At present,simultaneous localization and mapping(SLAM) for an autonomous underwater vehicle(AUV)is a research hotspot.Aiming at the problem of non-linear model and non-Gaussian noise in AUV motion,an improved method o...At present,simultaneous localization and mapping(SLAM) for an autonomous underwater vehicle(AUV)is a research hotspot.Aiming at the problem of non-linear model and non-Gaussian noise in AUV motion,an improved method of variance reduction fast simultaneous localization and mapping(FastSLAM) with simulated annealing is proposed to solve the problems of particle degradation,particle depletion and particle loss in traditional FastSLAM,which lead to the reduction of AUV location estimation accuracy.The adaptive exponential fading factor is generated by the anneal function of simulated annealing algorithm to improve the effective particle number and replace resampling.By increasing the weight of small particles and decreasing the weight of large particles,the variance of particle weight can be reduced,the number of effective particles can be increased,and the accuracy of AUV location and feature location estimation can be improved to some extent by retaining more information carried by particles.The experimental results based on trial data show that the proposed simulated annealing variance reduction FastSLAM method avoids particle degradation,maintains the diversity of particles,weakened the degeneracy and improves the accuracy and stability of AUV navigation and localization system.展开更多
激光雷达同时定位与建图(LiDAR SLAM)技术通常适用于静态环境下,而在动态场景下,定位与建图效果会受到影响;同时,地面分割模块通常用作点云分类处理,然而地面欠分割问题会影响特征点的选择;并且,通常的框架只使用一种回环检测方法,这可...激光雷达同时定位与建图(LiDAR SLAM)技术通常适用于静态环境下,而在动态场景下,定位与建图效果会受到影响;同时,地面分割模块通常用作点云分类处理,然而地面欠分割问题会影响特征点的选择;并且,通常的框架只使用一种回环检测方法,这可能会导致漏检现象。针对上述问题,提出一种动态场景下基于地面分割与回环优化的LiDAR SLAM系统(GSLC-SLAM)。首先,利用lmnet对点云进行动态剔除,该算法将生成的距离图像与残差图像作为网络的输入,并通过SalsaNext网络预测出动态物体;其次,利用高效的gridestiamte算法进行地面分割,该算法利用不均匀网格划分的方法来减少网格的数量,从而保证分割的效率,并利用正交性、高度和平坦度这3个指标进一步筛选地面点;最后,使用由LinK3D(Linear Keypoints for Three Dimensions point cloud)描述子与BoW3D(Bag of Words for Three Dimensions point cloud)词袋构成的新回环检测方法检测回环,该方法利用边缘特征点生成描述子,使用类似于汉明距离的方式进行描述子匹配,并采用类似于词袋的方法构建BoW3D作为LinK3D描述子的数据库,从而对关键帧提取的描述子进行存储以及回环检测。在数据集KITTI(Karlsruhe Institute of Technology and Toyota Technological Institute at Chicago)上的实验结果表明,在KITTI00、02与05序列中与Lego-Loam(Lightweight and ground-optimized LiDAR odometry and mapping)相比,GSLC-SLAM的均方根误差(RMSE)分别降低了5.8%,78.2%,12.5%;相较于F-LOAM(Fast LiDAR Odometry And Mapping),在KITTI00与05序列中GSLC-SLAM的RMSE分别降低了76.7%和53.8%,而在KITTI02序列中GSLC-SLAM表现不佳。经过验证可知,GSLC-SLAM可以有效减少动态物体的干扰、精确分割地面点并减少回环检测的漏检,进而使系统定位精度更高且更鲁棒。展开更多
视觉同步定位与建图(VSLAM)技术常常用于室内机器人的导航与感知,然而VSLAM的位姿估算方法是针对静态环境的,当场景中存在运动对象时,可能会导致定位和建图失败。针对此问题,提出了一个结合实例分割与聚类的VSLAM系统。所提系统使用实...视觉同步定位与建图(VSLAM)技术常常用于室内机器人的导航与感知,然而VSLAM的位姿估算方法是针对静态环境的,当场景中存在运动对象时,可能会导致定位和建图失败。针对此问题,提出了一个结合实例分割与聚类的VSLAM系统。所提系统使用实例分割网络生成场景中动态对象的概率掩膜,同时利用多视图几何的方法检测场景中的动态点,并将检测到的动态点与获得的概率掩膜匹配之后确定动态物体的精确动态掩膜;利用动态掩膜删除动态物体的特征点,然后利用剩余的静态特征点准确估计摄像机的位置。为了解决实例分割网络欠分割的问题,采用深度填充算法和聚类算法保证动态特征点完全删除。最后,重建图片被动态物体遮挡的背景,在正确的相机位姿下建立静态稠密点云地图。在公开的TUM(Technical University of Munich)数据集上的实验结果表明,在动态环境中,所提系统在保证实时性的同时能实现鲁棒的定位与建图。展开更多
基金supported by the National Science Fund of China under Grants 61603034China Postdoctoral Science Foundation under Grant 2019M653870XB+1 种基金Beijing Municipal Natural Science Foundation (3182027)Fundamental Research Funds for the Central Universities,China,FRF-GF-17-B44,and XJS191315
文摘At present,simultaneous localization and mapping(SLAM) for an autonomous underwater vehicle(AUV)is a research hotspot.Aiming at the problem of non-linear model and non-Gaussian noise in AUV motion,an improved method of variance reduction fast simultaneous localization and mapping(FastSLAM) with simulated annealing is proposed to solve the problems of particle degradation,particle depletion and particle loss in traditional FastSLAM,which lead to the reduction of AUV location estimation accuracy.The adaptive exponential fading factor is generated by the anneal function of simulated annealing algorithm to improve the effective particle number and replace resampling.By increasing the weight of small particles and decreasing the weight of large particles,the variance of particle weight can be reduced,the number of effective particles can be increased,and the accuracy of AUV location and feature location estimation can be improved to some extent by retaining more information carried by particles.The experimental results based on trial data show that the proposed simulated annealing variance reduction FastSLAM method avoids particle degradation,maintains the diversity of particles,weakened the degeneracy and improves the accuracy and stability of AUV navigation and localization system.
文摘激光雷达同时定位与建图(LiDAR SLAM)技术通常适用于静态环境下,而在动态场景下,定位与建图效果会受到影响;同时,地面分割模块通常用作点云分类处理,然而地面欠分割问题会影响特征点的选择;并且,通常的框架只使用一种回环检测方法,这可能会导致漏检现象。针对上述问题,提出一种动态场景下基于地面分割与回环优化的LiDAR SLAM系统(GSLC-SLAM)。首先,利用lmnet对点云进行动态剔除,该算法将生成的距离图像与残差图像作为网络的输入,并通过SalsaNext网络预测出动态物体;其次,利用高效的gridestiamte算法进行地面分割,该算法利用不均匀网格划分的方法来减少网格的数量,从而保证分割的效率,并利用正交性、高度和平坦度这3个指标进一步筛选地面点;最后,使用由LinK3D(Linear Keypoints for Three Dimensions point cloud)描述子与BoW3D(Bag of Words for Three Dimensions point cloud)词袋构成的新回环检测方法检测回环,该方法利用边缘特征点生成描述子,使用类似于汉明距离的方式进行描述子匹配,并采用类似于词袋的方法构建BoW3D作为LinK3D描述子的数据库,从而对关键帧提取的描述子进行存储以及回环检测。在数据集KITTI(Karlsruhe Institute of Technology and Toyota Technological Institute at Chicago)上的实验结果表明,在KITTI00、02与05序列中与Lego-Loam(Lightweight and ground-optimized LiDAR odometry and mapping)相比,GSLC-SLAM的均方根误差(RMSE)分别降低了5.8%,78.2%,12.5%;相较于F-LOAM(Fast LiDAR Odometry And Mapping),在KITTI00与05序列中GSLC-SLAM的RMSE分别降低了76.7%和53.8%,而在KITTI02序列中GSLC-SLAM表现不佳。经过验证可知,GSLC-SLAM可以有效减少动态物体的干扰、精确分割地面点并减少回环检测的漏检,进而使系统定位精度更高且更鲁棒。
文摘视觉同步定位与建图(VSLAM)技术常常用于室内机器人的导航与感知,然而VSLAM的位姿估算方法是针对静态环境的,当场景中存在运动对象时,可能会导致定位和建图失败。针对此问题,提出了一个结合实例分割与聚类的VSLAM系统。所提系统使用实例分割网络生成场景中动态对象的概率掩膜,同时利用多视图几何的方法检测场景中的动态点,并将检测到的动态点与获得的概率掩膜匹配之后确定动态物体的精确动态掩膜;利用动态掩膜删除动态物体的特征点,然后利用剩余的静态特征点准确估计摄像机的位置。为了解决实例分割网络欠分割的问题,采用深度填充算法和聚类算法保证动态特征点完全删除。最后,重建图片被动态物体遮挡的背景,在正确的相机位姿下建立静态稠密点云地图。在公开的TUM(Technical University of Munich)数据集上的实验结果表明,在动态环境中,所提系统在保证实时性的同时能实现鲁棒的定位与建图。
