激光—相机系统语义栅格建图和路径规划

目的 SLAM（simultaneous localization and mapping）是移动机器人在未知环境进行探索、感知和导航的关键技术。激光SLAM测量精确，便于机器人导航和路径规划，但缺乏语义信息。而视觉SLAM的图像能提供丰富的语义信息，特征区分度更高，但其构建的地图不能直接用于路径规划和导航。为了实现移动机器人构建语义地图并在地图上进行路径规划，本文提出一种语义栅格建图方法。方法 建立可同步获取激光和语义数据的激光-相机系统，将采集的激光分割数据与目标检测算法获得的物体包围盒进行匹配，得到各物体对应的语义激光分割数据。将连续多帧语义激光分割数据同步融入占据栅格地图。对具有不同语义类别的栅格进行聚类，得到标注物体类别和轮廓的语义栅格地图。此外，针对语义栅格地图发布导航任务，利用路径搜索算法进行路径规划，并对其进行改进。结果 在实验室走廊和办公室分别进行了语义栅格建图的实验，并与原始栅格地图进行了比较。在语义栅格地图的基础上进行了路径规划，并采用了语义赋权算法对易移动物体的路径进行对比。结论 多种环境下的实验表明本文方法能获得与真实环境一致性较高、标注环境中物体类别和轮廓的语义栅格地图，且实验硬件结构简单、成本低、性能良好，适用于智能化机器人的导航和路径规划。     

实时更新的全局一致三维栅格建图

在未知的三维环境中,移动机器人自主导航通常需要实时构建与环境全局一致的栅格地图,而现有大部分系统缺少地图更新策略,构建的栅格地图与实际环境不一致.文中将同步定位与建图模块获得的环境信息以点云形式提供给栅格建图模块处理,同时提出基于关键帧的高效数据结构和地图实时更新策略,实时构建可用于移动机器人自主导航的全局一致的地图.室内动态的实验数据测试表明,文中方法可以有效实时更新地图,生成与环境一致的三维栅格地图,支持其后续的自主导航操作.     

基于VSLAM的自主移动机器人三维同时定位与地图构建

移动机器人在探索未知环境且没有外部参考系统的情况下,面临着同时定位和地图构建（SLAM）问题。针对基于特征的视觉SLAM（VSLAM）算法构建的稀疏地图不利于机器人应用的问题,提出一种基于八叉树结构的高效、紧凑的地图构建算法。首先,根据关键帧的位姿和深度数据,构建图像对应场景的点云地图;然后利用八叉树地图技术进行处理,构建出了适合于机器人应用的地图。将所提算法同RGB-D SLAM（RGB-Depth SLAM）算法、ElasticFusion算法和ORB-SLAM（Oriented FAST and Rotated BRIEF SLAM）算法通过权威数据集进行了对比实验,实验结果表明,所提算法具有较高的有效性、精度和鲁棒性。最后,搭建了自主移动机器人,将改进的VSLAM系统应用到移动机器人中,能够实时地完成自主避障和三维地图构建,解决稀疏地图无法用于避障和导航的问题。     

基于改进RBPF算法的轮式机器人SLAM导航系统设计

传统的机器人导航系统在复杂的地形环境中常常无法引导机器人躲避突然出现的障碍物,无法精准采集数据。为此提出一种改进RBPF算法的轮式机器人SLAM导航系统,对系统硬件和软件进行设计。系统硬件主要由导航功能模块、底盘驱动模块、控制模块组成,利用RPLIDAR A1型激光测距雷达设计导航功能模块,并设计底盘驱动模块和控制模块。软件设计中,以改进RBPF算法为基础,设计了轮式机器人SLAM导航系统的实现程序,应用算法代入的方式加强了普通轮式机器人导航算法对粒子计算与卡尔曼滤波的敏感程度。实验结果表明,改进RBPF算法在避障和计算误差方面的优势,证明了该系统相比传统避障后的路径选择更便捷,导航错误出现率降低了30%左右。     

Active SLAM and Exploration with Particle Filters Using Kullback-Leibler Divergence

Autonomous exploration under uncertain robot location requires the robot to use active strategies to trade-off between the contrasting tasks of exploring the unknown scenario and satisfying given constraints on the admissible uncertainty in map estimation. The corresponding problem, namely active SLAM (Simultaneous Localization and Mapping) and exploration, has received a large attention from the robotic community for its relevance in mobile robotics applications. In this work we tackle the problem of active SLAM and exploration with Rao-Blackwellized Particle Filters. We propose an application of Kullback-Leibler divergence for the purpose of evaluating the particle-based SLAM posterior approximation. This metric is then applied in the definition of the expected information from a policy, which allows the robot to autonomously decide between exploration and place revisiting actions (i.e., loop closing). Extensive tests are performed in typical indoor and office environments and on well-known benchmarking scenarios belonging to SLAM literature, with the purpose of comparing the proposed approach with the state-of-the-art techniques and to evaluate the maturity of truly autonomous navigation systems based on particle filtering.     

Geometric and Bayesian models for safe navigation in dynamic environments

Autonomous navigation in open and dynamic environments is an important challenge, requiring to solve several difficult research problems located on the cutting edge of the state of the art. Basically, these problems may be classified into three main categories: (a) SLAM in dynamic environments; (b) detection, characterization, and behavior prediction of the potential moving obstacles; and (c) online motion planning and safe navigation decision based on world state predictions. This paper addresses some aspects of these problems and presents our latest approaches and results. The solutions we have implemented are mainly based on the followings paradigms: multiscale world representation of static obstacles based on the wavelet occupancy grid; adaptative clustering for moving obstacle detection inspired on Kohonen networks and the growing neural gas algorithm; and characterization and motion prediction of the observed moving entities using Hidden Markov Models coupled with a novel algorithm for structure and parameter learning.     

基于视觉惯性里程计与语义信息的无人机SLAM方法研究

室内环境中存在丰富的语义信息,可以使机器人更好地理解环境,提高机器人位姿估计的准确性。虽然语义信息在机器人同时定位与地图构建(SLAM)领域得到了深入研究和广泛应用,但是在环境准确感知、语义特征提取和语义信息利用等方面还存在着很多困难。针对上述难点,提出了一种基于视觉惯性里程计算法与语义信息相结合的新方法,该方法通过视觉惯性里程计来估计机器人的状态,通过校正估计,构建从语义检测中提取的几何表面的稀疏语义地图;通过将检测到的语义对象的几何信息与先前映射的语义信息相关联来解决视觉惯性里程计和惯性测量单元的累积误差问题。在室内环境中对装备RGB-D深度视觉和激光雷达的无人机进行验证实验,结果表明,该方法比视觉惯性里程计算法取得了更好的结果。应用结合语义信息和视觉惯性里程计的SLAM算法表现出很好的鲁棒性和准确性,该方法能提高无人机导航精度,实现无人机智能自主导航。     

动态场景下基于自适应语义分割的RGB-D SLAM算法

目前较为成熟的视觉SLAM算法在应用于动态场景时,往往会因动态对象干扰而导致系统所估计的位姿误差急剧增大甚至算法失效。为解决上述问题,本文提出一种适用于室内动态场景的视觉SLAM算法,根据当前帧中特征点的运动等级信息自适应判断当前帧是否需要进行语义分割,进而实现语义信息的跨帧检测;根据语义分割网络提供的先验信息以及该对象在先前场景中的运动状态,为每个特征点分配运动等级,将其归类为静态点、可移静态点或动态点。选取合适的特征点进行位姿的初估计,再根据加权静态约束的结果对位姿进行二次优化。最后为验证本文算法的有效性,在TUM RGB-D动态场景数据集上进行实验,并与ORB-SLAM2算法及其他处理动态场景的SLAM算法进行对比,结果表明本文算法在大部分数据集上表现良好,相较改进前的ORB-SLAM算法,本文算法在室内动态场景中的定位精度可提升90.57%。     

VecSLAM: An Efficient Vector-Based SLAM Algorithm for Indoor Environments

In this paper, we present an efficient SLAM (Simultaneous Localization and Mapping) algorithm named VecSLAM, which localizes and builds a vector map for mobile robots in indoor environments. Compared to grid-mapping approaches, vector-based mapping algorithms require a relatively small amount of memory. Two essential operations for successful vector mapping are vector merging and loop closing. Merging methods used by traditional line segment-based mapping algorithms do not consider the sensor characteristics, which causes additional mapping error and makes it harder to close loops after navigation over a long distance. In addition, few line segment-based SLAM approaches contain loop closing methodology. We present a novel vector merging scheme based on a recursive least square estimation for robust mapping. An efficient loop closing method is also proposed, which effectively distributes the resultant mapping error throughout the loop to guarantee global map consistency. Simulation studies and experimental results show that VecSLAM is an efficient and robust online localization and mapping algorithm.     

Johnny: An Autonomous Service Robot for Domestic Environments

In this article we describe the architecture, algorithms and real-world benchmarks performed by Johnny Jackanapes, an autonomous service robot for domestic environments. Johnny serves as a research and development platform to explore, develop and integrate capabilities required for real-world domestic service applications. We present a control architecture which allows to cope with various and changing domestic service robot tasks. A software architecture supporting the rapid integration of functionality into a complete system is as well presented. Further, we describe novel and robust algorithms centered around multi-modal human robot interaction, semantic scene understanding and SLAM. Evaluation of the complete system has been performed during the last years in the RoboCup@Home competition where Johnnys outstanding performance led to successful participation. The results and lessons learned of these benchmarks are explained in more detail.     

计算复杂度降低的基于CDKF的SLAM算法

为了降低移动机器人基于中心差分卡尔曼滤波(CDKF)的同时定位与地图构建(SLAM)算法的计算复杂度,使其适于较大规模环境中的应用,提出了一种改进的CDKF SLAM算法。该算法以CDKF的线性回归卡尔曼滤波(LRKF)形式为基础,利用SLAM自身特点,重构其预测和观测更新过程中的状态变量及相应的方差矩阵,改进CDKF的采样方法,从而将CDKF SLAM算法的计算复杂度降为O(n2)。不同规模环境中的仿真实验及停车场数据集的实验验证了在不改变CDKF SLAM算法估计准确度的条件下,本文算法的运行时间明显缩短,更适于大规模环境中的应用。     

Collision-free Autonomous Navigation of A Small UAV Using Low-cost Sensors in GPS-denied Environments

This paper proposes a novel complete navigation system for autonomous flight of small unmanned aerial vehicles (UAVs) in GPS-denied environments. The hardware platform used to test the proposed algorithm is a small, custom-built UAV platform equipped with an onboard computer, RGB-D camera, 2D light detection and ranging (LiDAR), and altimeter. The error-state Kalman filter (ESKF) based on the dynamic model for low-cost IMU-driven systems is proposed, and visual odometry from the RGB-D camera and height measurement from the altimeter are fed into the measurement update process of the ESKF. The pose output of the ESKF is then integrated into the open-source simultaneous location and mapping (SLAM) algorithm for pose-graph optimization and loop closing. In addition, the computationally efficient collision-free path planning algorithm is proposed and verified through simulations. The software modules run onboard in real time with limited onboard computational capability. The indoor flight experiment demonstrates that the proposed system for small UAVs with low-cost devices can navigate without collision in fully autonomous missions while establishing accurate surrounding maps.

     

一种基于聚类分组的快速联合兼容SLAM数据关联算法

针对在移动机器人同时定位与建图（SLAM）过程中如何快速准确获取数据关联结果的问题,提出了一种基于DBSCAN（density-based spatial clustering of application with noise）聚类分组的快速联合兼容SLAM数据关联算法（DFJCBB）．首先,采用局部关联策略将参与关联的特征点限定在局部地图中;其次,针对多数环境中量测都有较明显的分布,采用一种基于密度聚类的方法DBSCAN对当前时刻的量测进行分组,从而得到若干关联度小的观测小组;最后,在每个小组中采用联合兼容分支定界（JCBB）算法进行数据关联,以获得每个小组量测与局部地图特征之间的最优关联解,并将这些关联解组合获得最终的关联结果．基于模拟器和标准数据集的仿真实验验证了该关联算法的性能,结果表明该关联算法在保证获得较高关联准确度的同时,大大降低了算法复杂度、缩短了运行时间,适用于解决不同复杂环境中的SLAM数据关联问题．     

基于SLAM的旋翼无人机组合导航算法研究

在旋翼无人机组合导航中,针对缺乏GPS作为导航信号源的室内飞行环境,为了达到精确定位的目的,提出一种基于SLAM（simultaneous localization and mapping）的旋翼无人机组合导航算法。首先,引入双线性插值算法,实现基于扫描匹配的即时定位与地图构建;其次,对陀螺仪、加速度计和磁罗盘建立捷联惯导系统误差模型,针对旋翼无人机的使用环境对误差模型进行简化;最后,应用联邦卡尔曼滤波算法,设计组合导航系统模型,将SLAM算法和捷联惯导系统估计出的位置数据进行融合。仿真结果表明所设计基于SLAM的旋翼无人机组合导航算法能够进一步提高组合导航系统对旋翼无人机位姿估计的精度。     

Recursive scan-matching SLAM

This paper presents Scan-SLAM, a new generalization of simultaneous localization and mapping (SLAM). SLAM implementations based on extended Kalman filter (EKF) data fusion have traditionally relied on simple geometric models for defining landmarks. This limits EKF-SLAM to environments suited to such models and tends to discard much potentially useful data. The approach presented in this paper is a marriage of EKF-SLAM and scan correlation. Landmarks are no longer defined by analytical models; instead they are defined by templates composed of raw sensed data. These templates can be augmented as more data become available so that the landmark definition improves with time. A new generic observation model is derived that is generated by scan correlation, and this permits stochastic location estimation for landmarks with arbitrary shape within the Kalman filter framework. The statistical advantages of an EKF representation are augmented with the general applicability of scan matching. Scan matching also serves to enhance data association reliability by providing a shape metric for landmark disambiguation. Experimental results in an outdoor environment are presented which validate the algorithm.     

基于动态耦合与空间数据关联的RGB-D SLAM算法

为了解决动态环境下视觉SLAM（同步定位与地图创建）算法定位与建图精度下降的问题,提出了一种基于动态耦合与空间数据关联的RGB-D SLAM算法。首先,使用语义网络获得预处理的语义分割图像,并利用边缘检测算法和相邻语义判定获得完整的语义动态物体;其次,利用稠密直接法模块实现对相机姿态的初始估计,这里动态耦合分数值的计算在利用了传统的动态区域剔除之外,还使用了空间平面一致性判据和深度信息筛选;然后,结合空间数据关联算法和相机位姿实时更新地图点集,并利用最小化重投影误差和闭环优化线程完成对相机位姿的优化;最后,使用相机位姿和地图点集构建八叉树稠密地图,实现从平面到空间的动态区域剔除,完成静态地图在动态环境下的构建。根据高动态环境下TUM数据集测试结果,本文算法定位误差相比于ORB-SLAM算法减小了约90%,有效提高了RGB-D SLAM算法的定位精度和相机位姿估计精度。     

Data association and loop closure in semantic dynamic SLAM using the table retrieval method

Simultaneous localization and mapping (SLAM) plays an important role in the area of robotics and augmented reality to simultaneously obtain its location and construct environment maps in real-time. There are many challenges in SLAM, such as data association, loop closure, and dynamic environments. In this paper, we propose a table retrieval method for SLAM data association and loop closure using semantic information in a dynamic environment. The detected landmarks are stored in a table for retrieval, and each landmark has its own semantic and location information for data association and loop closure. The proposed method only checks the corresponding items, so it is not necessary to traverse all the landmarks in the reference frames, which is beneficial to real-time performance and cost efficiency. Experiments are performed to verify the effectiveness of our method on the public TUM and KITTI dataset. The results show that our system achieves considerable performance improvement compared with state-of-the-art methods.

     

Autonomous Landing of MAVs on an Arbitrarily Textured Landing Site Using Onboard Monocular Vision

This paper presents a novel solution for micro aerial vehicles (MAVs) to autonomously search for and land on an arbitrary landing site using real-time monocular vision. The autonomous MAV is provided with only one single reference image of the landing site with an unknown size before initiating this task. We extend a well-known monocular visual SLAM algorithm that enables autonomous navigation of the MAV in unknown environments, in order to search for such landing sites. Furthermore, a multi-scale ORB feature based method is implemented and integrated into the SLAM framework for landing site detection. We use a RANSAC-based method to locate the landing site within the map of the SLAM system, taking advantage of those map points associated with the detected landing site. We demonstrate the efficiency of the presented vision system in autonomous flights, both indoor and in challenging outdoor environment.     

Real-time implementation of airborne inertial-SLAM

This paper addresses some challenges to the real-time implementation of Simultaneous Localisation and Mapping (SLAM) on a UAV platform. When compared to the implementation of SLAM in 2D environments, airborne implementation imposes several difficulties in terms of computational complexity and loop closure, with high nonlinearity in both vehicle dynamics and observations. An implementation of airborne SLAM is formulated to relieve this computational complexity in both direct and indirect ways. Our implementation is based on an Extended Kalman Filter (EKF), which fuses data from an Inertial Measurement Unit (IMU) with data from a passive vision system. Real-time results from flight trials are provided.     

基于Rao-Blackwellized粒子滤波器移动机器人SLAM研究

SLAM是移动机器人在未知环境下实现自主导航的关键技术,为解决传统RBPF-SLAM算法建图效果差、计算效率低的不足,基于分层控制的思想,利用kobuki底盘和RPLIDAR A2雷达搭建了机器人导航系统,提出一种优化的Rao-Blackwellized粒子滤波的SLAM方法,粒子采样时纳入高精度的激光数据以弥补里程计数据的不足,优化建议分布函数,对相邻扫描帧进行迭代最近点匹配,增加自适应重采样步骤,并进行了现场建图实验.对比定位误差和运行效率,改进方法要优于传统方法,表明改进方法能有效解决上述问题.