基于优化地面分割与回环检测的激光同时定位与建图算法

Laser Simultaneous Localization and Mapping Algorithm Based on Optimized Ground Segmentation and Closed-Loop Detection

提出一种优化地面分割与回环检测策略的激光雷达同时定位与建图(SLAM)算法,首先,建立同心区模型,使用主成分分析(PCA)算法来提取点云区域性统计特征,设计地面似然估计二分类方法去除地面上可能出现的非地面点。其次,在特征中提取模块,通过平坦度与球度系数来额外提取球体特征,以此来增加提取点云帧上的关键点。最后,优化回环匹配策略,采用基于马氏距离的鲁棒解耦的全局准配策略,矫正累积误差,提高定位与建图精度;在公开数据集、实际环境中评估算法性能与验证实际应用偏好,并与LOAM、LeGO-LOAM、FAST-LIO等算法进行对比。结果表明,相比于LeGO-LOAM算法,所提算法在定位精度和稳定性上均有大幅度提升,其中在具有回环序列00和02上定位精度提升分别达到82.92%和83.38%,在无回环序列10上定位精度提升达到63.18%,现场验证表明所提算法满足实际应用需求。

Objective As a crucial aspect of automatic driving,unmanned vehicle technology has garnered extensive attention and research in both academia and industry.Autonomous vehicles require robust perception and decisionmaking systems for autonomous navigation,with simultaneous localization and mapping(SLAM)being one of the core components.While many advanced SLAM algorithms have achieved stable and highprecision positioning and mapping,challenges persist.For example,nonsmooth and uneven roads can distort collected data,making it difficult to establish reliable feature correspondence between frames,leading to significant map drift and positioning errors.Given the inaccuracy of existing laser SLAM algorithms in ground segmentation,low featurematching efficiency,and the high computational demands of traditional loop closure detection methods based on Euclidean distance,we propose a lidar SLAM algorithm with optimized ground segmentation and closedloop detection strategy.Methods We first introduce a more reliable ground segmentation method for nonsmooth roads during the preprocessing stage.By establishing a concentric region model for each point cloud frame and using principal component analysis(PCA)to extract statistical characteristics,we design a ground likelihood estimation binary classification method to remove unstable ground points.This approach addresses the issue of misclassifying nonground points as ground due to small slopes between adjacent laser points,achieving more accurate segmentation of nonsmooth road surfaces.Additionally,we introduce a sphere feature point extraction method alongside the standard edge and plane feature points.This enhances the point cloud’s useful information for matching between consecutive frames,improving both efficiency and robustness while reducing the influence of redundant point clouds.In addition,we propose a robust global alignment strategy based on Mahalanobis distance to replace the traditional iterative closest point(ICP)matching method using Euclidean distance.Mahalanobis distance,which measures covariance,can more effectively calculate the similarity between two unknown sample sets,thereby improving the accuracy of ICP closedloop matching without excessive computational overhead.Results and Discussions We evaluate the positioning accuracy and trajectory in both urban and rural scenes using the KITTI dataset.The proposed method is compared with LOAM,LeGOLOAM,and FASTLIO algorithms for quantitative analysis.The absolute pose error(APE)results(Table 1)show that,based on the root mean square errorindex,our algorithm significantly improves positioning accuracy and stability.In the ablation experiment(Table 2),our algorithm significantly improves positioning accuracy and stability.Through EVO trajectory visualization(Fig.8),the proposed algorithm shows superior consistency with the ground truth trajectory in terms of trajectory deviation and closedloop integrity,verifying the algorithm’s deployability.The algorithm’s time complexity and ability to process large datasets are also evaluated(Table 3).Compared with the LeGOLOAM algorithm,our method improves the average loop frame matching calculation by 16.56%,meeting both high accuracy and realtime deployment requirements for unmanned vehicles.Finally,the algorithm’s robustness and generalization are validated using the M2DGR dataset and realworld mining environments in Shandong province(Figs.10 and 11).The results confirm that our algorithm meets practical application needs.Conclusions Addressing the inaccuracies of existing laser SLAM algorithms in ground segmentation,low featurematching progress,and high computational cost of traditional closedloop detection methods based on Euclidean distance,we propose a laser SLAM algorithm based on optimized ground segmentation and closedloop detection.This method uses the LeGOLOAM framework to extract regional statistical features of the point cloud based on a concentric region model,incorporating a ground likelihood estimation binary classification method to accurately segment nonground points and remove unstable ground points.Additionally,the extraction of sphere features enhances the accuracy of interframe matching.Finally,we optimize the closedloop strategy with a robust decoupling global alignment based on Mahalanobis distance,effectively correcting cumulative errors and improving overall positioning and mapping accuracy.Comparative experiments using the KITTI public dataset demonstrate the advantages of our algorithm in positioning accuracy,and the M2DGR dataset further verifies its applicability in realworld scenarios.Our algorithm successfully constructs a globally consistent 3D map with high precision.