應用強化式學習於模組化機器人

Application of Reinforcement Learning to Modular Robot

王志平(Chih-Ping Wang)

指導教授 ： 林彥正

大同大學/工程學院/機械工程學系所/碩士(2006年)

摘要

機械人的運動學模式和機械人系統、視覺系統間的關係都會因為重新裝配模組化機械人而改變。在本研究中，為解決使用者可能碰到的問題，試著用強化式學習訓練機器人控制器，使手臂末端到達照相機取得的影像中心。然而強化式學習費時，這裡利用階段式學習來降低學習時間，並且利用模擬來減少機器人線上學習時危險移動的可能性，學習完成後結果將會用來控制實際的機器人。改變相機相對於機器人於不同位置，此方法皆可行。

關鍵字

強化式學習 ； 模組化機器人

並列摘要

After the reconfiguration of the modular robot, the inverse kinematics of robot and the relationship between robot system and vision system have to be determined. In this research, it is attempted to save the problem from users by training robot controller to move the end-effector to the center of the image took by camera with reinforcement learning. However, reinforcement learning is time-consuming and a hierarchical method is applied to reduce the time of learning. Also, to lessen the possibility of hazardous action during learning, it is done in simulation. After the completion of learning, the knowledge gained is used to control the real robot. The method is feasible for different relative positions between robot and camera.

並列關鍵字

Reinforcement Learning ； Modular Robot

參考文獻

[3] Sutton, R. S., and Barto, A. G, “inforcement learning: An introduction. “, MIT Press, 1998.

[4] Doya, K., “Reinforcement Learning in Continuous Time and Space”, Neural Computation, 12, pp.219-245, 2000.

[5] Morimoto, and Doya, K,” Acquisition of Stand-up Behavior by a Real Robot using Hierarchical Reinforcement Learning”, Proceedings of the Seventeenth International Conference on Machine Learning.

[7] Weber*, C., Wermter, S., and Zochios, A.,” Robot docking with neural vision and reinforcement”, Knowledge-Based Systems 17, pp. 165–172, 2004.

[11] Chen,J. L.,” Calibration of Modular Robot Using a Vision System” Thesis of Mechanical Engineering, Tatung University, July 2004.