- 學位論文
結合改良式立體視覺與顏色辨識於機械手臂夾物之研究
A Study on Integration of Modified Stereo Vision and Color Recognition into a Robotic Arm for Grabbing Objects
摘要
本文使用一部具有二台攝影機建構之立體視覺系統及末端致動器為夾爪之5軸機器手臂，拍攝環境影像後，利用影像處理及改良式立體視覺演算法進行目標物之偵測及顏色辨識，藉此引導機械手臂動作，再由末端夾爪精準的抓取位於空間中的目標物。此研究大致分為三個重要部份：第一部份為具有二個旋轉自由度的雙眼視覺系統，可模擬人類的頭部及雙眼運動，對空間中的目標物進行偵測及識別，並搭配改良式立體視覺演算法計算目標物與機械手臂的三維相對位置；第二部份為機械手臂的設計，其第一軸採中空旋轉平台設計，仿人類的腰部功能，負責調整機器手臂的工作面向；其餘為由4部步進馬達設計而成的右手臂型式，最後一軸的末端致動器為夾爪型式，可夾取物體；第三部份為機械手臂及立體視覺系統的個人電腦控制器，包含多軸運動控制卡、影像擷取卡等硬體，及影像處理、立體視覺等軟體程式，當偵測及辨識得到目標物位置之後，藉由機器人逆向運動學轉換得到機械手臂各軸馬達所需轉動的角度，使之能抓取工作範圍內的目標物並移動至指定位置。
並列摘要
In this study, a robotic arm that has a stereovision system constructed by dual cameras and five degrees of freedom with its end-effector attached a clamp is designed for detecting and recognizing specified objects in the working environment by using image processing and modified stereovision algorithm. It also could recognize an object’s colors or detection moving object, and then to guide the end-effector of the robotic arm to grab objects accurately in the working environment. This study consists of three major parts. The first part is the vision system, which composed of two cameras and two motors to simulate human’s vision system. The second part is the design of this robotic arm which has a hollow rotary stage used to control the direction of this robotic arm, and the other is a right-hand-type arm composed of four stepper motors. The third part is a PC-based controller, including hardware such as image capture card and multi-axis motion control card, and software such as image processing programs and the modified stereovision algorithm. Therefore, the stereovision system can calculate the three-dimensional coordinates between objects and the robotic arm by using image processing methods and a modified stereovision algorithm. This system can also calculate the rotating angle of every stepped motor by adopting robot inverse kinematics. Finally, the end-effector can grab all specified objects and move them to the appointed destination.