Collaborative positioning for swarms:A brief survey of vision,LiDAR and wireless sensors based methods

As positioning sensors,edge computation power,and communication technologies continue to develop,a moving agent can now sense its surroundings and communicate with other agents.By receiving spatial information from both its environment and other agents,an agent can use various methods and sensor types to localize itself.With its high flexibility and robustness,collaborative positioning has become a widely used method in both military and civilian applications.This paper introduces the basic fundamental concepts and applications of collaborative positioning,and reviews recent progress in the field based on camera,LiDAR(Light Detection and Ranging),wireless sensor,and their integration.The paper compares the current methods with respect to their sensor type,summarizes their main paradigms,and analyzes their evaluation experiments.Finally,the paper discusses the main challenges and open issues that require further research.

New self-calibration approach to space robots based on hand-eye vision

To overcome the influence of on-orbit extreme temperature environment on the tool pose(position and orientation) accuracy of a space robot,a new self-calibration method based on a measurement camera(hand-eye vision) attached to its end-effector was presented.Using the relative pose errors between the two adjacent calibration positions of the space robot,the cost function of the calibration was built,which was different from the conventional calibration method.The particle swarm optimization algorithm(PSO) was used to optimize the function to realize the geometrical parameter identification of the space robot.The above calibration method was carried out through self-calibration simulation of a six-DOF space robot whose end-effector was equipped with hand-eye vision.The results showed that after calibration there was a significant improvement of tool pose accuracy in a set of independent reference positions,which verified the feasibility of the method.At the same time,because it was unnecessary for this method to know the transformation matrix from the robot base to the calibration plate,it reduced the complexity of calibration model and shortened the error propagation chain,which benefited to improve the calibration accuracy.

Robot Positioning Based on Multiple Quick Response Code Landmarks

The scheme of robot positioning based on multiple quick response(QR)code landmarks is proposed.Firstly,the pose of the robot relative to the QR code landmarks is obtained by extracting the feature points of the QR code,combined with the visual computing technology.Then,the conversion of the absolute pose of the robot is completed based on the absolute position of the QR code landmark,and thus the real-time position of the robot is obtained.The proposed scheme makes full use of the QR code fault tolerance and multiple QR code landmarks to improve the calculation accuracy.It has good robustness and versatility,and it is easy to implement.It can help the robot to complete the positioning in the actual work,making robot navigation more accurate.

Research on DSO vision positioning technology based on binocular stereo panoramic vision system

In the visual positioning of Unmanned Ground Vehicle(UGV),the visual odometer based on direct sparse method(DSO) has the advantages of small amount of calculation,high real-time performance and high robustness,so it is more widely used than the visual odometer based on feature point method.Ordinary vision sensors have a narrower viewing angle than panoramic vision sensors,and there are fewer road signs in a single frame of image,resulting in poor road sign tracking and positioning capabilities,and severely restricting the development of visual odometry.Based on these considerations,this paper proposes a binocular stereo panoramic vision positioning algorithm based on extended DSO,which can solve these problems well.The experimental results show that the binocular stereo panoramic vision positioning algorithm based on the extended DSO can directly obtain the panoramic depth image around the UGV,which greatly improves the accuracy and robustness of the visual positioning compared with other ordinary visual odometers.It will have widely application prospects in the UGV field in the future.

Binocular Vision Positioning Method for Safety Monitoring of Solitary Elderly

In nowadays society,the safety of the elderly population is becoming a pressing concern,especially for those who live alone.There might be daily risks such as accidental falling or treatment attack on them.Aiming at these problems,indoor positioning could be a critical way to monitor their states.With the rapidly development of the imaging techniques,wearable and portable cameras are very popular,which could be set on human individual.And in view of the advantages of the visual positioning,the authors propose a binocular visual positioning algorithm to real-timely locate the elderly indoor.In this paper,the imaging model has been established with the corrected image data from the binocular camera;then feature extraction has been completed to provide reference to adjacent image matching based on the binary robust independent elementary feature(BRIEF)descriptor,finally the camera movement and the states of the elderly have been estimated to distinguish their falling risk.In the experiments,the real-sense D435i sensors were adopted as the binocular cameras to obtain indoor images,and three experimental scenarios have been carried out to test the proposed method.The results show that the proposed algorithm can effectively locate the elderly indoor and improve the real-time monitoring capability.

Study of Web-based integration of pneumatic manipulator and its vision positioning

Pneumatic driven system is widely used in industrial automation, mainly for relatively simple tasks with open-loop control. Because of the pneumatic system’s compressibility and few stop positions, it was considered hard to control in a precise motion control system. With the help of newly developed pneumatic servo control technology, using servo-pneumatic positioning controller now is just as easy as using electro-servo system. This article discusses Web-based servo-pneumatic manipulator control and object recognition and positioning. The authors built a three-degrees-of-freedom (3 DOF) pneumatic manipulator with a servo-pneumatic closed-loop control system and machine vision system in their lab. Web-based tele-operation was a basic ability in this experimental system. After installing a CCD camera, video capture card, and related software developed by the authors, the robot could recognize the user specified object through the Web page and find its position. The remote user could command the robot to move to the position and to grab the object. The critical issues of Web-based control are to integrate hybrid open-architecture mechatronic system through the Web and develop a software language environment characterized by the script. The authors’ experiment showed that pneumatic devices could serve as accurate position control and be controlled through the Web.

基于TwinCAT Vision的自动插磁视觉定位系统设计

为解决传统的视觉系统与组装流水线的流程控制分属于两套不同系统的问题,在通过串口或TCP/IP进行通信时易导致停机、停线、减慢生产节拍等问题,利用TwinCAT Vision机器视觉模块设计了一套流水线上的转子视觉定位系统,系统的图像处理部分被添加到整合PLC(programmable logic controller)运动控制的通用控制平台TwinCAT上,实现与整个转子装配流水线中PLC运动控制模块的无缝连接。视觉定位系统通过TwinCAT Vision采集流水线操作台上的转子图像,传递到实时内核模式下的PLC机器视觉与工艺流程控制系统中。研究表明,与传统机器视觉方案相比,该视觉定位系统减少了通信环节,提高了系统稳定性,节省时间约26.2 ms,效率提高96.3%左右,有效缩短了检测环节的用时。

Optimal Positioning of Mobile Platforms for Accurate Manipulation Operations

Many mobile robotics applications, especially in industrial environments, require the robot to perform safe navigation and then reach the goal with a high precision. In this research work, the objective is to analyze the appropriateness of autonomous natural navigation strategies for mobile manipulation tasks. The system must position itself in a realistic map, follow a path closely and then achieve an accurate positioning in the destination point in order to be able to perform the manipulation, inspection or pick task efficiently. Autonomous navigation is not able to fulfill the accuracy required by some of the jobs so that a second positioning system using vision is proposed in this paper. The experiments show that localization systems have, on average, an error greater than a decimetre and how an additional positioning system can reduce it to a few millimetres.

基于单激光束信息的掘锚装备视觉定位方法研究

煤矿井下掘锚装备智能化是改善行业采掘失衡问题的关键,而掘锚装备的精确定位是实现其智能化的前提。与其他传统定位方法相比,基于视觉的位姿测量方法以其无接触、无累计误差的优势在煤矿井下得到了初步的应用。针对目前煤矿井下掘进工作面掘锚装备视觉定位方法存在的合作标靶结构复杂、标定繁琐的问题,结合掘进工作面原有激光指向仪特征,提出一种基于单激光束信息的掘锚装备视觉定位方法。该方法通过分析激光指向仪光斑及光束图像特征,提出了一种基于二维反正切函数拟合的激光光斑中心提取方法和基于Hough直线检测的激光束中心线提取方法,构建了基于点线特征的双目视觉位姿解算模型,得出了掘锚装备在巷道中的实时位姿。最后,为了验证提出的特征提取方法和视觉定位方法的可行性和准确性,在实验室模拟掘进工作面工况环境搭建平台进行了试验。结果表明:基于矿用激光指向仪信息的掘锚装备视觉定位方法具有较高的位姿测量精度。在50 m的测试范围内,机身位置在巷道坐标系下沿X轴、Y轴和Z轴的平均测量误差分别为25.44、58.64、31.08 mm,其最大误差分别为55.16、127.39、63.57 mm;机身姿态在巷道坐标系下的俯仰角、偏航角和横滚角的平均测量误差分别为0.22°、0.22°、0.41°,其最大误差分别为0.29°、0.37°、0.58°。满足煤矿井下巷道施工的定位精度要求。

基于双自由度转台的全向空间单目视觉室内定位测量方法

针对传统单目视觉测量系统测量视场有限的问题,本文提出一种基于双自由度旋转平台的全向空间单目视觉测量方法。首先,对双自由度旋转平台的转轴参数进行标定,用副相机拍摄固定在双自由度转台上的棋盘格标定板,提取棋盘格角点的位置坐标,并将其转化到同一相机坐标系下。利用PCA(主成分分析)平面拟合得到初始位置转轴参数中的方向向量,使用空间最小二乘圆拟合方法得到初始位置下转轴参数中的位置参数。然后,通过转台转动的角度以及罗德里格斯公式将不同位置下相机获取的数据进行坐标系统一,实现水平和竖直方向全向空间下的目标测量。最后,通过高精度激光测距仪验证了本方法的测量精度,并通过与双目视觉测量系统、wMPS测量系统进行比对实验,验证了本方法的全向空间测量能力。实验结果表明,本方法测量精度基本达到双目视觉测量系统水平,但测量范围远大于双目视觉测量,可以满足全向空间测量要求。

基于机器视觉的芯片字符区域分割和定位算法

芯片表面的字符对分选具有重要意义,对字符的定位是分选工作的关键步骤。为了提高分选工作定位效率和定位精度,提出了一种基于改进的区域生长算法和凸包检测算法分割和定位芯片表面字符区域方法。首先,对采集图像进行预处理操作,利用改进的Canny算法获取无干扰图像边缘,将图像边缘作为区域生长法的种子点并以图像自适应阈值作为生长准则分割图像,使用最大内接矩形算法粗定位字符区域;其次,采用Harris角点检测算法获取字符角点分布位置;最后,筛选角点并提取关键点,利用一种改进的凸包检测算法定位字符区域。经过实验验证,所设计的算法能够完整的分割和定位芯片表面字符区域,定位精度和效率较原有方法提升5.3%和15.4%,满足实际工业生产的要求。

基于视频的轨道车辆自主定位方法研究

针对轨道施工车辆自主定位需求,提出一种基于车载前视相机拍摄百米标视频的轨道车辆自主定位方法。该方法首先对YOLOX-s网络进行改进并构建了百米标的目标检测模型,完成对百米标的目标检测;其次,当检测到百米标后,结合图像预处理和卷积循环神经网络(CRNN)网络构建百米标数字文本识别模型,提取百米标的数字文本信息,从而实现对轨道施工车辆的定位。经实验验证该方法能够快速准确定位轨道施工车辆的位置信息。

形状匹配的铁路油罐车罐口视觉定位方法

为了克服非均匀光照、车型以及摄像机安装位置等因素造成的罐口定位误差,提出了一种基于形状匹配的铁路油罐车罐口视觉定位方法。利用罐口为标准几何形状的特点,使用标准图像提取罐口边缘并进行形状拟合;将得到的轮廓形状作为图像识别模板,在待搜索图像中使用基于轮廓的归一化互相关查找目标;在搜索过程中对形状模板进行缩放,以兼容不同型号车型罐口;利用图像金字塔技术减小计算量,加快匹配速度。结果表明,所提出的方法满足误差要求,能够应用于工业现场。

复杂环境下基于视觉/惯性的单兵自主定位性能评估

针对在卫星信号拒止等复杂环境下单兵自主定位精度低的问题,提出基于视觉/惯性测量单元(IMU)的单兵自主定位技术。将高效的IMU初始化方法融合到ORB-SLAM3算法并应用于单兵自主定位技术中,评估了单兵实时运动整体定位精度,重点分析了改进ORB-SLAM3算法在单目/IMU、双目/IMU下的定位精度准确性和鲁棒性。实验表明:在复杂树林环境下,单兵在基于视觉/IMU自主定位时,改进算法的IMU初始化时间最少提高了10 s,双目/IMU的估计轨迹曲线更加吻合实际运动轨迹曲线。在绝对轨迹误差的各项评估指标中,双目/IMU比单目/IMU的均方根误差提高了24.67%,而且定位精度和鲁棒性都要优于单目/IMU,为城市巷战中单兵自主高精度定位的实现提供了一种切实可行的思路和举措。

应用激光跟踪仪和单目视觉检测三维水模体定位精度方法研究

针对三维水模体检测方法较少、检测过程复杂等问题,提出基于激光跟踪仪和单目视觉的三维水模体定位精度检测方法。激光跟踪仪三维水模体定位精度检测对比实验验证三维水模体在有水和无水的情况下定位精度一致。单目视觉三维水模体定位精度检测实验结果表明:X轴、Y轴、Z轴和空间对角线的定位误差均在0.050 mm以内,重复性分别为0.030 mm,0.064 mm,0.056 mm,0.140 mm,X轴和Y轴的垂直度为0.800 mm,Y轴和Z轴的垂直度为0.761 mm,X轴和Z轴的垂直度为0.503 mm,与激光跟踪仪的测量精度在一个量级。最后,经不确定度分析得到相邻点距离测量误差的标准差为0.0187 mm,满足检测要求。两种方法都能实现非接触测量,简化冗杂的检测过程,可满足医院对医用直线加速器的日常检测需求。

深海自主对接级联式视觉导引定位技术研究

针对深海工作站自主对接回收作业潜器的视觉定位问题,提出一种多类型标志的级联式导引定位策略,设计基于单目视觉定位的水下对接导引定位系统,采用改进k-means聚类算法进行多阈值自适应图像分割,实现对坞站预设的导引光源和AprilTag识别定位。分别在有、无自然光照条件下,开展水下导引定位与对接的水池试验,在水下存在大量悬浮颗粒和光照不均匀等条件下仍然取得较好的实际识别定位效果,验证了本文所提出方法的合理性和稳定性。

基于视觉点线特征自适应融合的VINS定位方法

由于Vins-mono算法在弱纹理环境中的定位精度不高,直接引入线特征的PL-Vinsmono算法的实时性能较差,故提出一种基于视觉点线特征自适应融合的VINS定位方法。首先在前端评估点特征质量,然后根据点特征质量判断是否引入线特征,最后在后端构建不同的损失函数进行迭代,提高了算法在弱纹理环境中的定位精度,也提高了在丰富纹理环境中的实时性。实验结果表明:在弱纹理环境下,该算法比Vins-mono算法的平均定位精度提高了16.7%;在丰富纹理环境下,该算法比PL-vinsmono算法的平均耗时减少了41.7%。

基于区域路标引导的月面大范围高效行驶导航技术

载人月球探测任务中,受月面环境的复杂性和车载系统配置的限制,仅依靠车载导航系统难以全自主实现精确导航,需要遥操作中心对载人车大范围移动进行智能化支持。针对载人车在复杂月面环境中进行远距离探测时的高效导航问题,提出了基于区域路标引导的月面大范围高效行驶导航方法,通过分析载人车导航相机成像区域,将全路线可视区域中的月坑构建为月面路标图;并利用载人车导航相机图像中的月坑构建导航相机路标图,使用子图匹配的方法确定载人车可视区域内的月坑和环月卫星影像中月坑的对应关系,从而完成载人车位姿的解算。仿真试验结果表明:提出方法可以实现大范围移动过程中的高效导航。

我国体育高端智库建设的国际定位、现实困囿及推进策略

采用文献资料法、实地访谈法、对比分析法对我国体育高端智库的国际化定位、现实困囿与推进策略展开研究。研究表明,随着全球体育治理与体育事务国际化进程的加速推进,我国体育高端智库建设存在国际视野意识不强、国际战略研究程度不深、中国特色品牌尚未形成、成果国际传播不畅、国际议题设置实力较弱、智库人才的国际化培养不足等现实困囿。中国作为负责任大国应结合新时代体育全球化发展进程的现实需要,增强国际视野意识,深化国际战略研究程度,着力打造中国特色品牌,提高成果的国际传播能力,提升国际议题设置能力,加大体育智库国际化人才培养,为在国际上建设具有中国特色的体育高端智库提供理论和实践的战略支撑。

基于双目视觉距离误差测量的工业机器人运动学标定方法

针对机器人标定中存在的成本昂贵以及应用生产中末端精度低问题,提出了一种基于双目视觉距离误差测量的工业机器人运动学标定方法。首先,进行双目相机标定和畸变矫正,通过双目视觉测量模型计算匹配特征点的距离并提出三维空间坐标的双目视差空间位置匹配策略。其次,以机器人运动学模型为基础,引入微分算子建立机器人微分运动模型,建立机器人运动学误差模型,得出机器人各个关节的运动学参数与机器人末端位置误差之间的关系。最后,以IRB1200机器人为研究对象,对比分析应用高精度激光跟踪仪与双目视觉测量方法得到的距离误差和位置误差,两者误差均在10^(-1)mm级别,满足距离误差和位置误差测量要求,且经多种优化算法对机器人进行运动学标定后,其距离误差比优化前平均降低了61.5%。基于双目视觉距离误差测量工业机器人运动学标定方法可有效提高机器人末端精度,降低标定成本。