應用強化式學習於視覺機器人的位置控制

Application of Reinforcement Learning to Vision Robot Position Control

連振宇(Chen-yu Lien)

指導教授 ： 林彥正

大同大學/工程學院/機械工程學系所/碩士(2008年)

摘要

每當相機與機器人的相對位置改變，兩者間的關係必須重新推導。為了讓系統能夠自動建立機器人運動與取像結果之間的關係，我們使用強化式學習來訓練機器人的控制器。利用影像中機械手臂末端與目標點的相對位置,機器人被訓練移動機器手臂末端到達影像上使用者所指定的任何區域。為了減少機器人危險移動的可能性以及減少學習的時間，先用模擬來做離線學習。再利用離線學習到的結果進一步讓機器人做線上學習。學習完成後可控制機器手臂到達影像上使用者所指定的任何區域。

關鍵字

強化式學習 ； 視覺機器人 ； 位置控制

並列摘要

The relationship between robot system and vision system has to be determined whenever the relative positions between robot and camera is changed. In order to determine the relationship between robot system and vision system automatically, we use reinforcement learning to train robot controller. According to the relative position between the end-effector and target in the image took by camera, the robot is trained to move the end-effector to the any target area assigned by user in the image took by camera. To lessen the possibility of hazardous action and reduce the time of learning, it is first done off-line in simulation. Then, using data obtained from off-line learning, on-line learning is executed on real robot. After the completion of learning, the knowledge gained is used to control the real robot to move the end-effector to the any target area assigned by user in the image took by camera.

並列關鍵字

Position Control ； Reinforcement Learning ； Vision Robot

參考文獻

[1] J. Mochizuki, M. Takahashi, and S. Hata, “Unpositioned Workpieces Handling Robot with Visual and Force Sensors”, Industrial Electronics, IEEE Transactions on, Vol.IE-34, Issue: 1, pp.1-4, Feb 1987.

[2] W. F. Clocksin, J. S. E. Bromley, P. G. Davey, A. R. Vidler, and C. G. Morgan, “An Implementation of Model-Based Visual Feedback for Robot Arc Welding of Thin Sheet Steel”, The International Journal of Robotics Research, Vol. 4, No. 1, pp. 13-26, 1985.

[4] B. Carlisle, S. Roth, J. Gleason and D. Mcghie, “The Puma/VS-100 Robot Vision System”, Proceeding of the First International Conference on Robot Vision and Sensory Controls, pp.149-160, 1981.

[6] Takahito Oshiro and Kajiro Watanabe, “Motion simulation of robot arm using reinforcement learning”, SICE 2007 Annual Conference, pp.1077 – 1080, Sept17-20, 2007.

[8] C. P. Wang, “Application of Reinforcement Learning to Modular Robot”, Thesis for Master of Science, Department of Mechanical Engineering, Tatung University, July 2006.