移动机器人的同时定位和地图创建方法

Simultaneous localization and map building for mobile robot

通过声纳传感器实时地创建和修正地图,局部地图是基于栅格的概率模型:工作环境被划分成栅格,每一个栅格赋一个值,标识栅格中有障碍物的概率.地图应用哈夫变换创建,定位通过对超声波数据应用滤波算法并结合地图创建实现.使用Pioneer2移动机器人在实际的室内环境中的实验,验证了该方法的可行性.

A map is built and updated immediately through sonar sensor. The local map is a grid-based probabilistic model: the work environment is decomposed into grids and every grid takes up a value, which indicates the probability of an obstacle in grids. The map is built through Hough transform. The map building combines with the sonar data obtained from a filter algorithm to realize the localization. Experimental results show the feasibility of this method.