撞球機器人之擊球決策設計

The Design of Shooting Strategy for a Billiard Robot

蘇裕淵(Yu-Yuan Su)

指導教授 ： 楊智旭

淡江大學/工學院/機械與機電工程學系碩士班/碩士(2010年)

https://doi.org/10.6846/TKU.2010.01008

摘要

本論文主要目的是應用可拓理論設計撞球機器人的擊球決策系統，整合撞球機器人各種擊球杆法，並加入模糊力道控制機制，使撞球機器人能夠自主判斷球局，決定使用何種擊球方式，實現撞球機器人在多種球局狀況下之攻擊與防守的擊球能力。
首先由CCD攝影機擷取影像，利用影像處理技術找出各球之顏色及球心座標，再以所撰寫之VB程式判斷是否有障礙球及障礙球的位置；在球局中，撞球機器人可以利用所設計之可拓擊球決策，判斷目前球局應該採取進攻或防守之擊球方式，再分別以直線攻擊、組合球攻擊、灌球攻擊、跳球攻擊、顆星攻擊、無障礙球局的安全球防守及障礙球局的顆星防守等七種擊球方式，令撞球機器人完成擊球進袋或是解球的動作，並利用所設計之模糊力道控制器，使機器人在擊球時能因應不同的距離及角度，計算適當的擊球力道。當機器人判斷為防守球局時，則整合過去之研究成果，使機器人執行在無障礙球局之安全球防守或是在障礙球局之顆星防守以達到解球目的。即是以智慧型決策系統搭配多元的擊球方式，賦予撞球機器人更完善的擊球能力，使撞球機器人之決策思維能更接近撞球選手的思考模式。
在機械視覺系統中，由攝影機擷取球檯上的影像，經由VB程式計算之後，得到母球行進至虛擬撞擊點的距離、子球與目標球袋之距離、擊球角以及障礙球位置判斷，作為擊球決策的衡量條件，判斷應採取攻擊或防守。經由實驗結果得知，所設計之擊球決策系統，確實可達成攻擊及防守的目的，同時在力道控制器的設計，則使用重心法配合模糊控制模擬並實現在實際的打擊上，由實驗得知，撞球機器人可確實因應距離及角度的變化，輸出適當的力道。撞球機器人擁有的五種攻擊擊球方式以及兩種防守擊球方式，可在多種球局下達到攻守兼備的目標。

關鍵字

撞球機器人 ； 可拓理論 ； 模糊理論 ； 可拓擊球決策

並列摘要

The object of this thesis is to develop the shooting strategy system for a billiard robot by using Extension theory and the shooting strength controller by using Fuzzy theory. The main purpose is to make billiard robot possess the imitation ability of how human beings to do shooting strategy of nine-balls pool games.
First, the CCD camera captures the image of the balls on the pool table. Then, the positions of the balls are calculated by the image processing technique and the develop software (Visual Basic). In nine-ball pool games, the shooting mode can be decided by the developed shooting strategy. This study combines seven shooting mode of billiard robot. There are straight shot, cushion shot, bank shot, kiss shot, jump shot, safety play and cushion defense shot. The shooting strategy is developed by the following four conditions. They are (1) distance between cue ball and the object ball, (2) distance between object ball and the corresponding pocket, (3) the angles between the cue ball, the object ball and the corresponding pocket and (4) the information of the block ball. Finally the billiard robot will execute the shooting command of the decided shooting mode. This study also develops pocketing successful rate by experiment. If the successful rate is larger than 50%, then the billiard robot would execute offensive shooting mode. If the successful rate is less than 50% billiard robot would execute defensive shooting mode. The shooting strength controller is also developed by using Fuzzy theory.
The simulated and experimental results show that the shooting strategy can make billiard robot choose the best offensive/or defensive shooting mode for pool games like human beings. And, the strength controller can be applied to adjust the shooting strength of each shooting mode of the billiard robot.

並列關鍵字

Billiard robot ； Extension theory ； Fuzzy theory ； Extension shooting strategy

參考文獻

[19]黎哲廷，撞球機器人在九號球局之應用，淡江大學機械與機電工程學系碩士論文，民國94年6月。

[23]劉家孝，撞球機器人之顆星攻守決策系統設計，淡江大學機械與機電工程學系碩士論文，民國97年6月。

[24]陳宥穆，撞球機器人之跳球決策系統設計，淡江大學機械與機電工程學系碩士論文，民國98年6月。

[2]T. Jebara, C. Eyster, “Augmenting the Billiards Experience with Probabilistic Vision and Wearable Computers,” IEEE Wearable Computers, October 1997, Vol.13 pp. 138 – 145.

[4]H. Nakama, I. Takaesu and H. Tokashiki, “Basic Study on Development of Shooting Mechanism for Billiard Robot,” JSME, Robotic Workshop, 2001.