSO)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134070139","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}
Pub Date : 2016-07-08DOI: 10.1109/ARSO.2016.7736251
K. Kojima, T. Tanikawa, K. Ohoba
After the Tohoku Earthquake on March 11, 2011, the National Institute of Advanced Industrial Science and Technology (AIST) and some private companies launched a disaster support project, the “Kesennuma Kizuna Project,” in the disaster area Kesennuma City, Miyagi Pref. We started new activities for implementing smart community technologies, such as energy management, robotic life care technologies, etc., to activate the human connections and the community. This paper briefly reviews the project, shows some of the technological results, generates a discussion, and proposes a new system-design process model for social systems.
{"title":"New system-design model using action research in a disaster area","authors":"K. Kojima, T. Tanikawa, K. Ohoba","doi":"10.1109/ARSO.2016.7736251","DOIUrl":"https://doi.org/10.1109/ARSO.2016.7736251","url":null,"abstract":"After the Tohoku Earthquake on March 11, 2011, the National Institute of Advanced Industrial Science and Technology (AIST) and some private companies launched a disaster support project, the “Kesennuma Kizuna Project,” in the disaster area Kesennuma City, Miyagi Pref. We started new activities for implementing smart community technologies, such as energy management, robotic life care technologies, etc., to activate the human connections and the community. This paper briefly reviews the project, shows some of the technological results, generates a discussion, and proposes a new system-design process model for social systems.","PeriodicalId":403924,"journal":{"name":"2016 IEEE Workshop on Advanced Robotics and its Social Impacts (ARSO)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128827394","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}
Pub Date : 2016-07-08DOI: 10.1109/ARSO.2016.7736295
Huihui Chu, Zong-Yi Wang, Xiang Luo
In order to realize the on-line quality inspection of tube-sheet welding, this paper establishes a vision-based quality inspection system to realize the defect detection. And image processing, as the most important part of inspection system, is in-depth studied. Image processing algorithms include two parts: preprocessing and defect detection. Image preprocessing includes median filter, Otsu segmentation, morphological operation, ROI (region of interest) and area smooth. In the defect detection part, the sum intensity of tube is used to judge whether there is a defect and the position of defect is determined accurately. Experimental results show that the image processing method can be widely used with high reliability and robustness.
{"title":"Quality inspection algorithm based on machine vision for tube-sheet welding","authors":"Huihui Chu, Zong-Yi Wang, Xiang Luo","doi":"10.1109/ARSO.2016.7736295","DOIUrl":"https://doi.org/10.1109/ARSO.2016.7736295","url":null,"abstract":"In order to realize the on-line quality inspection of tube-sheet welding, this paper establishes a vision-based quality inspection system to realize the defect detection. And image processing, as the most important part of inspection system, is in-depth studied. Image processing algorithms include two parts: preprocessing and defect detection. Image preprocessing includes median filter, Otsu segmentation, morphological operation, ROI (region of interest) and area smooth. In the defect detection part, the sum intensity of tube is used to judge whether there is a defect and the position of defect is determined accurately. Experimental results show that the image processing method can be widely used with high reliability and robustness.","PeriodicalId":403924,"journal":{"name":"2016 IEEE Workshop on Advanced Robotics and its Social Impacts (ARSO)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129745000","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}
Based on the requirement of complicated surface polishing from manufacturing automation, aiming at solving the complex and inefficient online teaching of robotic polishing system, this paper proposes a force-controlled polishing system and implements off-line programming on process path of blade polishing by robot through analyzing the deformation of the contact part between blade and buffing wheel. Finite element was used to analyze the contact part, and the blade polishing module was developed in the environment of robot studio combining the horizontal line cutting method and the Douglas-Peucker algorithm. Simulation was taken on the off-line module and the resulting file was input into the industrial robot to carry out experiments. The results show that this method had better experimental effect and faster processing efficiency.
{"title":"A flexible system of complex surface polishing based on the analysis of the contact force and path research","authors":"Ting Huang, Chuang Li, Zhenhua Wang, Yiming Liu, Guodong Chen","doi":"10.1109/ARSO.2016.7736297","DOIUrl":"https://doi.org/10.1109/ARSO.2016.7736297","url":null,"abstract":"Based on the requirement of complicated surface polishing from manufacturing automation, aiming at solving the complex and inefficient online teaching of robotic polishing system, this paper proposes a force-controlled polishing system and implements off-line programming on process path of blade polishing by robot through analyzing the deformation of the contact part between blade and buffing wheel. Finite element was used to analyze the contact part, and the blade polishing module was developed in the environment of robot studio combining the horizontal line cutting method and the Douglas-Peucker algorithm. Simulation was taken on the off-line module and the resulting file was input into the industrial robot to carry out experiments. The results show that this method had better experimental effect and faster processing efficiency.","PeriodicalId":403924,"journal":{"name":"2016 IEEE Workshop on Advanced Robotics and its Social Impacts (ARSO)","volume":"126 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131337255","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}
Pub Date : 2016-07-08DOI: 10.1109/ARSO.2016.7736263
Di Wu, Huabin Chen, Yiming Huang, Yinshui He, Shanben Chen
Variable polarity plasma arc welding, as an advanced manufacturing technology, has been successfully used in industrial production due to high energy density. The need for the control of the weld penetration remains of a long term interest in VPPAW process. In this study, a simple-flexible vision system was established to acquire a series of keyhole images, and the geometrical appearance of keyhole including the keyhole width and area are extracted based on part-based tree model. Then the acquired keyhole features are used to predict the weld penetration by using a novel extreme learning machine model. The research shows that ELM model can predict the penetration state of variable polarity plasma arc welding credibly and achieve real time monitoring for welding quality.
{"title":"Weld penetration identification for VPPAW based on keyhole features and extreme learning machine","authors":"Di Wu, Huabin Chen, Yiming Huang, Yinshui He, Shanben Chen","doi":"10.1109/ARSO.2016.7736263","DOIUrl":"https://doi.org/10.1109/ARSO.2016.7736263","url":null,"abstract":"Variable polarity plasma arc welding, as an advanced manufacturing technology, has been successfully used in industrial production due to high energy density. The need for the control of the weld penetration remains of a long term interest in VPPAW process. In this study, a simple-flexible vision system was established to acquire a series of keyhole images, and the geometrical appearance of keyhole including the keyhole width and area are extracted based on part-based tree model. Then the acquired keyhole features are used to predict the weld penetration by using a novel extreme learning machine model. The research shows that ELM model can predict the penetration state of variable polarity plasma arc welding credibly and achieve real time monitoring for welding quality.","PeriodicalId":403924,"journal":{"name":"2016 IEEE Workshop on Advanced Robotics and its Social Impacts (ARSO)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130599023","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}
Pub Date : 2016-07-08DOI: 10.1109/ARSO.2016.7736273
Kuan-Chun Sun, Sheng-Wen Lo, Jwusheng Hu
This study aims to find an efficient 3D localization method related to a single dipole landmark in near magnetic field using IMU (Inertial Measurement Unit) array. We derive a novel algorithm that can avoid dealing with high order nonlinearity and singularity of distance in denominator in a mathematical dipole model by using a designed structure array to approach the gradient tensor. Moreover, we apply a state constrained Kalman filter for solving an underdetermined problem and estimating the rotation matrix between sensor and landmark simultaneously. The simulation analysis and experiment result show the effectiveness of the proposed algorithm in estimating the 3D position from a single dipole magnetic landmark.
{"title":"A single dipole-based localization method in near magnetic field using IMU array","authors":"Kuan-Chun Sun, Sheng-Wen Lo, Jwusheng Hu","doi":"10.1109/ARSO.2016.7736273","DOIUrl":"https://doi.org/10.1109/ARSO.2016.7736273","url":null,"abstract":"This study aims to find an efficient 3D localization method related to a single dipole landmark in near magnetic field using IMU (Inertial Measurement Unit) array. We derive a novel algorithm that can avoid dealing with high order nonlinearity and singularity of distance in denominator in a mathematical dipole model by using a designed structure array to approach the gradient tensor. Moreover, we apply a state constrained Kalman filter for solving an underdetermined problem and estimating the rotation matrix between sensor and landmark simultaneously. The simulation analysis and experiment result show the effectiveness of the proposed algorithm in estimating the 3D position from a single dipole magnetic landmark.","PeriodicalId":403924,"journal":{"name":"2016 IEEE Workshop on Advanced Robotics and its Social Impacts (ARSO)","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117215238","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}
The smart manufacturing program is gaining more and more research interests. To meet the requirements of increasingly low-volume, time-critical tasks, the traditional program-by-teaching methods should be replaced by more flexible and intelligent manufacturing processes. In this paper, we introduce the efforts of deploying ubiquitous robotic technology to the smart manufacturing program. Firstly, the various machinery processes are implemented as distributed components, which have standardized data ports and service ports. As a result, the machines could communicate and cooperate with each other. Further, a general-purpose task planner based on automated planning techniques is implemented to coordinate the machines for various tasks. We also use a test bed of smart assembly line to demonstrate the effectiveness of the proposed framework. Advances in planning technologies and cost reduction have brought the systems into the range of even small-to-medium enterprises.
{"title":"Study on ubiquitous robotic systems for smart manufacturing program","authors":"Q. Cao, Wenshan Wang, Xiaoxiao Zhu, Chuntao Leng, Masaru Adachi","doi":"10.1109/ARSO.2016.7736275","DOIUrl":"https://doi.org/10.1109/ARSO.2016.7736275","url":null,"abstract":"The smart manufacturing program is gaining more and more research interests. To meet the requirements of increasingly low-volume, time-critical tasks, the traditional program-by-teaching methods should be replaced by more flexible and intelligent manufacturing processes. In this paper, we introduce the efforts of deploying ubiquitous robotic technology to the smart manufacturing program. Firstly, the various machinery processes are implemented as distributed components, which have standardized data ports and service ports. As a result, the machines could communicate and cooperate with each other. Further, a general-purpose task planner based on automated planning techniques is implemented to coordinate the machines for various tasks. We also use a test bed of smart assembly line to demonstrate the effectiveness of the proposed framework. Advances in planning technologies and cost reduction have brought the systems into the range of even small-to-medium enterprises.","PeriodicalId":403924,"journal":{"name":"2016 IEEE Workshop on Advanced Robotics and its Social Impacts (ARSO)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121525099","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}
Pub Date : 2016-07-08DOI: 10.1109/ARSO.2016.7736250
T. Matsuo
This paper focuses on the responsibility/compensation aspect of the laws of robotics in Japan. This paper uses the automated vehicles as examples. The paper discusses civil and criminal responsibilities of designers, manufacturers and users of the automated vehicles. The issue of responsibility/compensation becomes very complex because of the characteristics of the automated vehicles and this paper discusses these issues from the viewpoint of both “over attribution” and “under attribution”.
{"title":"The preliminary analysis on the laws of robotics in Japan — Using automated vehicles as examples","authors":"T. Matsuo","doi":"10.1109/ARSO.2016.7736250","DOIUrl":"https://doi.org/10.1109/ARSO.2016.7736250","url":null,"abstract":"This paper focuses on the responsibility/compensation aspect of the laws of robotics in Japan. This paper uses the automated vehicles as examples. The paper discusses civil and criminal responsibilities of designers, manufacturers and users of the automated vehicles. The issue of responsibility/compensation becomes very complex because of the characteristics of the automated vehicles and this paper discusses these issues from the viewpoint of both “over attribution” and “under attribution”.","PeriodicalId":403924,"journal":{"name":"2016 IEEE Workshop on Advanced Robotics and its Social Impacts (ARSO)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114369865","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}
Pub Date : 2016-07-08DOI: 10.1109/ARSO.2016.7736271
Shuhe Chang, Yanqing Zhong, Zhenhua Quan, Yuxiang Hong, Jinle Zeng, D. Du
With the rapid development of computer vision technology, target tracking systems based on image processing is widely used in various fields. Aiming at the problem of image blurring while photographing in vibration environment, this paper proposed a smart tracking method based on physical motion compensation. This method centered the target in the camera while isolating the environment vibration. It not only improved the tracking success rate but also greatly reduced the search area which improved the efficiency of the TLD algorithm.
{"title":"A real-time object tracking and image stabilization system for photographing in vibration environment using OpenTLD algorithm","authors":"Shuhe Chang, Yanqing Zhong, Zhenhua Quan, Yuxiang Hong, Jinle Zeng, D. Du","doi":"10.1109/ARSO.2016.7736271","DOIUrl":"https://doi.org/10.1109/ARSO.2016.7736271","url":null,"abstract":"With the rapid development of computer vision technology, target tracking systems based on image processing is widely used in various fields. Aiming at the problem of image blurring while photographing in vibration environment, this paper proposed a smart tracking method based on physical motion compensation. This method centered the target in the camera while isolating the environment vibration. It not only improved the tracking success rate but also greatly reduced the search area which improved the efficiency of the TLD algorithm.","PeriodicalId":403924,"journal":{"name":"2016 IEEE Workshop on Advanced Robotics and its Social Impacts (ARSO)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124225376","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：