【摘要】 针对移动机器人利用单一传感器信息在未知环境下进行同时定位与地图创建(SLAM)存在准确性低、信息丢失等问题，提出一种基于贝叶斯法则的单线激光雷达和深度相机信息结合的SLAM建图方法。充分利用由深度图像转化的伪激光雷达数据与激光雷达信息，按区分优先级的融合规则进行信息融合，在地图更新阶段，基于贝叶斯推理构建概率模型，对二维栅格地图进行更新。在真实场景下利用ROS机器人进行验证，实验结果表明多传感器融合所建地图与真实场景一致性较高，有效地提高了机器人的环境感知能力。更多还原

【Abstract】 Aiming at the problems of low accuracy and information loss of mobile robot using single sensor information for simultaneous localization and mapping(SLAM) in unknown environment.This paper presented a method of data fusion for single-line lidar and depth camera based on Bayesian rule estimation SLAM.The lidar information and pseudo-lidar data transformed from the depth image are fully utilized, and the information is fused according to the fusion rules of priority differentiation.In the map updating stage, the probability model is constructed based on Bayesian inference to update the two-dimensional raster map.In the real scene, ROS robot is used for verification.Experimental results show that the map built by multi-sensor fusion has a high consistency with the real scene, which effectively improves the robot′s environmental perception ability.更多还原