融合视觉信息的激光SLAM

Laser SLAM Mapping Method Based on Visual Information

针对Gmapping SLAM(simultaneous location and mapping)算法在地图构建过程中对里程计定位精度要求较高且存在粒子耗散、退化等问题,本文首先设计出并行视觉识别与定位网络,用视觉特征与定位信息弥补粒子退化与激光点的漂移,强化定位能力,提高语义信息与构图精度;其次优化提议分布,将观测模型从里程计观测模型变换为激光观测模型并进行高斯采样,用更少的粒子覆盖机器人的概率分布;最后通过贝叶斯规则将视觉信息与激光信息融合,利用仿真工具、机器人平台与原算法进行对比,实验结果表明该算法不仅有效地提高地图构建的精确度与鲁棒性而且丰富了地图的语义信息。

In view of the fact that the Gmapping SLAM algorithm has high requirements on the accuracy of odometry positioning information in the process of map construction,and there are problems such as particle dissipation and degradation,Firstly,a parallel visual recognition and localization network is designed to strengthen the localization ability and improve the semantic in⁃formation and composition accuracy;Secondly,the optimization proposal distribution is improved,we use the laser observation model to replace the odometrg motion model and perform Gaussian sampling to cover the probability distribution of the robot with fewer particles;Finally,the visual information and laser information are fused by Bayesian rule,and the original algorithm is compared.The results show that the algorithm improves the accuracy and robustness of map construction and enriches the seman⁃tic information.