基于多信息融合的移动机器人定位算法

为了提高机器人的定位精度,提出了一种基于里程计、单目视觉与激光雷达信息相融合的自定位算法.首先,由里程计推算出机器人在各个时刻位置的估计值;其次,在不同时刻计算出机器人摄像头与任意两个环境特征点的夹角变化,通过激光雷达获得环境特征点的距离和角度并利用扩展卡尔曼滤波算法与里程计的定位信息进行融合;最后,由匹配的环境特征对机器人的位置进行修正,得到精确的位置估计.实验结果表明,该算法在多转角、长距离的情况下取得了满意的效果,有效地提高了定位精度.

Localization Algorithm of Mobile Robot Based on Multi Information Fusion

In order to increase the localization precision of mobile robot, a self-localization algorithm based on odometry, single vision and laser radar has been proposed. First, odometry estimated robot''s pose at every sampling time. Secondly, at different times, the angle changes between any two of the environmental feature points and robot camera were calculated. Laser radar obtained the information that indicating distance and angle of landmarks. Then, the data provided by odometry, single vision and laser radar were fused together by means of an extended Kalman filter (EKF) technique. Finally, the position of robot was reset by matched environment feature, and the position estimation of robot was given accurately. Experiment result proves that such an algorithm achieves good localization effect under multi-corner and long-distance conditions, and improves the localization precision efficiently.