基于自适应特征及闭环优化的激光即时定位与建图算法

Laser Simultaneous Localization and Mapping Algorithm Based on Adaptive Features and Closed-Loop Optimization

即时定位与建图(SLAM)应用的场景多样但受限于计算成本。基于此,提出了一种基于自适应特征及闭环优化的激光SLAM算法(FAST-SAM)。采用自适应特征提取方法Better Feature在不同的距离下保证特征提取的准确性,再通过基于随机一致性采样优化的地面特征滤除方法去除不可靠的特征并使特征数量保持稳定,在帧间匹配和闭环检测模块分别采用正态分布变换粗配准与最近点迭代精配准结合的匹配算法及所提两段式闭环检测算法,最终输出激光惯性里程计并建立全局点云地图。在LIO-SAM、KITTI开源数据集及广西大学实测数据集上的实验结果表明,与主流的SLAM算法相比,所提算法在提升精度的同时,将各环节的计算效率提升25.6%以上。

Simultaneous localization and mapping(SLAM)has various application scenarios but is limited due to computational cost.Therefore,a SLAM algorithm(FASTSAM)based on adaptive features and closedloop optimization is proposed.The proposed algorithm uses the adaptive feature extraction method Better Feature to ensure the accuracy of the feature extraction at different distances.Then,it uses the ground feature filtering method based on random sample consensus to remove unreliable features and keep the number of features stable.In the scan matching and loopclosure detection modules,we use a matching algorithm combining the normal distribution transformation,nearest point iteration algorithm,and the proposed twostage loopclosure detection algorithm to output the laser inertial odometry and establish a global point cloud map.The experimental results on the LIOSAM,KITTI open source datasets,and the measured datasets of Guangxi University show that compared with the mainstream SLAM algorithms,the proposed algorithm improves the accuracy and the computational efficiency of each link by more than 25.6%.