智慧型自組織小腦模型控制器應用於汽車控制設計

Intelligent Self-Organizing Cerebellar Model Articulation Controller for Car Control Design

李欣懌(Hsin-Yi Li)

指導教授 ： 林志民

元智大學/電機通訊學院/電機工程學系/碩士(2009年)

摘要

本論文主要針對小腦模型控制器進行設計，並結合適應控制、監督式控制以及自組織控制設計技巧，來提出自組織小腦模型控制器，並應用於閉迴路系統的控制上。在監督式自組織小腦模型控制器設計上，防鎖死剎車系統與汽車追隨控制問題可視為一個追蹤問題，利用監督式自組織小腦模型控制器來控制可獲得非常不錯的結果。最後，將發展多輸入多輸出的自組織小腦模型控制器，並應用於變換車道系統的控制上。最後經由模擬的結果顯示，對於這些系統，本論文所提出的控制器均能獲得滿足的控制性能。除了使用matlab進行模擬外，同時也利用虛擬實境(VR)技術進行模擬，在VR系統，利用3D Studio MAX建構場景，並使用3D動畫開發工具Virtual Reality來製作整個動作流程，並藉由此虛擬實境來呈現車輛的動作，驗證本論文所提出的控制法則對於汽車控制能達到良好的控制效能。

關鍵字

自組織小腦模型控制器 ； 汽車控制設計

並列摘要

This thesis focuses on the design of the Cerebellar Model Articulation Controller (CMAC) based on adaptive control, supervisory control and self-organizing control, which attempt to provide a comprehensive treatment of CMACs in closed-loop control applications. For supervisory self-organizing Cerebellar Model Articulation Controller, the antilock braking systems (ABS) and the car-following control system are formulated as the tracking problems. The supervisory self-organizing Cerebellar Model Articulation Controller is designed to achieve satisfactory tracking performance for antilock braking system and car-following control system. Finally, a design method of self-organizing CMAC for multi-input multi output nonlinear is developed and is applied to lane-change control system. From the simulation results, the proposed intelligent control techniques have been shown to achieve satisfactory control performance for the considered nonlinear systems. In addition to using matlab’s simulations, the virtual reality (VR) simulations are also carried out. In the VR system, the 3D Studio MAX is used to construct the scenes, and use the 3D animation development tool Virtual Reality is used to program the entire playing process. Moreover, the virtual reality technique is applied to show the motion of vehicles. The simulation results are illustrated to validate the proposed control method for car control applications.

並列關鍵字

Self-Organizing of Cerebellar Model Articulation Controller ； Car Control Design

參考文獻

[1] K. S. Narendra and K. Parthasara thy , “Identification and control of dynamical systems using neural networks,” IEEE Trans. Neural Networks, vol. 1, no. 1, pp. 4-27, 1990.

[2] R. M. Sanner and J.-J. E. Slotine, “Gaussian networks for direct adaptive control,” IEEE Trans. Neural Networks, vol. 3, no. 6, pp. 837-863, 1992.

[3] A. Agarwal, “ A systematic classification of neural-network-based control,” IEEE Contr. Syst. Mag., vol. 17, pp. 75-93, 1997.

[4] F. L. Lewis, A. Yesildirek, and K. Liu, “Multilayer neural-net robot controller with guaranteed tracking performance,” IEEE Trans. Neural Networks, vol. 7, no. 2, pp. 388-399, 1996.

[5] K, Nam, “Stabilization of feedback linearizable systems using radial basis function network,” IEEE Trans. Automatic Control, vol. 44, no. 5, pp. 1026-1031, 1999.