整合力矩控制與重心估測並利用增強式學習提升雙足機器人行走穩定性

Integration of CoG Estimation and Torque Control and Utilizing Reinforcement Learning to Enhance Walking Stability in Bipedal Robots

鄭逸倫(Yi-Lun Cheng)

指導教授 ： 葉廷仁

國立清華大學/工學院/動力機械工程學系/碩士(2018年)

摘要

本研究旨在透過強化式學習並整合重心估測與力矩控制提昇雙足機器人行走穩定性。本實驗室原已利用重心自適應控制器完成雙足機器人之平衡控制，其利用滑車模型(Cart-Table Model)作為機器人動態模型，並以串聯彈性致動器(Series Elastic Actuator)構成的踝關節作為力矩輸入，再透過重心自適應控制器將實際系統存在的重心偏差納入考量，完成平衡控制。本研究以此為基礎，將擺動腳質量加入考慮，設計雙滑車模型用於機器人行走模型之規劃，將機器人質心軌跡及擺動腳軌跡同時規劃，使機器人能以貼近自身動態的軌跡向前行走。此外，由於機器人行走時腳部擺動造成的角動量使機器人行走方向不穩定，本研究亦提出一增強式學習架構，利用手部擺動以及髖關節旋轉使機器人行走方向更加穩定。

關鍵字

雙足機器人 ； 串聯彈性致動器 ； 重心自適應控制器 ； 雙滑車模型 ； 行走軌跡規劃 ； 增強式學習

並列摘要

This thesis aims to improve walking stability in bipedal robots through integrate torque control and CoG estimation. In addition, we utilize reinforcement learning to make walking direction of the robot more straight. The cart table model is used as dynamic model of the robot. In order to use ankle torque as torque input of the system, the ankle of the robot is consisting of series elastic actuator. Because of the change of robot’s posture or measurement errors, CoG may not be at the ideal place. So, we use a controller that can automatically estimate the bias of the CoG. Based on the dynamic model and the controller above. We take the mass of the swing leg into consideration and propose a model named "double cart-table model" to generate walking pattern. The double cart table model simultaneously plans the robot’s upper body centroid and the end point of swing leg trajectory by using two equivalent masses. In this way, the robot can walk forward with a trajectory which is close to its own dynamics. Furthermore, the angular momentum caused by swing leg during walking period makes the walking direction of the robot unstable. This study then proposes a reinforcement learning method to make it more stable.

並列關鍵字

biped robot ； series elastic actuator ； torque control ； trajectory planning ； reinforcement learning

參考文獻

[1] "Pepper," Aldebaran Robotics, SoftBank Robotics Corp., [Online]. Available:https://www.ald.softbankrobotics.com/en/coolrobots-/pepper.

[2] "Zenbo," ASUSTeK Computer Inc., [Online]. Available: https://zenbo.asus.com/tw/.

[3] T. McGeer, "Passive dynamic walking," The international journal of robotics research, vol. 2, no. 9, pp. 62-82, 1990.

[4] "ASIMO," Honda Motor Co., Ltd., [Online]. Available: http://asimo.honda.com/.

[5] "Atlas," Boston Dynamics, [Online]. Available: https://www.bostondynamics.com/atlas.