融合图特征的多机器人栅格地图拼接方法

现有的栅格地图拼接方法在地图重叠区域较小、地图特征较少、地图存在自相似性和非刚性形变的情况下匹配精度往往会大幅度下降甚至失配,提出了一种融合图特征的多机器人栅格地图拼接方法。提取待匹配栅格地图的ORB特征点并粗匹配,接下来建立ORB特征点之间的中值[K]近邻图;建立最优传输目标函数并融合ORB特征和图特征构建传输代价矩阵,同时建立增广节点筛选通过Sinkhorn算法求解最优匹配,RANSAC算法求解两张栅格地图之间的刚体变换,实现多机器人栅格地图的配准和拼接。通过实验验证了该方法具备较高的拼接精度,可应对重叠率低、特征不太明显的场景,展现出了较快的计算速度,并分析了相关参数对算法表现的影响。     

一种实时的三维语义地图生成方法

为了提高模块化机械臂分拣作业效率,研究了一种实时三维语义地图生成方法。该方法设计了一种改进的区域增长分割算法提高了分割效率和准确性,通过基于距离阈值的特征匹配方法得到候选模型,采用随机采样一致性（RANSAC）和迭代最近点算法（ICP）生成转变假设并对候选模型进行验证,获取物体位姿信息,保存于XML地图文件中,将其与机械臂末端位姿进行推理分析,得到抓取任务轨迹。实验结果表明,该方法满足作业实时性与准确性的要求。     

基于ORB-SLAM2系统的快速误匹配剔除算法与地图构建

针对ORB-SLAM2系统中随机抽样一致（RANSAC）算法在误匹配剔除时因其算法本身的随机性而导致效率较低的问题和在ORB-SLAM2系统里未能构建稠密点云地图的问题,采用渐进一致采样（PROSAC）算法来改进ORB-SLAM2系统中的误匹配剔除,并在系统中添加稠密点云地图和八叉树地图构建线程。首先,与RANSAC算法相比,PROSAC算法依据评价函数对特征点进行预排序,并选取评价质量较高的特征点求解单应性矩阵,根据单应性矩阵的解与匹配误差阈值进行误匹配剔除;然后,根据ORB-SLAM2系统进行相机的位姿估计与重定位;最后,根据所选关键帧进行稠密点云地图与八叉树地图的构建。根据TUM数据集上的实验结果,PROSAC算法在进行相同图像的误匹配剔除时所用时间是RANSAC算法的50%左右,并且所提系统的绝对轨迹误差与相对位姿误差与ORB-SLAM2系统基本一致,表现出良好的鲁棒性;另外,与稀疏点云地图相比,提出的新构建地图可以直接用于机器人的导航与路径规划。     

基于ORB-SLAM2系统的快速误匹配剔除算法与地图构建

针对ORB-SLAM2系统中随机抽样一致（RANSAC）算法在误匹配剔除时因其算法本身的随机性而导致效率较低的问题和在ORB-SLAM2系统里未能构建稠密点云地图的问题，采用渐进一致采样（PROSAC）算法来改进ORB-SLAM2系统中的误匹配剔除，并在系统中添加稠密点云地图和八叉树地图构建线程。首先，与RANSAC算法相比，PROSAC算法依据评价函数对特征点进行预排序，并选取评价质量较高的特征点求解单应性矩阵，根据单应性矩阵的解与匹配误差阈值进行误匹配剔除；然后，根据ORB-SLAM2系统进行相机的位姿估计与重定位；最后，根据所选关键帧进行稠密点云地图与八叉树地图的构建。根据TUM数据集上的实验结果，PROSAC算法在进行相同图像的误匹配剔除时所用时间是RANSAC算法的50%左右，并且所提系统的绝对轨迹误差与相对位姿误差与ORB-SLAM2系统基本一致，表现出良好的鲁棒性；另外，与稀疏点云地图相比，提出的新构建地图可以直接用于机器人的导航与路径规划。     

基于结构相似的RANSAC改进算法

为了减少传统RANSAC（Random Sample Consensus,随机抽样一致性）算法的迭代次数和运行时间,提高算法的速度和精度,提出了一种基于结构相似的RANSAC改进算法。采用BRISK（Binary Robust Invariant Scalable Keypoints）算法提取和描述二进制特征点,用Hamming距离进行特征匹配,获得初始匹配点集,利用结构相似约束剔除误匹配点,得到新的匹配点集,用新的点集作为RANSAC的输入,求出变换矩阵。该算法在初始匹配后进行了匹配点提纯,能快速求得变换模型。实验证明该算法迭代次数和运行时间比传统RANSAC算法明显减少,因此改进的算法在速度和精度上优于传统的RANSAC算法。     

基于SURF特征的枪弹痕迹匹配方法

为实现枪弹痕迹的自动比对与识别,提出将特征识别加速鲁棒特征(SURF)算法引入到弹壳痕迹匹配研究中,利用该算法提取弹底窝痕三维表面形貌特征,并采用随机抽样一致性(RANSAC)算法实现匹配优化。重点讨论了SURF特征点检测中参数调整及匹配效果关系,并借助美国国家标准与技术研究院(NIST)提供的弹底窝痕测试样本实现了最佳参数及识别条件的认定。实验结果表明,SURF算法对弹底窝痕表面形貌特征的提取与描述优异,在测试样本上可达到90%以上的匹配率。     

基于谱对称的形状配准方法

针对现有三维形状配准方法中存在左右翻转的错误匹配问题,提出了基于内蕴对称特征检测的高效形状配准算法。首先,通过热核与几何约束构建模型的内蕴自对称点对;其次,基于谱嵌入特征空间分析提取模型的内蕴对称平面,并依据模型表面法向量有效识别模型的左右结构属性;然后,根据内蕴对称点对获得模型的一致性谱对称结构描述;最后,引入一致性点漂移算法(CPD),实现基于谱对称的非刚性模型的形状配准,有效避免了模型配准中的左右结构翻转问题。实验进一步论证了这种方法不仅有效提高了模型匹配的效率,而且能有效识别同类模型的结构特征,对于非刚性模型的配准具有较强的鲁棒性。     

基于双目视觉的新型并联机构末端位姿检测

针对一种新型3-DOF驱动冗余并联机构,为提高双目视觉末端位姿检测的实时性和精度,首先采用Harris-SIFT算法对图片进行预匹配,通过Harris提取图像特征点,并采用SIFT特征描述子对图像进行匹配,使得匹配结果兼具实时性和稳定性;为解决匹配算法存在的误差匹配和错误匹配问题,提出一种改进的RANSAC算法对预匹配结果进行提纯,该改进方法通过分格取点和提前取点验算临时模型克服常规RANSAC算子匹配不准确、算法费时的缺点.实验结果表明,采用改进的RANSAC算法提纯较常规RANSAC算子不仅可以大幅度降低图像处理时间,而且可以更大程度提高匹配正确率,进而位姿检测的实时性和精度得以提高.     

气象卫星图像导航的地标匹配算法研究与优化

对气象卫星图像自动地标导航系统中的地标匹配算法进行了深入研究,采用基于最大相关系数的地标匹配算法来保证匹配精度,综合利用计算优化、搜索优化、并行优化等技术得到优化的地标匹配算法。实验结果表明,该算法能够有效降低算法复杂度,明显提高算法执行效率,同时保证地标匹配的准确性,满足自动地标导航系统的高可靠性和高时效性需求。     

一种改进AKAZE特征和RANSAC的图像拼接算法

针对传统图像描述方法在图像对变化复杂时特征点配准精度低,且传统RANSAC算法计算稳定性差的问题,提出一种结合改进AKAZE特征与RANSAC算法的图像拼接算法。利用AKAZE算法构造非线性尺度空间提取图像特征点,采用卷积神经网络描述符生成128维特征向量描述图像特征点,通过精简特征点并在迭代中设定嵌套阈值改进RANSAC算法得到最优变换矩阵模型,结合最佳缝合线算法和多频段融合算法对变换后的图像进行拼接。实验结果表明,和传统AKAZE算法相比,该算法在图像对的视角差异和光照差异较大时,配准精度分别提高12.60和6.99个百分点,改进后的RANSAC算法计算时间较改进前缩短4.17ms,图像拼接精度更高。     

特征序列数据关联机器人同步定位与地图构建

针对噪声不确定性增大的数据关联问题,提出特征点序列数据关联机器人同步定位与地图构建方法。根据机器人环境特征点的空间几何信息,基于图论建立特征点间的信息相关性。利用相邻两步的特征点观测信息协方差的变化,转化成求解特征点TSP问题和特征序列最大相关函数,以此确定所观测特征点的数据关联。实验证明,提出的方法可在噪声不确定性增大的情况下,保证同步定位与地图构建算法的一致性。     

Saliency and spatial information-based landmark selection for mobile robot navigation in natural environments

In this paper, a landmark selection and tracking approach is presented for mobile robot navigation in natural environments, using textural distinctiveness-based saliency detection and spatial information acquired from stereo data. The presented method focuses on achieving high robustness of tracking rather than self-positioning accuracy. The landmark selection method is designed to select a small amount of the most salient feature points in a wide variety of sparse unknown environments to ensure successful matching. Landmarks are selected by an iterative algorithm from a textural distinctiveness-based saliency map extended with spatial information, where a repulsive potential field is created around the position of each already selected landmark for better distribution in order to increase robustness. The template matching of landmarks is aided with visual odometry-based motion estimation. Other robustness increasing strategies includes estimating landmark positions by unscented Kalman filters as well as from surrounding landmarks. Experimental results show that the introduced method is robust and suitable for natural environments.     

Map Management for Efficient Simultaneous Localization and Mapping (SLAM)

The solution to the simultaneous localization and map building (SLAM) problem where an autonomous vehicle starts in an unknown location in an unknown environment and then incrementally build a map of landmarks present in this environment while simultaneously using this map to compute absolute vehicle location is now well understood. Although a number of SLAM implementations have appeared in the recent literature, the need to maintain the knowledge of the relative relationships between all the landmark location estimates contained in the map makes SLAM computationally intractable in implementations containing more than a few tens of landmarks. This paper presents the theoretical basis and a practical implementation of a feature selection strategy that significantly reduces the computation requirements for SLAM. The paper shows that it is indeed possible to remove a large percentage of the landmarks from the map without making the map building process statistically inconsistent. Furthermore, it is shown that the computational cost of the SLAM algorithm can be reduced by judicious selection of landmarks to be preserved in the map.     

Simultaneous localization and mapping using the Geometric Projection Filter and correspondence graph matching

A common way of localization in robotics is using triangulation on a system composed of a sensor and some landmarks (which can be artificial or natural). First, when no identifying marks are set on the landmarks, their identification by a robust algorithm is a complex problem which may be solved using correspondence graphs. Secondly, when the localization system has no a priori information about its environment, it has to build its own map in parallel with estimating its position, a problem known as simultaneous localization and mapping (SLAM). Recent works have proposed to solve this problem based on building a map made of invariant features. This paper describes the algorithms and data structure needed to deal with landmark matching, robot localization and map building in a single efficient process, unifying the previous approaches. Experimental results are presented using an outdoor robot car equipped with a two-dimensional scanning laser sensor.     

Vision-based global localization and mapping for mobile robots

We have previously developed a mobile robot system which uses scale-invariant visual landmarks to localize and simultaneously build three-dimensional (3-D) maps of unmodified environments. In this paper, we examine global localization, where the robot localizes itself globally, without any prior location estimate. This is achieved by matching distinctive visual landmarks in the current frame to a database map. A Hough transform approach and a RANSAC approach for global localization are compared, showing that RANSAC is much more efficient for matching specific features, but much worse for matching nonspecific features. Moreover, robust global localization can be achieved by matching a small submap of the local region built from multiple frames. This submap alignment algorithm for global localization can be applied to map building, which can be regarded as alignment of multiple 3-D submaps. A global minimization procedure is carried out using the loop closure constraint to avoid the effects of slippage and drift accumulation. Landmark uncertainty is taken into account in the submap alignment and the global minimization process. Experiments show that global localization can be achieved accurately using the scale-invariant landmarks. Our approach of pairwise submap alignment with backward correction in a consistent manner produces a better global 3-D map.     

Robust outdoor stereo vision SLAM for heavy machine rotation sensing

The paper presents a robust outdoor stereo vision simultaneous localization and mapping (SLAM) algorithm. It estimates camera pose reliably in outdoor environments with directional sunlight illumination causing shadows and non-uniform scene lighting. The algorithm has been developed to measure a mining rope shovel’s rotation angle about its vertical axis (“swing” axis). A stereo camera is mounted externally to the shovel house (upper revolvable portion of the shovel), with a clear view of the shovel’s lower carbody. As the shovel house swings, the camera revolves with the shovel house in a planar circular orbit, seeing differing views of the carbody top. During the swing, the SLAM algorithm builds a map of observed 3D features on the carbody and simultaneously using these landmarks to estimate the camera position. This estimated camera position is then used to compute the shovel swing angle. Two novel techniques are employed to improve the SLAM algorithm’s robustness in outdoor environments. First, a “Locally Maximal” feature selection technique for Harris corners is used to select features more consistently in non-uniformly illuminated scenes. Another novel technique is the use of 3D “Feature Clusters” as SLAM landmarks rather than individual single features. The Feature Cluster landmarks improve the robustness of the landmark matching and allow significant reduction of the SLAM filter computational cost. This approach of estimating the shovel swing angle has a maximum error of ±1° upon SLAM map convergence. Results demonstrate the improvements of using the novel techniques compared to previous methods.     

Optimal landmark selection for triangulation of robot position

A mobile robot can identify its own position relative to a global environment model by using triangulation based on three landmarks in the environment. It is shown that this procedure may be very sensitive to noise depending on spatial landmark configuration, and relative position between robot and landmarks. A general analysis is presented which permits prediction of the uncertainty in the triangulated position.

In addition an algorithm is presented for automatic selection of optimal landmarks. This algorithm enables a robot to continuously base its position computation on the set of available landmarks, which provides the least noise sensitive position estimate. It is demonstrated that using this algorithm can result in more than one order of magnitude reduction in uncertainty.