設計動態派翠遞迴式模糊類神經網路控制系統應用於自走車避障及路徑追蹤

Design of Dynamic Petri Recurrent-Fuzzy- Neural-Network Control System for Obstacle Avoidance and Path Tracking of Mobile Robot

劉嘉鳴(Chia-Ming Liu)

指導教授 ： 魏榮宗

元智大學/電機通訊學院/電機工程學系/碩士(2009年)

摘要

本篇論文主要目的在於發展動態派翠遞迴式模糊類神經網路控制系統，並將其應用於自走車避障及路徑追蹤。動態派翠遞迴式模糊類神經網路中，將派翠網路和遞迴式架構的觀念引入傳統的模糊類神經網路，以減緩參數學習計算量的負擔以及增加網路對應的能力。首先，本論文採用監督式梯度遞減法來發展動態派翠遞迴式模糊類神經網路的線上調整法則，並且藉由離散型里亞普諾函數決定動態派翠遞迴式模糊類神經網路的學習速率以確保追蹤誤差收斂。為了更進一步強化系統的穩定性，本論文設計強健型動態派翠遞迴式模糊類神經網路控制系統，利用投影法則和里亞普諾穩定理論推導其網路參數調整法則，如此可確保網路參數收斂和系統穩定特性，並且不需要系統資訊以及補償的輔助控制器。本論文藉由自走車在不同路徑的數值模擬與實驗結果可以驗證所提出的路徑追蹤控制系統之有效性。
另一方面，自走車具有感測週遭環境的能力，藉由感測器的資訊可獲知車子與環境的相對位置，並且即時的規劃路徑到達目的地，因此，本論文亦設計一個適應性路徑規劃控制系統，其勿需事先瞭解環境資訊且無需龐大的記憶體空間以及冗餘的計算量；在此系統中，自走車可根據所設計之追蹤模組、避障模組、自旋模組以及狀態選擇逐漸的到達目的地，本論文並以自走車操縱在不同可能發生之障礙物形狀的數值模擬與實驗結果來驗證所設計之適應性路徑規劃控制系統之有效性。

關鍵字

派翠網路 ； 遞迴式架構 ； 模糊類神經網路 ； 里亞普諾函數 ； 強健控制 ； 路徑追蹤 ； 適應控制 ； 路徑規劃 ； 避障 ； 自走車

並列摘要

This thesis focuses on the development of dynamic Petri recurrent fuzzy-neural-network (DPRFNN) control systems, and applies these designed control systems to the obstacle avoidance and path tracking of a nonholonomic mobile robot. In the DPRFNN, the concept of a Petri net (PN) and the recurrent frame of internal feedback loops are incorporated into a traditional fuzzy neural network (FNN) to alleviate the computation burden of parameter learning and to enhance the dynamic mapping of network ability. First, the supervised gradient descent method is used to develop the online training algorithm for the DPRFNN control, and analytical methods based on a discrete-type Lyapunov function are proposed to determine its varied learning rates for ensuring the convergence of path tracking errors. Moreover, a robust DPRFNN control system is designed to further enhance the system stability, and the corresponding adaptation laws of network parameters are established in the sense of projection algorithm and Lyapunov stability theorem to ensure the network convergence as well as stable control performance without the requirement of detailed system information and the compensation of auxiliary controllers. In addition, the effectiveness of the proposed path-tracking control schemes under different moving paths is verified by numerical simulations and experimental results.
On the other hand, the mobile robot is capable of sensing its surrounding environment, interpreting the sensed information to obtain the knowledge of its location and the environment, planning a real-time trajectory to reach the object. Thus, an adaptive path-planning control scheme is also designed without detailed environmental information, large memory size and heavy computation burden in this thesis for the obstacle avoidance of a mobile robot. In this scheme, the robot can gradually approach its object according to the motion tracking mode, obstacle avoidance mode, self-rotation mode, and robot state selection. The effectiveness of the proposed adaptive path-planning control scheme is verified by numerical simulations and experimental results of a differential-driving mobile robot under the possible occurrence of obstacle shapes.

並列關鍵字

Petri net ； Recurrent structure ； Fuzzy neural network ； Lyapunov function ； Robust control ； Path tracking ； Adaptive control ； Path planning ； Obstacle avoidance ； Mobile robot

參考文獻

[1] J. Palac?n, J. A. Salse, I. Valga??n, and X. Clua, “Building a mobile robot for a floor-cleaning operation in domestic environments,” IEEE Trans. Instrum. Meas., vol. 53, no. 5, pp. 1418-1424, 2004.

[3] T. Yamaguchi, E. Sato, and Y. Takama, “Intelligent space and human centered robotics,” IEEE Trans. Ind. Electron., vol. 50, no. 5, pp. 881-889, 2003.

[4] J. M. Lee, K. Son, M. C. Lee, J. W. Choi, S. H. Han, and M. H. Lee, “Localization of a mobile robot using the image of a moving object,” IEEE Trans. Ind. Electron., vol. 50, no. 3, pp. 612-619, 2003.

[5] S. Y. Oh, J. H. Lee, and D. H. Choi, “A new reinforcement learning vehicle control architecture for vision-based road following,” IEEE. Trans. Vehicular Technol., vol. 49, no. 3, pp. 997-1005, 2000.

[6] T. C. Lee, C. Y. Tsai, and K. T. Song, “Fast parking control of mobile robots: a motion planning approach with experimental validation,” IEEE Trans. Contr. Syst. Technol., vol. 12, no. 5, pp. 661-676, 2004.