基於滑動模式之適應模糊與動態類神經控制器設計對雙足機器人的控制

SLIDING MODEL CONTROL BASED ADAPTIVEFUZZY AND DRCNN CONTROLLER DESIGN FOR BIPED ROBOT SYSTEMS

林佳奇(Chia-Chi Lin)

指導教授 ： 游文雄

大同大學/電機資訊學院/電機工程學系所/碩士(2011年)

摘要

在本篇論文中我們對雙足機器人提出一基於滑動模式的動態遞迴小腦類神經。 動態遞迴小腦類神經觀察器是設計來估測雙足機器人的不確定項。對雙足機器人設計一結合主要控制器與補償控制器的混和控制系統。主要控制包含模糊適應估測器和動態遞迴小腦類神經觀察器，補償控制器是針對系統不確定性的近似誤差做補償。模糊適應控制器使用兩個更新法則來訓練模糊系統的權重和近似誤差。接著，應用泰勒線性化的方法來增加動態遞迴小腦類神經的學習能力。藉由李亞普諾夫的穩定性準則、芭芭拉的推論法則和泰勒線性化的方法來推導出控制系統的適應法則並且同時增加動態遞迴小腦類神經的學習能力，使得系統可以達到漸近穩定的目的。最後，模擬與實驗的結果證實所提出之混和控制器對雙足機器人控制的有效性和追蹤性能。

關鍵字

類神經 ； 模糊 ； 雙足機器人

並列摘要

In this thesis, a dynamic recurrent cerebellar neural network (DRCNN) based on
sliding-mode echnique is proposed for biped robotic systems. The DRCNN observer
is designed for estimating the uncertain of biped robotic systems. A hybrid control system, integrating principal and compensation controller, is developed for biped robotic systems. The principal controller containing an adaptive fuzzy estimator and a DRCNN observer is the main controller, and the compensation controller is a compensator for the approximation error of the system uncertainty. The adaptive fuzzy controller uses two update laws to train the weights and approximation error estimator of the fuzzy system. The Taylor linearization is employed to increase thelearning ability of DRCNN. By Lyapunov stability theorem and Barbalat’s lemma, the adaptive laws of the control system are derived so that the asymptotical stability of the system can be guaranteed. Finally, simulation and experiment results demonstrate the effectiveness, tracking performance of the proposed control scheme for biped robotic systems.

並列關鍵字

neural network ； biped robot ； fuzzy

參考文獻

[2] K. Loffler, M. Gienger, F. Pfeiffer, and H. Ulbrich, ”Sensors and control concept of a biped robot,” IEEE Trans. Ind. Electron., vol. 51, no. 5,pp. 972-980, 2004.

[3] J. Furusho and A. Sano, ”Sensor-based control of a nine-link biped,” Int. J.Robot. Res., vol. 9, no. 2, pp. 83-98, 1990.

[5] Y. F. Zheng and H. Hemami, ”Impact effects of biped contact with the environment,”IEEE Systems, Man, and Cybernetics Society, vol. SMC-14, no. 3,pp.437-443, 1984.

[6] G. A Medrano Cerda and E. E. Eldukhri, ”Biped robot locomotion in the

[8] C. Chevallereau, D. Djoudi, and J. W. Grizzle, ”Stable bipedal walking with foot rotation through direct regulation of the zero moment point,” IEEE Trans. on Robotics, vol. 24, no. 2, Apr. 2008.