基于ROS机器人的相机与激光雷达融合技术研究

Research on the fusion technology of camera and lidar based on ROS intelligent mobile robot

为提高智能移动机器人的感知能力,针对智能机器人相机与激光雷达融合提出一种基于直线与平面拟合算法,并将其应用于ROS智能移动机器人系统。基于PPB方法对相机图像进行畸变校正获得角点的二维坐标,采用点云反射强度(PCI)的方法获得角点的三维坐标。通过解决N点透视位姿求解问题(PNP问题)的方法来获得三维坐标与二维坐标之间的变换,变换后完成相机与激光雷达的点云融合。将激光雷达与深度相机安装与机器人顶部并通过比较选择ORB算法作为机器人的SLAM方式,实验结果表明融合后机器人能够更有效地识别小体积障碍物,具有一定的应用前景。

In order to improve the perception ability of intelligent mobile robots,an algorithm based on straight line and plane fitting is proposed for the fusion of intelligent robot camera and lidar,and it is applied to the ROS intelligent mobile robot system.Based on the PPB method,the camera image is subjected to distortion correction to obtain the two-dimensional coordinates of the corner points,and the point cloud reflection intensity(PCI)method is used to obtain the three-dimensional coordinates of the corner points.The transformation between three-dimensional coordinates and two-dimensional coordinates is obtained by solving the N-point perspective pose problem(PNP problem),and the point cloud fusion between the camera and the lidar is completed after the transformation.The lidar and depth camera are installed on the top of the robot,and the ORB algorithm is selected as the SLAM method of the robot through comparison.The experimental results show that the fusion robot can more effectively identify small-volume obstacles,which has certain application prospects.