{"title":"基于深度学习的机械臂拾取物体模式识别解决方案","authors":"M. N. Anh, D. X. Bien","doi":"10.46338/ijetae0223_13","DOIUrl":null,"url":null,"abstract":"This article presents the pattern recognition solution based on two deep learning modules supporting the robotic manipulator to pick up and drop objects. The first deep learning module performs image processing to recognize identified objects. The second module is used to train object pick and drop tasks based on the recognition results of the first module. To check the feasibility of the proposed pattern recognition solution, several tests are performed on a real robot arm model with 6 degrees of freedom with the constraints of joint variables limited from -170 degrees to 170 degrees. After performing 84 tests in more than 8 hours on GeForce RTX 3080 GPU with changes in object features (shape and colour), pick up or drop location, the statistical results show that the robot can be done exactly as required with up to 94% accuracy with a low-cost USB camera.","PeriodicalId":169403,"journal":{"name":"International Journal of Emerging Technology and Advanced Engineering","volume":"16 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A Solution of Pattern Recognition Based on Deep Learning for Robotic Manipulator to Pick Up and Drop Objects\",\"authors\":\"M. N. Anh, D. X. Bien\",\"doi\":\"10.46338/ijetae0223_13\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This article presents the pattern recognition solution based on two deep learning modules supporting the robotic manipulator to pick up and drop objects. The first deep learning module performs image processing to recognize identified objects. The second module is used to train object pick and drop tasks based on the recognition results of the first module. To check the feasibility of the proposed pattern recognition solution, several tests are performed on a real robot arm model with 6 degrees of freedom with the constraints of joint variables limited from -170 degrees to 170 degrees. After performing 84 tests in more than 8 hours on GeForce RTX 3080 GPU with changes in object features (shape and colour), pick up or drop location, the statistical results show that the robot can be done exactly as required with up to 94% accuracy with a low-cost USB camera.\",\"PeriodicalId\":169403,\"journal\":{\"name\":\"International Journal of Emerging Technology and Advanced Engineering\",\"volume\":\"16 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-02-04\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"International Journal of Emerging Technology and Advanced Engineering\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.46338/ijetae0223_13\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Emerging Technology and Advanced Engineering","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.46338/ijetae0223_13","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
A Solution of Pattern Recognition Based on Deep Learning for Robotic Manipulator to Pick Up and Drop Objects
This article presents the pattern recognition solution based on two deep learning modules supporting the robotic manipulator to pick up and drop objects. The first deep learning module performs image processing to recognize identified objects. The second module is used to train object pick and drop tasks based on the recognition results of the first module. To check the feasibility of the proposed pattern recognition solution, several tests are performed on a real robot arm model with 6 degrees of freedom with the constraints of joint variables limited from -170 degrees to 170 degrees. After performing 84 tests in more than 8 hours on GeForce RTX 3080 GPU with changes in object features (shape and colour), pick up or drop location, the statistical results show that the robot can be done exactly as required with up to 94% accuracy with a low-cost USB camera.