激光点云匹配是影响激光SLAM系统精度和效率的关键因素.传统激光SLAM算法无法区分场景结构,且在非结构化场景下由于特征提取不佳而出现性能退化.为此,提出一种联合CPD(coherent point drift)面向复杂场景的自适应激光SLAM算法CPD-LOAM....激光点云匹配是影响激光SLAM系统精度和效率的关键因素.传统激光SLAM算法无法区分场景结构,且在非结构化场景下由于特征提取不佳而出现性能退化.为此,提出一种联合CPD(coherent point drift)面向复杂场景的自适应激光SLAM算法CPD-LOAM.该算法提出一种基于预判和验证相结合的场景结构辨识方法,首先引入场景特征变量对场景结构进行初步判断,然后从几何特征角度通过表面曲率对其进行验证,增强对场景结构辨识的准确性.此外,在非结构化场景下添加CPD算法进行点云预配准,进而利用ICP算法进行再配准,解决该场景下的特征退化问题,从而提高点云配准的精度和效率.实验结果表明,提出的场景特征变量以及表面曲率可以根据设置的阈值有效地区分场景结构,在公开数据集KITTI上的验证结果显示,CPD-LOAM较LOAM算法定位误差降低了84.47%,相较于LeGO-LOAM与LIO-SAM算法定位精度也分别提升了55.88%和30.52%,且具有更高的效率和鲁棒性.展开更多
煤矿智能化的重大需求对煤矿井下移动机器人智能感知提出了更高的要求,视觉同时定位与建图(Visual Simultaneous Localization and Mapping,VSLAM)是煤矿机器人智能感知的关键技术。然而,煤矿井下存在非结构化环境特征、纹理弱、光照不...煤矿智能化的重大需求对煤矿井下移动机器人智能感知提出了更高的要求,视觉同时定位与建图(Visual Simultaneous Localization and Mapping,VSLAM)是煤矿机器人智能感知的关键技术。然而,煤矿井下存在非结构化环境特征、纹理弱、光照不均匀、空间狭小等问题,现有依赖启发式阈值进行关键帧选取的方法无法满足煤矿下视觉SLAM的定位与建图需求。为此,提出一种煤矿井下多重约束的视觉SLAM关键帧选取方法,实现了煤矿井下移动机器人实时稳健的位姿估计,并为煤矿井下数字孪生提供数据基础。首先,提出的方法根据几何结构约束,采用自适应阈值取代静态启发式阈值进行关键帧选取,以实现视觉SLAM关键帧选取的有效性和鲁棒性。其次,通过重心平衡原则对有效特征点分布进行均匀化处理,以进一步确保视觉SLAM关键帧选取的稳定性以及创建地图点的稠密性和准确性。最后,利用航向角阈值对转向处做进一步约束,降低视角突变对视觉SLAM精度的影响。为验证本文方法的有效性,利用自主搭建的移动机器人数据采集平台在室内场景及煤矿井下分别进行了实验,并从绝对轨迹误差(Absolute Trajectory Error,ATE)和均方根误差(Root Mean Square Error,RMSE)等方面进行了定量和定性评价。结果表明:相比于启发式视觉SLAM关键帧选取方法,提出的方法在室内场景中轨迹RMSE提高了29%,在煤矿井下环境中轨迹RMSE提高了44%,具有较高的鲁棒性、定位精度和全局一致的建图效果。展开更多
This paper presents a robust visual simultaneous localization and mapping(SLAM) system that leverages point and structural line features in dynamic man-made environments. Manhanttan world assumption is considered and ...This paper presents a robust visual simultaneous localization and mapping(SLAM) system that leverages point and structural line features in dynamic man-made environments. Manhanttan world assumption is considered and the structural line features in such man-made environments provide rich geometric constraint, e.g., parallelism. Such a geometric constraint can be therefore used to rectify 3 D maplines after initialization. To cope with dynamic scenarios, the proposed system are divided into four main threads including 2 D dynamic object tracking, visual odometry, local mapping and loop closing. The 2 D tracker is responsible to track the object and capture the moving object in bounding boxes. In such a case, the dynamic background can be excluded and the outlier point and line features can be effectively removed. To parameterize 3 D lines, we use Pl ¨ucker line coordinates in initialization and projection processes, and utilize the orthonormal representation in unconstrained graph optimization process. The proposed system has been evaluated in both benchmark datasets and real-world scenarios, which reveals a more robust performance in most of the experiments compared with the existing state-of-the-art methods.展开更多
针对目前仿真果园环境研究不考虑地形起伏的问题,基于二维正态分布函数生成具有起伏特征的地面模型,并搭建果园仿真环境测试基于2D激光雷达的同步定位与建图(simultaneous localization and mapping, SLAM)算法的性能。通过控制土地模...针对目前仿真果园环境研究不考虑地形起伏的问题,基于二维正态分布函数生成具有起伏特征的地面模型,并搭建果园仿真环境测试基于2D激光雷达的同步定位与建图(simultaneous localization and mapping, SLAM)算法的性能。通过控制土地模型的起伏变化程度、最大高低落差以及突起分布密度等参数生成不同地形特征的土地;通过2D激光雷达、里程计等传感器获取移动机器人在果园仿真模型中的观测数据;通过可视化SLAM定位偏差及SLAM建图效果评价4种经典2D激光SLAM算法(Hector SLAM,GMapping, Karto SLAM,Cartographer)在具有不同地形的果园环境中的性能。实验结果表明:在果园环境中,随着土地起伏变化程度及最大高低落差的增加,2D激光SLAM算法的定位性能与建图性能将会降低;Hector SLAM能够提供更精准的定位结果,但是建图鲁棒性较差;GMapping能够获得更准确的环境地图,但是定位鲁棒性较差;Cartographer的定位及建图的鲁棒性均较为良好,但会出现少量偏差;Karto SLAM相较于其他算法,在果园环境中不具备优势。展开更多
针对飞行载体的实时ORB-SLAM实现问题,提出一种在嵌入式系统实现的改进ORB(oriented FAST and rotated BRIEF)单目视觉里程计算法。算法首先对输入图像进行灰度化、高斯滤波预处理实现简化运算和图像去噪,考虑到算法移植及在嵌入式系统...针对飞行载体的实时ORB-SLAM实现问题,提出一种在嵌入式系统实现的改进ORB(oriented FAST and rotated BRIEF)单目视觉里程计算法。算法首先对输入图像进行灰度化、高斯滤波预处理实现简化运算和图像去噪,考虑到算法移植及在嵌入式系统实现,将图像预处理和ORB图像特征提取与匹配等功能封装为IP(intellectual property)核,布置到硬件系统中,提高特征提取与匹配的速度和正确率,保证位姿估计实时性。搭建ZYNQ嵌入式系统,开展对比实验,实验结果表明:改进后的算法特征点匹配率提高了3.78倍,特征提取与匹配的耗时缩短为原来的1/8,处理图像的帧率可以达到19 fps,满足实时性要求。展开更多
This paper describes a brain-inspired simultaneous localization and mapping （SLAM） system using oriented features from accelerated segment test and rotated binary robust independent elementary （ORB） features of R...This paper describes a brain-inspired simultaneous localization and mapping （SLAM） system using oriented features from accelerated segment test and rotated binary robust independent elementary （ORB） features of RGB （red, green, blue） sensor for a mobile robot. The core SLAM system, dubbed RatSLAM, can construct a cognitive map using information of raw odometry and visual scenes in the path traveled. Different from existing RatSLAM system which only uses a simple vector to represent features of visual image, in this paper, we employ an efficient and very fast descriptor method, called ORB, to extract features from RCB images. Experiments show that these features are suitable to recognize the sequences of familiar visual scenes. Thus, while loop closure errors are detected, the descriptive features will help to modify the pose estimation by driving loop closure and localization in a map correction algorithm. Efficiency and robustness of our method are also demonstrated by comparing with different visual processing algorithms.展开更多
文摘激光点云匹配是影响激光SLAM系统精度和效率的关键因素.传统激光SLAM算法无法区分场景结构,且在非结构化场景下由于特征提取不佳而出现性能退化.为此,提出一种联合CPD(coherent point drift)面向复杂场景的自适应激光SLAM算法CPD-LOAM.该算法提出一种基于预判和验证相结合的场景结构辨识方法,首先引入场景特征变量对场景结构进行初步判断,然后从几何特征角度通过表面曲率对其进行验证,增强对场景结构辨识的准确性.此外,在非结构化场景下添加CPD算法进行点云预配准,进而利用ICP算法进行再配准,解决该场景下的特征退化问题,从而提高点云配准的精度和效率.实验结果表明,提出的场景特征变量以及表面曲率可以根据设置的阈值有效地区分场景结构,在公开数据集KITTI上的验证结果显示,CPD-LOAM较LOAM算法定位误差降低了84.47%,相较于LeGO-LOAM与LIO-SAM算法定位精度也分别提升了55.88%和30.52%,且具有更高的效率和鲁棒性.
文摘煤矿智能化的重大需求对煤矿井下移动机器人智能感知提出了更高的要求,视觉同时定位与建图(Visual Simultaneous Localization and Mapping,VSLAM)是煤矿机器人智能感知的关键技术。然而,煤矿井下存在非结构化环境特征、纹理弱、光照不均匀、空间狭小等问题,现有依赖启发式阈值进行关键帧选取的方法无法满足煤矿下视觉SLAM的定位与建图需求。为此,提出一种煤矿井下多重约束的视觉SLAM关键帧选取方法,实现了煤矿井下移动机器人实时稳健的位姿估计,并为煤矿井下数字孪生提供数据基础。首先,提出的方法根据几何结构约束,采用自适应阈值取代静态启发式阈值进行关键帧选取,以实现视觉SLAM关键帧选取的有效性和鲁棒性。其次,通过重心平衡原则对有效特征点分布进行均匀化处理,以进一步确保视觉SLAM关键帧选取的稳定性以及创建地图点的稠密性和准确性。最后,利用航向角阈值对转向处做进一步约束,降低视角突变对视觉SLAM精度的影响。为验证本文方法的有效性,利用自主搭建的移动机器人数据采集平台在室内场景及煤矿井下分别进行了实验,并从绝对轨迹误差(Absolute Trajectory Error,ATE)和均方根误差(Root Mean Square Error,RMSE)等方面进行了定量和定性评价。结果表明:相比于启发式视觉SLAM关键帧选取方法,提出的方法在室内场景中轨迹RMSE提高了29%,在煤矿井下环境中轨迹RMSE提高了44%,具有较高的鲁棒性、定位精度和全局一致的建图效果。
基金supported by the Institute for Guo Qiang of Tsinghua University (Grant No. 2019GQG1023)the National Natural Science Foundation of China (Grant No. 61873140)the Independent Research Program of Tsinghua University (Grant No. 2018Z05JDX002)。
文摘This paper presents a robust visual simultaneous localization and mapping(SLAM) system that leverages point and structural line features in dynamic man-made environments. Manhanttan world assumption is considered and the structural line features in such man-made environments provide rich geometric constraint, e.g., parallelism. Such a geometric constraint can be therefore used to rectify 3 D maplines after initialization. To cope with dynamic scenarios, the proposed system are divided into four main threads including 2 D dynamic object tracking, visual odometry, local mapping and loop closing. The 2 D tracker is responsible to track the object and capture the moving object in bounding boxes. In such a case, the dynamic background can be excluded and the outlier point and line features can be effectively removed. To parameterize 3 D lines, we use Pl ¨ucker line coordinates in initialization and projection processes, and utilize the orthonormal representation in unconstrained graph optimization process. The proposed system has been evaluated in both benchmark datasets and real-world scenarios, which reveals a more robust performance in most of the experiments compared with the existing state-of-the-art methods.
文摘针对目前仿真果园环境研究不考虑地形起伏的问题,基于二维正态分布函数生成具有起伏特征的地面模型,并搭建果园仿真环境测试基于2D激光雷达的同步定位与建图(simultaneous localization and mapping, SLAM)算法的性能。通过控制土地模型的起伏变化程度、最大高低落差以及突起分布密度等参数生成不同地形特征的土地;通过2D激光雷达、里程计等传感器获取移动机器人在果园仿真模型中的观测数据;通过可视化SLAM定位偏差及SLAM建图效果评价4种经典2D激光SLAM算法(Hector SLAM,GMapping, Karto SLAM,Cartographer)在具有不同地形的果园环境中的性能。实验结果表明:在果园环境中,随着土地起伏变化程度及最大高低落差的增加,2D激光SLAM算法的定位性能与建图性能将会降低;Hector SLAM能够提供更精准的定位结果,但是建图鲁棒性较差;GMapping能够获得更准确的环境地图,但是定位鲁棒性较差;Cartographer的定位及建图的鲁棒性均较为良好,但会出现少量偏差;Karto SLAM相较于其他算法,在果园环境中不具备优势。
文摘针对飞行载体的实时ORB-SLAM实现问题,提出一种在嵌入式系统实现的改进ORB(oriented FAST and rotated BRIEF)单目视觉里程计算法。算法首先对输入图像进行灰度化、高斯滤波预处理实现简化运算和图像去噪,考虑到算法移植及在嵌入式系统实现,将图像预处理和ORB图像特征提取与匹配等功能封装为IP(intellectual property)核,布置到硬件系统中,提高特征提取与匹配的速度和正确率,保证位姿估计实时性。搭建ZYNQ嵌入式系统,开展对比实验,实验结果表明:改进后的算法特征点匹配率提高了3.78倍,特征提取与匹配的耗时缩短为原来的1/8,处理图像的帧率可以达到19 fps,满足实时性要求。
基金supported by National Natural Science Foundation of China(No.61673283)
文摘This paper describes a brain-inspired simultaneous localization and mapping （SLAM） system using oriented features from accelerated segment test and rotated binary robust independent elementary （ORB） features of RGB （red, green, blue） sensor for a mobile robot. The core SLAM system, dubbed RatSLAM, can construct a cognitive map using information of raw odometry and visual scenes in the path traveled. Different from existing RatSLAM system which only uses a simple vector to represent features of visual image, in this paper, we employ an efficient and very fast descriptor method, called ORB, to extract features from RCB images. Experiments show that these features are suitable to recognize the sequences of familiar visual scenes. Thus, while loop closure errors are detected, the descriptive features will help to modify the pose estimation by driving loop closure and localization in a map correction algorithm. Efficiency and robustness of our method are also demonstrated by comparing with different visual processing algorithms.
