應用於自動化生產及分揀之物件姿態估測系統
dc.contributor | 許陳鑑 | zh_TW |
dc.contributor | 王偉彥 | zh_TW |
dc.contributor | Hsu, Chen-Chien | en_US |
dc.contributor | Wang, Wei-Yen | en_US |
dc.contributor.author | 陳薪鴻 | zh_TW |
dc.contributor.author | Chen, Hsin-Hung | en_US |
dc.date.accessioned | 2020-10-19T06:46:15Z | |
dc.date.available | 2025-08-31 | |
dc.date.available | 2020-10-19T06:46:15Z | |
dc.date.issued | 2020 | |
dc.description.abstract | 近幾年來,產業為了提升生產效率,大量使用自動化生產設備取代人力,透過電腦視覺與機器運動控制的整合搭配,已大幅增加自動化生產的效率。受惠於GPU計算平台的普及,不論機器學習或是深度學習技術紛紛出現於各種應用場景之中,以往使用電腦視覺方法不能或是難以解決的問題,透過引進深度學習都有出色的表現。本文主要研究內容可分為三部分:第一部分利用輝達(Nvidia)所提出之基於深度學習單攝影機物件姿態估測演算法(Deep Object Pose Estimation, DOPE),其中包含產生物件的立體模型,再匯入Unreal Engine遊戲引擎並搭配輝達深度學習資料集合成器(Nvidia Deep learning Dataset Synthesizer, NDDS)套件,產生訓練數據,用來對神經網路進行權重訓練,完成後即可用來對物件姿態進行估測;第二部分使用加拿大Kinova公司所生產之Jaco 2四軸機械手臂並透過機器人作業系統(Robot Operating System, ROS)完成物件夾取功能;第三部分運用PyQt設計一圖形使用者介面(Graphical User Interface, GUI)整合前兩部分,讓使用者透過單一介面即可獲得物件估測和手臂執行資訊,也可透過其進行參數調整。模擬於生產線上應用,用以輔助加工與分類之程序,達成自動化生產製造之目的。 | zh_TW |
dc.description.abstract | In this thesis, we propose an object pose estimation system for pick and place automation. There are three parts of the system. In the first part, we use a single camera to develop an object pose estimation system based on Deep Object Pose Estimation (DOPE). Then we use a Kinova JACO 2 4-DoF robotic arm to perform object picking through Robot Operating System (ROS). Finally, a Graphical User Interface (GUI) is designed to integrate the pose estimation system and robotic arm, so that users can obtain object estimation and arm execution information through a user friendly interface. To validate the viability, the proposed system is applied to a simplified production line automation environment. The experiment results show the robotic arm is able to properly pick objects base on the pose estimated, thus processing and sorting automation is achieved. | en_US |
dc.description.sponsorship | 電機工程學系 | zh_TW |
dc.identifier | G060775006H | |
dc.identifier.uri | http://etds.lib.ntnu.edu.tw/cgi-bin/gs32/gsweb.cgi?o=dstdcdr&s=id=%22G060775006H%22.&%22.id.& | |
dc.identifier.uri | http://rportal.lib.ntnu.edu.tw:80/handle/20.500.12235/110769 | |
dc.language | 中文 | |
dc.subject | 深度學習 | zh_TW |
dc.subject | 機器人作業系統 | zh_TW |
dc.subject | 物件姿態估測 | zh_TW |
dc.subject | 資料集生成 | zh_TW |
dc.subject | 機械手臂 | zh_TW |
dc.subject | 圖形使用者介面 | zh_TW |
dc.subject | deep learning | en_US |
dc.subject | ROS | en_US |
dc.subject | object pose estimate | en_US |
dc.subject | synthetic data | en_US |
dc.subject | robotic arm | en_US |
dc.subject | GUI | en_US |
dc.title | 應用於自動化生產及分揀之物件姿態估測系統 | zh_TW |
dc.title | Object Pose Estimation System for Pick and Place Automation | en_US |