首页> 外国专利> METHOD FOR DETECTING OBSTACLE FOR AUTONOMOUS NAVIGATION OF MOBILE ROBOT IN A LIMITRED SPACE

METHOD FOR DETECTING OBSTACLE FOR AUTONOMOUS NAVIGATION OF MOBILE ROBOT IN A LIMITRED SPACE

机译:有限空间中移动机器人自主导航的检测方法

摘要

The present invention relates to a method of detecting an obstacle for the autonomous driving of a moving robot in a limited space, capable of increasing the stability of an autonomous driving robot based on artificial intelligence, which is used for short-distance driving such as human or material transportation and surveillance in a complex such as a university campus, a company, an institution, a town or the like, under a precondition suitable for the purpose. The method of detecting an obstacle for the autonomous driving of a moving robot in a limited space, which is used to track an autonomous driving robot in a predetermined complex through GPS and a stereo camera and estimate a route and calculate an obstacle in accordance with a result of the tracking, includes the following steps: enabling the robot to collect image information through the stereo camera; obtaining a depth image by pixel from the collected image information; data-filtering the obtained image to separate plane information and other information; recognizing information excluding plane information which is linear as an obstacle from the filtered information; dividing the location of the obstacle into three areas to determine which of the areas the obstacle is located in; and outputting a warning sound changing depending on the areas. Therefore, since a robot is operated in a state in which a load is applied, a quick movement of the robot can be guaranteed and the memory and calculation volume of the robot can be configured in a small size.
机译:本发明涉及一种用于在有限空间内检测运动机器人自动驾驶的障碍物的方法,该方法能够提高基于人工智能的自动驾驶机器人的稳定性,该方法用于诸如人的短距离驾驶。或在适合于此目的的前提下,在大学校园,公司,机构,城镇等类似建筑中进行物料运输和监视。一种在有限空间内检测移动机器人自动驾驶障碍物的方法,该方法用于通过GPS和立体摄像机跟踪预定复合体中的自动驾驶机器人并估算路线并根据障碍物计算出障碍物。跟踪的结果包括以下步骤:使机器人能够通过立体相机收集图像信息;从收集到的图像信息中逐像素获取深度图像;对获得的图像进行数据滤波以分离平面信息和其他信息;从过滤后的信息中识别出除了作为障碍物的线性信息以外的平面信息的信息;将障碍物的位置分为三个区域,以确定障碍物位于哪个区域;并输出根据区域而变化的警告声音。因此,由于机器人在施加负载的状态下操作,因此可以确保机器人的快速运动,并且可以以小尺寸配置机器人的存储器和计算量。

著录项

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号