Mobile robot map building based on laser ranging and kinect

摘要

Restricted by environmental noise and the sensor itself performances, environmental information collected by various sensors of mobile robot has certain uncertainty. Laser Range Finder (LRF) has high precise measurement and large measuring range, but it can only acquire the environment information at a certain level, especially, it is unable to detect obstacles below the level of LRF measuring, so the environmental map that derived by it is incomplete. Microsoft Kinect sensor is a new kind of range camera, it has advantages of low price, strong capability of data collection, synchronous acquisition of RGB image and depth image. However, it encounters problems of low precision and limited measurement range. To fill the depth holes in depth image, we proposed a Combined Median Filter (CMF) algorithm. Then an approach which fused Kinect with LRF is proposed for obtaining a more accurate and more complete environmental map. The Robotic Operating System (ROS) which provided a messaging transformational mechanism for software modules integration was chosen as the robot software development platform.