基于ROS与Kinect的移动机器人同时定位与地图构建

同时定位与地图构建(SLAM)技术一直以来都是移动机器人实现自主导航和避障的核心问题,移动机器人需要借助传感器来探测周围的物体同时构建出相应区域的地图。由于传统的1D和2D传感器,如超声波传感器、声呐和激光测距仪等在建图过程中无法检测出Z轴(垂直方向)上的信息,易增加机器人发生碰撞的概率,同时影响建图结果的精确度。本文利用Kinect作为机器人SLAM的传感器,将其采集到的三维信息转化成二维的激光数据进行地图构建,同时借助机器人操作系统(robot operating system,ROS)进行仿真分析和实际测试。结果表明Kinect可以弥补1D和2D传感器采集信息的不足,同时能够较好的保持建图的完整性和可靠性,适用于室内的移动机器人SLAM实现。

Mobile robot simultaneous localization and mapping based on ROS and Kinect

Simultaneous localization and mapping (SLAM) has always been the key technology to achieve mobile robot autonomous navigation and obstacle avoidance. Mobile robot needs sensors to see objects around it, map the surrounding area. Traditional 1D and 2D sensors such as ultrasonic sensor, sonar and laser range finder for area mapping is not precise .Bucause, they can not detect information in vertical direction,it is likely to increase the probability of robot collision and inaccurate mapping.In this paper Kinect is used to be the robot SLAM sensor, which collected 3D information into 2D laser data, the same time with the robot operating system (ROS) simulation analysis and practical tests are verified. The results showed that Kinect can make up the lack of 1D and 2D sensor to collect information and it can also maintain the integrity and reliability of the mapping,Kinect is suitable for mobile robot SLAM indoor realization.