Review of Simultaneous Localization and Mapping Technology in the Agricultural Environment

Simultaneous localization and mapping(SLAM)is one of the most attractive research hotspots in the field of robotics,and it is also a prerequisite for the autonomous navigation of robots.It can significantly improve the autonomous navigation ability of mobile robots and their adaptability to different application environments and contribute to the realization of real-time obstacle avoidance and dynamic path planning.Moreover,the application of SLAM technology has expanded from industrial production,intelligent transportation,special operations and other fields to agricultural environments,such as autonomous navigation,independent weeding,three-dimen-sional(3D)mapping,and independent harvesting.This paper mainly introduces the principle,sys-tem framework,latest development and application of SLAM technology,especially in agricultural environments.Firstly,the system framework and theory of the SLAM algorithm are introduced,and the SLAM algorithm is described in detail according to different sensor types.Then,the devel-opment and application of SLAM in the agricultural environment are summarized from two aspects:environment map construction,and localization and navigation of agricultural robots.Finally,the challenges and future research directions of SLAM in the agricultural environment are discussed.

Research on simultaneous localization and mapping for AUV by an improved method:Variance reduction FastSLAM with simulated annealing

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.

Robust Iterated Sigma Point FastSLAM Algorithm for Mobile Robot Simultaneous Localization and Mapping

Simultaneous localization and mapping （SLAM） is a key technology for mobile robots operating under unknown environment. While FastSLAM algorithm is a popular solution to the SLAM problem, it suffers from two major drawbacks： one is particle set degeneracy due to lack of observation information in proposal distribution design of the particle filter; the other is errors accumulation caused by linearization of the nonlinear robot motion model and the nonlinear environment observation model. For the purpose of overcoming the above problems, a new iterated sigma point FastSLAM （ISP-FastSLAM） algorithm is proposed. The main contribution of the algorithm lies in the utilization of iterated sigma point Kalman filter （ISPKF）, which minimizes statistical linearization error through Gaussian-Newton iteration, to design an optimal proposal distribution of the particle filter and to estimate the environment landmarks. On the basis of Rao-Blackwellized particle filter, the proposed ISP-FastSLAM algorithm is comprised by two main parts： in the first part, an iterated sigma point particle filter （ISPPF） to localize the robot is proposed, in which the proposal distribution is accurately estimated by the ISPKF; in the second part, a set of ISPKFs is used to estimate the environment landmarks. The simulation test of the proposed ISP-FastSLAM algorithm compared with FastSLAM2.0 algorithm and Unscented FastSLAM algorithm is carried out, and the performances of the three algorithms are compared. The simulation and comparing results show that the proposed ISP-FastSLAM outperforms other two algorithms both in accuracy and in robustness. The proposed algorithm provides reference for the optimization research of FastSLAM algorithm.

A novel method for mobile robot simultaneous localization and mapping

A novel mobile robot simultaneous localization and mapping (SLAM) method is implemented by using the Rao- Blackwellized particle filter (RBPF) for monocular vision-based autonomous robot in unknown indoor environment. The particle filter combined with unscented Kalman filter (UKF) for extending the path posterior by sampling new poses integrating the current observation. Landmark position estimation and update is implemented through UKF. Furthermore, the number of resampling steps is determined adaptively, which greatly reduces the particle depletion problem. Monocular CCD camera mounted on the robot tracks the 3D natural point landmarks structured with matching image feature pairs extracted through Scale Invariant Feature Transform (SIFT). The matching for multi-dimension SIFT features which are highly distinctive due to a special descriptor is implemented with a KD-Tree. Experiments on the robot Pioneer3 showed that our method is very precise and stable.

Mobile Robot Hierarchical Simultaneous Localization and Mapping Using Monocular Vision

A hierarchical mobile robot simultaneous localization and mapping (SLAM) method that allows us to obtain accurate maps was presented. The local map level is composed of a set of local metric feature maps that are guaranteed to be statistically independent. The global level is a topological graph whose arcs are labeled with the relative location between local maps. An estimation of these relative locations is maintained with local map alignment algorithm, and more accurate estimation is calculated through a global minimization procedure using the loop closure constraint. The local map is built with Rao-Blackwellised particle filter (RBPF), where the particle filter is used to extending the path posterior by sampling new poses. The landmark position estimation and update is implemented through extended Kalman filter (EKF). Monocular vision mounted on the robot tracks the 3D natural point landmarks, which are structured with matching scale invariant feature transform (SIFT) feature pairs. The matching for multi-dimension SIFT features is implemented with a KD-tree in the time cost of O(lbN). Experiment results on Pioneer mobile robot in a real indoor environment show the superior performance of our proposed method.

Rapid State Augmentation for Compressed EKF-Based Simultaneous Localization and Mapping

A new method for speeding up the state augment operations involved in the compressed extended Kalman filter-based simultaneous localization and mapping （CEKF-SLAM） algorithm was proposed. State augment usually requires a fully-updated state eovariance so as to append the information of newly observed landmarks, thus computational volume increases quadratically with the number of landmarks in the whole map. It was proved that state augment can also be achieved by augmenting just one auxiliary coefficient ma- trix. This method can yield identical estimation results as those using EKF-SLAM algorithm, and computa- tional amount grows only linearly with number of increased landmarks in the local map. The efficiency of this quick state augment for CEKF-SLAM algorithm has been validated by a sophisticated simulation project.

Simultaneous Localization and Mapping System Based on Labels

In this paper a label-based simultaneous localization and mapping（ SLAM） system is proposed to provide localization to indoor autonomous robots. In the system quick response（ QR） codes encoded with serial numbers are utilized as labels. These labels are captured by two webcams,then the distances and angles between the labels and webcams are computed. Motion estimated from the two rear wheel encoders is adjusted by observing QR codes. Our system uses the extended Kalman filter（ EKF） for the back-end state estimation. The number of deployed labels controls the state estimation dimension. The label-based EKF-SLAM system eliminates complicated processes,such as data association and loop closure detection in traditional feature-based visual SLAM systems. Our experiments include software-simulation and robot-platform test in a real environment. Results demonstrate that the system has the capability of correcting accumulated errors of dead reckoning and therefore has the advantage of superior precision.

Underwater Simultaneous Localization and Mapping Based on Forward-looking Sonar

A method of underwater simultaneous localization and mapping （SLAM） based on forward-looking sonar was proposed in this paper. Positions of objects were obtained by the forward-looking sonar, and an improved association method based on an ant colony algorithm was introduced to estimate the positions. In order to improve the precision of the positions, the extended Kalman filter （EKF） was adopted. The presented algorithm was tested in a tank, and the maximum estimation error of SLAM gained was 0.25 m. The tests verify that this method can maintain better association efficiency and reduce navigatioJ~ error.

基于深度学习的移动机器人语义SLAM方法研究

为了给移动机器人提供细节丰富的三维语义地图,支撑机器人的精准定位,本文提出一种结合RGB-D信息与深度学习结果的机器人语义同步定位与建图方法。改进了ORB-SLAM2算法的框架,提出一种可以构建稠密点云地图的视觉同步定位与建图系统;将深度学习的目标检测算法YOLO v5与视觉同步定位与建图系统融合,反映射为三维点云语义标签,结合点云分割完成数据关联和物体模型更新,并用八叉树的地图形式存储地图信息;基于移动机器人平台,在实验室环境下开展移动机器人三维语义同步定位与建图实验,实验结果验证了本文语义同步定位与建图算法的语义信息映射、点云分割与语义信息匹配以及三维语义地图构建的有效性。

视觉SLAM方法综述

实时定位与建图(SLAM)技术搭载特定传感器,使移动机器人在无任何环境先验条件下,在运动过程中自主建立环境模型来计算自身位姿,大幅提高其自主导航能力,以及对不同应用环境的适应性。视觉SLAM方法以相机作为外部传感器,通过采集周围环境信息来创建地图并实时估计机器人自身位姿。为此,介绍了具有代表性的经典视觉SLAM方法及与深度学习相结合的视觉SLAM方法,分析了视觉SLAM方法中采用的不同特征检测方法、后端优化、闭环检测,以及动态环境下视觉SLAM方法的应用,总结了视觉SLAM方法的问题,并探讨了视觉SLAM方法在未来的热点研究方向和发展前景。

面向港口环境精细感知的无人船多传感器融合SLAM系统

针对港口环境高精度感知需求,综合考虑影响同时定位与建图(SLAM)精度的港口环境因素,提出基于多传感器融合的激光SLAM环境感知方案。通过分析多种传感器对港口SLAM环境感知的影响,引入惯性测量传感器弥补激光SLAM输出频率低和剧烈运动位姿估计不准确等缺陷,采用卫星定位系统信息进行高程数据约束,处理船舶运动特性导致的垂荡累计漂移。从应用需求出发,对传感器进行选型和布置优化,搭建基于无人船的港口环境多传感器融合SLAM系统。结果表明,提出的港口环境高精度点云地图获取方案能在典型港口场景下准确实时建图,为水面精细SLAM提供技术支持。

基于激光SLAM多地形机器人的设计

为解决传统轮式机器人在复杂地形中受限与腿式机器人控制策略复杂的问题,提出一种多地形机器人。结合激光即时定位与地图构建(SLAM)方法和自适应式轮腿机构,将树莓派作为运算单元,搭载(ROS)机器人操作系统,应用激光SLAM技术实现环境地图构建和机器人导航,同时结合深度模型和摄像头完成图像任务。自适应式轮腿机械结构使机器人能够根据环境需求自动切换为轮式或腿式行进模式。底层控制器采用STM32F407,机器人通过PID算法能实现精准的移动和机械臂作业。结果表明:该多地形机器人控制方法简单高效,在坡地、草地、坑地、台阶障碍物等复杂地形中展现了灵活移动的能力,最大翻越障碍高度可达250 mm,爬坡角度可达45°,在稳定性和适应性方面具有显著优势。

基于改进特征描述的SLAM动态算法研究

针对原ORB描述符算法匹配精度低、匹配耗时长,动态场景中移动的物体严重影响视觉SLAM系统的定位精度和鲁棒性,以及ORB-SLAM3系统只能构建稀疏点云地图,无法构建稠密地图的问题,提出一种基于BEBLID描述符和目标检测的改进型ORB-SLAM3。在跟踪线程中融合轻量级YOLOv5s动态目标检测网络和动态特征剔除模块,提高系统的定位精度;利用增强高效局部图像描述符BEBLID代替原特征描述算法,与原ORB特征提取方法结合,增强图像的表现力和描述效率,提升特征匹配精度和效率;增加稠密建图线程,根据关键帧与相应位姿完成稠密点云地图的构建。在公开TUM RGB-D数据集上的实验表明,与原ORB-SLAM3相比,本文算法特征匹配精度提高了7%以上;在高动态环境下系统定位精度提高98%以上,在低动态环境下最大提升60%以上,有效提高了系统在动态环境下的定位精度和鲁棒性;并构建了三维稠密点云地图,为后续应用于机器人自主导航、避障和路径规划等工作奠定了基础。

多传感器融合SLAM研究综述

如今,移动机器人技术的发展使得同步定位与建图(SLAM)技术越来越受到学者的关注。在未知环境下,使移动机器人能够自主完成建图或者探索,是SLAM最基本的要求。在过去的十年,单传感器为机器人的建图和探索提供了良好的效果,而多传感器融合SLAM则以其强鲁棒、高精度的技术特性,为提升移动机器人建图的精度和速度提供了更高的可能性,成为了SLAM发展的主要研究方向。文中总结了现今多传感器融合SLAM的方案,首先对单传感器方案进行了比较;然后对多传感器融合技术的方案进行了对比;最后,分析了多传感器融合SLAM的难点与解决方案,并对多传感器融合SLAM的未来与发展进行了探讨。

基于点线特征融合的实时视惯SLAM算法

为了在光照不足和低纹理场景中实现移动机器人的高精度实时定位和建图,提出了一种基于视觉点线特征以及IMU特征融合的实时SLAM算法。首先通过跳跃路由策略和自适应阈值策略改进了EDlines算法,提高了线特征提取的质量,从而提高了特征跟踪的有效性。然后将视觉惯性特征紧耦合建立约束,通过滑动窗口和边缘化模型进行非线性优化,实现了高精度高实时性的状态估计。实验证明,所提算法在线特征提取的有效性方面优于传统的线段提取算法,同时SLAM系统的定位精度和鲁棒性均得到有效提升。

动态场景下基于实例分割与光流的语义SLAM建图

视觉同步定位与建图技术常用于室内智能机器人的导航,但是其位姿是以静态环境为前提进行估计的。为了提升视觉即时定位与建图(Simultaneous Localization And Mapping,SLAM)在动态场景中的定位与建图的鲁棒性和实时性,在原ORB-SLAM2基础上新增动态区域检测线程和语义点云线程。动态区域检测线程由实例分割网络和光流估计网络组成,实例分割赋予动态场景语义信息的同时生成先验性动态物体的掩膜。为了解决实例分割网络的欠分割问题,采用轻量级光流估计网络辅助检测动态区域,生成准确性更高的动态区域掩膜。将生成的动态区域掩膜传入到跟踪线程中进行实时剔除动态区域特征点,然后使用地图中剩余的静态特征点进行相机的位姿估计并建立语义点云地图。在公开TUM数据集上的实验结果表明,改进后的SLAM系统在保证实时性的前提下,提升了其在动态场景中的定位与建图的鲁棒性。

基于语义分割的视觉SLAM算法研究

目前大多数的视觉SLAM算法基于静态环境的假设,环境中的动态物体容易引起位姿估计的不准确。提出一种针对动态环境的改进算法。基于DS-SLAM方案进行改进,首先采用自适应阈值提取ORB特征点并通过改进四叉树算法将特征点均匀化;之后采用稀疏光流法跟踪角点的运动,同时结合Segment语义分割线程的结果分割动态物体;最后采用几何约束滤除动态点,保留高质量的特征点进行位姿估计,完成定位和建图功能。利用TUM数据集进行精度评测,相比于DS-SLAM算法,改进算法的实时性提升了9.02%。动态环境中相机位姿误差缩小了38.94%。通过提高特征点的质量,结合光流法和语义分割的优势,提升了机器人系统的定位精度和实时性。

动态场景下基于语义分割的视觉SLAM方法

针对在动态场景下视觉同步定位与建图(SLAM)鲁棒性差、定位与建图精度易受动态物体干扰的问题,设计一种基于改进DeepLabv3plus与多视图几何的语义视觉SLAM算法。以语义分割网络DeepLabv3plus为基础,采用轻量级卷积网络MobileNetV2进行特征提取,并使用深度可分离卷积代替空洞空间金字塔池化模块中的标准卷积,同时引入注意力机制,提出改进的语义分割网络DeepLabv3plus。将改进后的语义分割网络DeepLabv3plus与多视图几何结合,提出动态点检测方法,以提高视觉SLAM在动态场景下的鲁棒性。在此基础上,构建包含语义信息和几何信息的三维语义静态地图。在TUM数据集上的实验结果表明,与ORB-SLAM2相比,该算法在高动态序列下的绝对轨迹误差的均方根误差值和标准差(SD)值最高分别提升98%和97%。

用于VSLAM系统的CNN在FPGA平台上的加速

为实现视觉同步定位与建图系统中卷积神经网络在FPGA上的加速,基于SuperPoint模型设计一种低功耗高效CNN加速器及相应的SoC系统。采用循环分块、数据复用、计算单元展开和双缓冲策略充分利用加速器的片上资源;为提高突发传输效率,预先对权重参数重排;提出Pack模块和Unpack模块,设计多通道数据传输,用于提高传输带宽。在Ultra96-V2 FPGA平台上部署整个SoC系统,在仅3 W左右的功耗下实现25.63 GOPS的吞吐量,其BRAM效率、DSP效率、性能密度和功耗效率相比之前的文献有明显优势。

煤矿井下移动机器人多传感器自适应融合SLAM方法

基于同时定位与建图(SLAM)技术的移动机器人能够快速、准确、自动化地采集空间数据,进行空间智能感知和环境地图构建,是实现煤矿智能化和无人化的关键。针对目前煤矿井下多传感器融合SLAM方法存在机器人前端位姿估计退化失效和后端融合精度不足的问题,提出了一种煤矿井下移动机器人激光雷达(LiDAR)−视觉−惯性(IMU)自适应融合SLAM方法。对LiDAR点云数据进行聚类分割,提取线面特征,利用IMU预积分状态进行畸变校正,采用基于自适应Gamma校正和对比度受限的自适应直方图均衡化(CLAHE)的图像增强算法处理低照度图像,再提取视觉点线特征。用IMU预积分状态为LiDAR特征匹配与视觉特征跟踪提供位姿初始值。根据LiDAR相邻帧的线面特征匹配得到移动机器人位姿,之后进行视觉点线特征跟踪,分别计算LiDAR、视觉、IMU位姿变化值,通过设定动态阈值来检测前端里程计的稳定性,自适应选取最优位姿。对不同传感器构建残差项,包括点云匹配残差、IMU预积分残差、视觉点线残差、边缘化残差。为了兼顾精度与实时性,基于滑动窗口实现激光点云特征、视觉特征、IMU测量的多源数据联合非线性优化,实现煤矿井下连续可用、精确可靠的SLAM。对图像增强前后效果进行试验验证,结果表明,基于自适应Gamma校正和CLAHE的图像增强算法能显著提升背光区和光照区的亮度和对比度,增加图像中的特征信息,大幅提升特征点提取数量和匹配质量,匹配成功率达90.7%。为验证所提方法的性能,在狭长走廊和煤矿巷道场景下进行试验验证,结果表明,所提方法在狭长走廊场景的定位均方根误差为0.15 m,构建的点云地图一致性较高;在煤矿巷道场景中的定位均方根误差为0.19 m,构建的点云地图可真实地反映煤矿井下环境。