- 學位論文
應用於自動駕駛系統中具有避障功能之智慧型車道跟隨控制設計
Intelligent Lane Following Control Design with Obstacle Avoidance for Self-Driving Systems
摘要
本文提出了一種智能自動駕駛系統，用於自動車道跟踪和避障。所提出的智能自動駕駛車輛平台包含三個紅外傳感器和一個攝像頭。利用從攝像機和那些傳感器獲得的信息，我們可以獲得非常清晰的車道跟踪點和障礙物的距離。這種智能自驅動系統的結構大致可分為兩部分：傳感和決策。 在傳感部分的工作中，系統主要處理由圖像和紅外光獲得的信息。基於檢測到的車道標記，確定車輛的相對位置以查看其是否在其車道內或者已經漂移到車道外。在決策部分，我們提出的自動駕駛車輛可以根據模糊控制策略跟隨車道，包括車道跟隨機制和自動緊急避障。此外，如果在該系統前面存在慢車輛，則自動駕駛車輛能夠改變車道並穩定地跟隨另一車道。 結果，所提出的自動駕駛車輛可以成功地操縱以穩定地保持在適當的車道中。當遇到障礙物時，車輛具有盡可能避免事故的潛力。給出了一些實際的實施結果，說明我們提出的自動駕駛系統確實可以通過避障來實現車道跟隨目的。
並列摘要
This thesis presents an intelligent self-driving system for the purpose of automatic lane following with obstacle avoidance. The proposed intelligent self-driving vehicle platform contains three infrared sensors and a camera. With the information obtained from the camera and those sensors, we can obtain a very clear lane tracking point and the distance of obstacle. The structure of this intelligent self-driving system can be roughly divided into two parts: sensing and decision making. In the works of the sensing part, the system mainly deals with the information obtained by the images and the infrared light. Based on the detected lane markings, the relative position of vehicle is determined to see whether it is within its lane or it has drifted outside the lane. In the part of decision-making, our proposed self-driving vehicle can follow the lanes according to the fuzzy control strategy, which includes the mechanism of the lane following and automatic emergency obstacle avoidance. In addition, if there is a slow vehicle in front of this system, the self-driving vehicle has the capability to change lane and follow the other lane stably. As a result, the proposed self-driving vehicle can successfully manipulate for keeping in the appropriate lane stably. When encountering obstacles, the vehicle has the potentials to avoid accidents as much as possible. Some practical implementation results are given to illustrate that our proposed self-driving system can indeed achieve the lane following purpose with obstacle avoidance.