基于聚类匹配的移动机器人地图实时创建算法

摘要

提出了一种基于模式识别聚类思想的数据点集匹配算法.该匹配算法具有传统迭代匹配算法和非迭代匹配算法的优点,匹配速度快,精度高.结合上述匹配算法,给出了一种基于激光测距仪的移动机器人环境地图实时创建方法.该方法使用从环境数据中提取出的特征点来完成两组激光数据点集的匹配,进而完成环境地图的创建.利用本实验室自主研发的救援机器人平台对该算法进行了验证,实验结果表明,该算法能够完成室内环境下移动机器人实时准确有效的环境地图创建.%A new laser scan matching method based on clustering was advanced. It took the advantages of both non-iterative matching method and iterative matching method and increased the speed and the precision of matching. A method of map building based on laser scans using the matching method above was presented for mobile robots. The map building method matched two consecutive scans according to the feature points extracted from the scans and then completed the whole map building. In the experiment of rescue robot developed by our laboratory, the new method can accomplish the task of real-time map building in indoor environment accurately and effectively.