以模糊類神經為基礎的適應性導航控制

Abstract

在智慧型運輸系統（ITS）中的先進車輛控制與安全系統裡，適應性導航控制（ACC）系統扮演著一個相當重要的角色。當前方有車輛時，ACC系統會進到跟車模式，跟隨前方的車輛並保持一定的安全距離；當前方沒有車輛時，ACC 系統會自動切換到定速模式，以一個預先設定的速度行駛。其中車輛油門與煞車的角度及切換的根據主要是依據車輛上的感測器，來偵測與前方車輛的相對速度及相對距離。在這裡我們利用模糊類神經網路來設計我們的控制器。利用模糊類神經網路的好處在於我們不需要知道複雜非線性的車輛動態模型。而且類神經網路具有學習的功能，可以透過學習使控制器適用於各種車輛。我們將ACC控制器分為三個部分：第一個部分是根據目前的交通狀況（相對速度及相對距離）和駕駛者的駕駛型式來決定車子需要多少加（減）速度；第二個部分是根據目前的車速及第一個部分所得到的加（減）速度來決定車子應該加多少油門或踩多少煞車；第三個部分則是用來補償誤差及干擾的。我們利用MATLAB程式在電腦上模擬真實的車輛及真實的環境，並同時考慮駕車舒適度及系統延遲時間來檢驗ACC控制器的性能。根據模擬結果顯示，所提出以模糊類神經網路為基礎的控制器可以提供一個安全、舒適和便利的駕駛，而且可以自動切換於跟車與定速兩種模式。

Adaptive Cruise Control (ACC) System is an important part of the Advanced Vehicle Control and Safety System (AVCSS) in Intelligent Transportation Systems (ITS). In this thesis we design an ACC controller based on fuzzy neural networks for following a leading vehicle to achieve the desired safety distance, or cruising at the pre-selected speed. The transmission between the two maneuvers is carried out automatically. The advantage of using fuzzy neural networks is that it doesn’t require the complete knowledge of nonlinear vehicle dynamics, and it can be applied to any vehicle regardless of its nonlinear or unobservable dynamics. We separate the ACC controller into three parts. The first one is used to determine the desired acceleration according to the current traffic situation (relative speed and relative distance) and driver’s driving style, the second one is used to determine the throttle angle or braking command depending on the current vehicle speed and desired acceleration, and the last one is used to compensate the modeling error and disturbances. The performance of ACC controller is evaluated based on a complex traffic model, which includes the accurate nonlinear vehicle dynamic model and various environments, and simulated by a computer with MATLAB software. The vehicle is assumed to be equipped with sensors that can measure the relative distance and vehicle speed. In addition, we also take maximum allowable jerks and the system delay into account. The fuzzy logic and neural networks based controller proposed in this thesis provides a safe, convenient and comfortable driving assistance system. The controller can switch between car following and cruise control automatically.