基于激光雷达的环境特征提取方法研究

环境特征提取是移动机器人导航中的研究难点,以2D激光雷达为环境感知传感器,针对室内环境中的应用提出一种环境特征提取方法;通过激光雷达的测距精度评估,基于近邻方法对环境中障碍进行空间分类特征提取;对该方法不足进行分析的基础之上,为了能够提取更为精确的特征信息,将SOM方法应用于激光雷达的环境特征提取中;结合装备2D激光雷达LMS291的自行研制的移动机器人采集的数据进行实验,实验结果验证了所提方法的有效性.     

基于激光雷达的移动机器人障碍测距研究

障碍距离检测是移动机器人导航的关键问题之一。为了实现精确实时的障碍检测,针对某二维TOF激光雷达,对其数据标定、物体表面的属性、混合像素等因素进行试验,评估了其测距性能。同时,通过移动机器人运行过程中激光雷达的测距数据分析,设计了动态自适应滤波器以消除障碍检测中的测距噪声干扰。运行过程中的障碍检测试验表明:该方法可以实现可靠的障碍检测,并为移动机器人导航中环境建模、自定位及路径规划提供支持。     

移动机器人扩展卡尔曼滤波定位与传感器误差建模

针对里程计在定位过程中存在累积误差的问题,建立了一种通用的移动机器人里程计误差模型,对里程计误差进行实时反馈补偿.在利用激光雷达进行环境特征提取过程中,根据激光雷达原始数据存在的误差,建立了激光雷达的观测误差模型,并根据环境特征和机器人的相对位置关系,建立了移动机器人观测模型.最后,结合里程计和激光雷达误差模型,利用扩展卡尔曼滤波(EKF)实现了基于环境特征跟踪的移动机器人定位.实验结果验证了里程计和激光雷达误差模型的引入,在增加较短定位时间的情况下,可以有效地提高移动机器人的定位精度.     

一种混合结构的移动机器人导航控制策略

研究了未知环境下移动机器人实时的导航控制问题.采用分布式系统将反射式行为、反应式行为与慎思规划相结合，设计了移动机器人导航控制策略.根据激光雷达传感器信息设计了基于栅格的实时避障算法和解锁策略.通过慎思规划解决了复杂环境下的局部势能陷阱问题.通过自行研制的移动机器人IMR01的实验验证了导航策略的有效性.     

组合导航辅助的激光雷达－相机实时语义建图

针对64线和128线激光雷达价格过于昂贵,而16线激光雷达点云过于稀疏无法直接进行语义信息提取的问题,本文提出了一种组合导航辅助的激光雷达-相机实时语义建图方法,并通过算法结构设计保障了语义建图的实时性.首先,在组合导航定位结果辅助下,完成了不同采集时刻的点云-图像配准;其次,从图像目标检测框中准确提取了语义物体类别的点云.基于移动机器人平台测试评估了语义建图性能,结果表明该方法能够有效的提高语义点云提取的准确率并在嵌入式处理器Xavier上实时构建语义地图,为移动机器人利用语义信息进行导航和实时执行任务奠定了基础.     

基于双通分离窗滤波算法的激光雷达数据预处理方法

地图创建是移动机器人领域一个基本且重要的方面;数据预处理环节是利用激光雷达建立环境地图的初始环节,由于环境及激光雷达自身的原因,测距数据中存在抖动和噪声,为了减弱抖动和噪声对于建立地图的影响,需要对测距数据进行滤波平滑;在分析了限幅滤波,算术平均滤波等常见的软件滤波算法之后,继而针对这几种算法的不足提出了利用TPSW进行激光雷达数据的预处理;然后通过实验对比测试了几种滤波算法对于激光雷达测距数据的滤波平滑效果,实验结果表明,经过双通分离窗滤波后,抖动和噪声的影响明显减弱,所提方法有效且可行,滤波平滑效果优于限幅滤波等方法。     

多线激光雷达越野环境障碍检测

运用多线激光雷达实现了越野环境中障碍物的检测.为了分析了传感器安装参数对系统性能的影响,采用设计了分层聚类算法,实现了场景中数据的分类;对影响雷达测距精度的因素进行了分析,给出了雷达数据的滤波方法;以相对高度,坡度和点密度作为判决条件,完成了越野环境中障碍物的识别.算法应用到了越野环境下无人驾驶车辆的导航上,试验证明方法稳定可靠,符合车辆自主行驶的要求.     

环境特征提取在移动机器人导航中的应用

针对移动机器人在未知结构化环境中导航的需要,采用2D激光雷达作为主要传感器,对诸如墙壁、拐角、出口等这些典型的环境特征分别设计了一套有效的特征提取算法,并在该算法的基础上提出了基于特征点的移动机器人导航策略.该策略不需要里程计等其他一些内部传感器的信息,并且也不依赖具体的环境表述模型,从激光雷达扫描一次所得的数据中即可提取出环境特征,从而来指引机器人导航,实现起来快速可靠.应用到移动机器人MORCS-1上进行实验,取得了满意的结果,算法的实时性与鲁棒性得到了验证.     

一种基于卡尔曼滤波的DR/LMS组合导航定位算法

本文介绍了一种基于DR航位推算与LMS高精度激光雷达全向测距技术的组合式导航定位系统,旨在应用于强电磁干扰环境下的变电站智能机器人自动巡检环境。DR/LMS组合式导航定位系统原理相对简单、实现方便、实时性强,且与其他组合式导航系统相比,在满足同样定位精度的前提下,成本低廉,现场运行效果良好。特别地,本文提出了一种基于卡尔曼滤波方法的定位精度优化估计方法,对原有定位及导航精度(定位精度可以达到cm级)加以改进与优化,进一步提高了导航系统的稳定性与精确性。整个系统模型及控制策略的实现基于工业用PC控制板的上位机LABVIEW软件控制系统,并结合MATLAB软件进行仿真与数据分析,经现场运行测试,定位及导航精度完全可以满足现场工业环境的应用需求.     

未知环境下基于FSA的移动机器人导航策略

采用2D激光雷达作为主要传感器,设计了一种未知室内环境下的移动机器人导航策略;该策略首先把机器人室内环境下的导航行为分为3个状态集:墙壁导航、走廊导航和通路导航,然后利用有限状态自动机的原理把这几种状态集融合到一起,构成了一种移动机器人自主探索未知环境的导航策略;该策略的特点在于不依赖里程计的信息,并且也不需要任何的环境地图,实现起来快速准确,对于环境的变化具有较强的鲁棒性;将该策略应用到移动机器人MORCS-1上进行了测试,实验结果表明了算法具有良好的实时性与可靠性.     

Development of a low-cost active 3D triangulation laser scanner for indoor navigation of miniature mobile robots

For miniaturized mobile robots that aim at exploring unknown environments, no-contact 3D sensing of basic geometrical features of the surrounding environment is one of the most important capabilities for survival and the mission. In this paper, a low-cost active 3D triangulation laser scanner for indoor navigation of miniature mobile robots is presented. It is implemented by moving both a camera and a laser diode together on the robot’s movable part. The movable part is actuated by a servo motor through a gear train to achieve ±90° scanning view angle. The software module includes image processing and data post-processing. 3D world coordinates are calculated from 2D image coordinates based on the triangulation principle. With a 3D laser scanning method, navigation algorithms for obstacle avoidance and gateway passing are proposed. Finally, experiments are conducted to validate performance of the scanner and to test the efficiency of the navigation algorithms.     

Mobile robot motion estimation by 2D scan matching with genetic and iterative closest point algorithms

The paper reports on mobile robot motion estimation based on matching points from successive two‐dimensional (2D) laser scans. This ego‐motion approach is well suited to unstructured and dynamic environments because it directly uses raw laser points rather than extracted features. We have analyzed the application of two methods that are very different in essence: (i) A 2D version of iterative closest point (ICP), which is widely used for surface registration; (ii) a genetic algorithm (GA), which is a novel approach for this kind of problem. Their performance in terms of real‐time applicability and accuracy has been compared in outdoor experiments with nonstop motion under diverse realistic navigation conditions. Based on this analysis, we propose a hybrid GA‐ICP algorithm that combines the best characteristics of these pure methods. The experiments have been carried out with the tracked mobile robot Auriga‐α and an on‐board 2D laser scanner. © 2006 Wiley Periodicals, Inc.     

移动机器人行为参数的PSO多目标优化

根据移动机器人的导航任务,提出基于粒子群优化(PSO)算法的行为参数多目标分层优化方法。将导航方向与导航速度相关的参数按优先级进行PSO算法分层选取,使机器人在路径近似最优的基础上实现导航时间最少。仿真结果表明,该方法可以提高导航效率,实现导航决策的逐步求精,从而改善机器人在未知环境下的自主导航性能。     

On the behaviour of low cost laser scanners in HW/SW particle filter SLAM applications

Particle filters (PFs) are computationally intensive sequential Monte Carlo estimation methods with applications in the field of mobile robotics for performing tasks such as tracking, simultaneous localization and mapping (SLAM) and navigation, by dealing with the uncertainties and/or noise generated by the sensors as well as with the intrinsic uncertainties of the environment. However, the application of PFs with an important number of particles has traditionally been difficult to implement in real-time applications due to the huge number of operations they require. This work presents a hardware implementation on FPGA (field programmable gate arrays) of a PF applied to SLAM which aims to accelerate the execution time of the PF algorithm with moderate resource. The presented system is evaluated for different sensors including a low cost Neato XV-11 laser scanner sensor. First the system is validated by post processing data provided by a realistic simulation of a differential robot, equipped with a hacked Neato XV-11 laser scanner, that navigates in the Robot@Factory competition maze. The robot was simulated using SimTwo, which is a realistic simulation software that can support several types of robots. The simulator provides the robot ground truth, odometry and the laser scanner data. Then the proposed solution is further validated on standard laser scanner sensors in complex environments. The results achieved from this study confirmed the possible use of low cost laser scanner for different robotics applications which benefits in several aspects due to its cost and the increased speed provided by the SLAM algorithm running on FPGA.     

A New Mobile Robot Toolbox for Matlab

In this study, a wheeled mobile robot navigation toolbox for Matlab is presented. The toolbox includes algorithms for 3D map design, static and dynamic path planning, point stabilization, localization, gap detection and collision avoidance. One can use the toolbox as a test platform for developing custom mobile robot navigation algorithms. The toolbox allows users to insert/remove obstacles to/from the robot’s workspace, upload/save a customized map and configure simulation parameters such as robot size, virtual sensor position, Kalman filter parameters for localization, speed controller and collision avoidance settings. It is possible to simulate data from a virtual laser imaging detection and ranging (LIDAR) sensor providing a map of the mobile robot’s immediate surroundings. Differential drive forward kinematic equations and extended Kalman filter (EKF) based localization scheme is used to determine where the robot will be located at each simulation step. The LIDAR data and the navigation process are visualized on the developed virtual reality interface. During the navigation of the robot, gap detection, dynamic path planning, collision avoidance and point stabilization procedures are implemented. Simulation results prove the efficacy of the algorithms implemented in the toolbox.     

Set-point Control of Mobile Robot with Obstacle Detection and Avoidance Using Navigation Function - Experimental Verification

This paper presents the results of an experimental verification of mobile robot control algorithm including obstacle detection and avoidance. The controller is based on the navigation potential function that was proposed in work (Urakubo, Nonlinear Dyn. 81(3), 1475–1487 2015). Conducted experiments considered the task of reaching and stabilization of robot in point. The navigation potential agregates information of robot position and orientation but also the repelling potentials of obstacles. The obstacle detection is performed solely with the use of laser scanner. The experiments show that the method can easily handle environments with one or two obstacles even if they instantly hide or show-up due to the scanner range limits. The experiments also indicate that the utilized control method has a good potential for being used in parallel parking task.     

Camera Recognition and Laser Detection based on EKF-SLAM in the Autonomous Navigation of Humanoid Robot

The ability of autonomous navigation of the humanoid robot under unknown environment is very important to real-life applications. EKF-SLAM based on the camera recognition and laser detection for humanoid robot NAO is presented in this paper. Camera recognition is used to recognize if the object is a landmark. Because the computational resources needed for the feature-based position estimation are quite expensive, the laser instead of the camera provides the position of the landmark. A fractional order proportional-integral (PI) controller is designed to reduce the derivation of the NAO robot from the desired path during autonomous navigation. Experiments show that the proposed method is valid and reliable for autonomous navigation of the NAO robot under unknown environment.