基于NDT匹配和改进回环检测的SLAM研究

3D SLAM of mobile robot based on NDT match and improved loop-closure detection

在利用即时定位与建图（SLAM）来对周围的环境进行三维建模的应用场景中,提出了一种改进的检测回环的方法。利用深度相机获得的三维点云数据进行正态分布变换（NDT）匹配,得到各个时刻间的初始相对位姿,之后利用随机抽样一致（RANSAC）算法来进一步提高初始匹配的精度。混合回环检测方法是利用空间位置的方法来锁定初始的候选匹配对象,减少全局搜索的耗时;利用基于外观相似性的方法对候选对象进行最后的判别,选择具有强鲁棒性的回环。对公开数据集及室内采集的数据进行实验,并与RGBD-SLAM和RTAB-MAP两种算法进行对比。结果表明,提出的方法原理正确,并在运行一段时间后,可获得比其他两种算法更快的闭环检测速度。

A improved loop-closure detection method for mobile robot Simultaneous Localization and Mapping（SLAM）is presented to address the problem of 3 D modeling in complex indoor environment.According to the camera calibration model and the image feature extraction and matching procedure,the association between two 3 Dpoint clouds can be established.On the basis of the Random Sample Consensus（RANSAC）algorithm,the correspondence based Normal Distribution Transform（NDT）algorithm arithmetic model is solved to realize the robot＇s initial localization effectively.The loop detection method,which combines the space based method and appearance similarity method,promotes the speed of detection.The key frame-to-frame selection mechanism is used for maintaining and updating the global map.Contrast experiments based on the datasets and the actual scene show that,compared with the RGBD-SLAM and RTABMAP,the improved hybrid loop-closure detection algorithm has better real-time performance.