- 學位論文
運用即時視覺伺服之機械手臂混合模糊控制系統
Hybrid Fuzzy Control of a Robotic Manipulator Employing Real-Time Visual Servoing
摘要
在混合力量與姿態的控制方法中,通常使用高維度力量感測器量測未知曲面法向量,但高維度的力量感測器價格不菲,對使用者是一不小的負擔。為改善上述問題,可採用以視覺為主,輔以雷射投影器及低維度力量感測器的架構,不僅大幅地降低成本,且與高維度力量感測器有相同效果。本論文中分別針對三種架構設計並實現混合模糊控制目標,第一種為眼在手架構,利用單眼視覺與雷射十字投影器來完成三維未知曲面的法向量重建。第二種為眼看手架構,其中的定位及姿態任務又分為兩種模式,其一為單眼視覺搭配雷射十字投影器並輔以力量感測器,其二則是雙眼視覺與雷射十字投影器的搭配。第三種架構則是混合雙眼眼看手的定位任務以及單眼眼在手的姿態控制任務,進行精度較高的控制。各種架構待定位及姿態控制任務完成後,結合力量控制對機械手臂進行定位及姿態的控制,進行鑽孔、插銷及鎖螺絲等精密加工任務。本論文以六軸機械手臂分別進行眼在手、眼看手以及整合眼在手與眼看手架構的實驗,成功驗證所提出之混合模糊控制器於三種架構的可行性。
並列摘要
Hybrid force and pose control would typically use an expensive high dimensional force sensor in addition to vision sensors. In contast to traditional approaches, a low-cost single-axis force sensor together with CCD cameras and a laser projector can be applied to carry out hybrid fuzzy force and pose control of a robotic manipulator on 3-D surfaces. Specifically, design of hybrid fuzzy control approaches has been applied to three visual servoing configurations, eye-in-hand, eye-to-hand, and integrated eye-in-hand and eye-to-hand. After visually determining the direction normal to a 3-D surface at any given location projected by the laser projector, a robotic manipulator equipped with a low-cost single-axis force sensor is able to perform hybrid fuzzy force and pose control for drilling, bolting, and screw locking tasks. The proposed approaches have been successfully validated on 3-D surfaces by performing experiments with an industrial robotic manipulator.