透過您的圖書館登入
IP:54.208.135.174
  • 學位論文

蟻群最佳化於機械手臂抓取和放置物件之路徑規劃

ACO-based Path Planning for Pick-and-Place Objects of Robot Manipulator

指導教授 : 翁慶昌

摘要


在機械手臂抓取和放置物件的路徑規劃上,本論文以蟻群最佳化演算法提出一個在短時間內可以自行規劃出機械手臂夾具末端點最佳路徑的設計與實現方法。本論文所提方法被用來解決一個機械手臂夾具末端點抓取和放置24個物件的路徑規劃問題,其是依據「上銀科技」所舉辦之「上銀智慧機器手實作競賽」之「眼明手快」比賽項目所建立的。即在一個有24個物件(圓球有4種顏色,每種5顆;正方體有4種顏色,每種1顆)的桌面上,如何規劃一個路徑來讓機械手臂可以依序的抓取桌面上所有圓球與正方體,並且放置到相同顏色與形狀的洞口內。在實驗的驗證上,本論文首先讓系統能夠透過桌面上的攝影機來擷取桌面上的影像,自動辨識與判斷四種顏色之圓球、正方體以及箱子上圓形與正方形洞口,並且建立這些物件的座標,然後應用本論文所提方法來規劃機械手臂抓取桌面上四種顏色的圓球與正方體以及將所抓取的物件放置在正確的箱子洞口內的最短路徑。也就是決定抓取桌面上圓球與正方體之先後順序,再讓機械手臂自主依照這個路徑規劃去依序抓取桌面上圓球與正方體,並且放入相同顏色與形狀的箱子洞口內,讓機械手臂在時間限制內完成任務。由實驗結果可知,所提的方法確實可以很快速的規劃出一個最短的路徑,讓機械手臂以較短的時間完成物件抓取和放置的任務。

並列摘要


In the path planning for the pick-and-place objects of a robot manipulator, a method based on an Ant Colony Optimization (ACO) algorithm is designed and implemented in this thesis. The proposed method is applied to solve the pick-and-place objects problem based on 「Hands-on Competition of HIWIN Intelligent Robot Manipulator」. There are totally 24 objects (four kinds of colors, each color has five balls and a cube) on a table. How to plan a path to let the robot manipulator can efficiently and automatically pick up in sequence all the balls and cubes on the desktop and place them into the same color and shape of the box hole. In the experimental verification, a vision system is constructed so that the desktop image can be captured by one camera placed on the top of desktop, four colors ball and cube and four colors round and square holes on the box can be automatically identified to calculate their coordinates. Then the proposed method is applied to plan a shortest path so that the robot manipulator can pick up all the balls and cubes with four colors on the desktop and place the grabbed object into the same color box hole in sequence. From the experimental results, the proposed method can be very fast indeed plan a shortest path so that the robot manipulator with a shorter time to complete the task of pick-and-place objects.

參考文獻


[12] M. Dorigo and L.M. Gambardella, “Ant colonies for the traveling salesman problem,” BioSystems, vol.43, pp.73-81, 1997.
[13] M. Dorigo and L.M. Gambardella, “Ant colony system: A cooperative learning approach to the traveling salesman problem,” IEEE Transitions on Evolutionary Computation, vol. 1, no. 1, pp.53-66, 1997.
[14] T. Stutzle and H. Hoos, “The MAX-MIN ant system and local search for the traveling salesman problem,” IEEE 4th International Conference on Evolutionary Computation, pp.309-314, 1997.
[17] B. Bullnheimer, R.F. Hartl, and C. Strauss, “Applying the ant system to the vehicle routing problem,” 2nd Metaheuristic International Conference, pp.285-296 ,1999.
[1] FANUC Robotics, URL: http://www.fanucrobotics.com

被引用紀錄


廖哲成(2015)。基於粒子群最佳化演算法之機械手臂的運動學校正〔碩士論文,淡江大學〕。華藝線上圖書館。https://doi.org/10.6846%2fTKU.2015.00066
連思豪(2014)。六軸機械手臂之NURBS插補器設計〔碩士論文,淡江大學〕。華藝線上圖書館。https://doi.org/10.6846%2fTKU.2014.01136
李育昇(2014)。六軸機械手臂與音圈馬達夾爪的設計〔碩士論文,淡江大學〕。華藝線上圖書館。https://doi.org/10.6846%2fTKU.2014.00236

延伸閱讀