自走式機器人在未知環境之路徑規劃與執行

Abstract

在本文中，我們提出一種新的自走式機器人基於即時感測資訊的路徑規劃 方法，此法是基於一個啟發性模糊類神經網路的架構來完成，目的是要使 自走式機器人能夠運用本身具備之感應能力在完全未知的環境中安全又有 效的到達目的地。此啟發性網路的輸入是量化後的超音波感測值，輸出則 為兩輪的速度命令。本方法允許自走式機器人連續又快速的運動，不會因 障礙物而停止。我們以一些模擬和實驗結果驗證了本方法的可行性。 In this paper we present a new method of local path-planning for a mobile robot based on the structure of a heuristic fuzzy- neuro network. The design goal is to facilitate a mobile robot to reach the target position safely and efficiently in a completely unknown environment. The inputs of the network are quantitized ultrasonic sensor data. The outputs are velocity commands to motor controller. The method is computationally efficient, robust, and insensitiveto sensor misreadings. It allows continuous and fast motion of the mobile robot without stopping by obstacles. The effectiveness of the proposed method is demonstrated by a series of simulations and experiments.