无人直升机自主着舰的目标定位视觉算法

根据无人直升机自主着舰的任务特点,构造了用于无人直升机自主着舰的视觉系统,选用仿射不变矩作为该视觉系统目标识别的特征和信息提取的手段,仿真实验表明,开发的算法能够在纵摇角小于15°的情况下正确的识别出目标,对目标中心位置的估计偏差在每个坐标轴向小于3个像素,方位角估计偏差小于9°。整套算法的鲁棒性和实时性满足无人直升机自主着舰的需求。     

基于双目视觉的人手定位与手势识别系统研究

提出了一种新的人手特征点提取方法,该方法将人手的质心作为匹配点,根据双目视觉定位数学模型计算目标位置信息,同时通过图像分割获取人手轮廓,利用轮廓凸包点特征来识别不同手势.在此基础上,研究设计了一种光学人手定位与手势识别系统,该系统在实时定位空间人手三维位置的同时,能够识别出相应的手势,可将其作为虚拟手的驱动接口,实现对虚拟物体的抓取、移动和释放操作.     

基于双目视觉的小型无人直升机位姿检测

无人直升机的位置与姿态检测是直升机自主飞行控制的基础。基于双目视觉原理,对直升机标志点进行检测并跟踪,利用基于顺序一致性的极线约束匹配方法,对检测到的多个标志点进行立体匹配,计算标志点三维坐标从而得到无人直升机的位置与姿态信息。设计一个基于双目视觉的小型无人直升机空间位姿测量托架,用于飞行控制模型及飞行控制算法的研究及验证。     

自主飞行机器人导航系统设计

自主飞行机器人系统是以微型直升机模型为载体的复杂系统。在该系统中导航系统采集各传感器数据得到机器人当前飞行姿态、空间位置以及相应的监控信息,控制模块依此监控信息按照给定策略计算并发出控制信号,实现飞行机器人的自主控制。本文对自主飞行机器人导航系统设计及功能实现做出了详细阐述。首先,给出了本自主飞行机器人的系统构造;其次,给出了导航系统的硬件组成部分以及各部分所完成的功能任务;最后阐述了导航系统的功能实现,包括飞行姿态和空间位置的获取。     

入侵目标视觉检测与识别的研究进展

入侵目标视觉检测与识别是无人机感知与规避技术领域中重点研究的课题,关键任务是无人机在飞行过程中通过机载传感器获取光学机载图像中并判断是否存在入侵目标,并对入侵目标进行检测识别和定位。入侵目标视觉检测与识别是将无人机安全集成到国家空域并保证无人机和有人机飞行安全的关键技术之一。本文主要围绕无人机感知与规避技术中的入侵目标视觉检测与识别技术方面,分析检测与识别入侵目标所面临的一些难点问题,综述当前入侵目标视觉检测与识别的主要处理方法,并指出了该领域存在的尚未解决的问题和展望未来的发展趋势。     

旋翼飞行机器人视觉定位方法及系统

为实现旋翼飞行机器人在室内环境中的精确定位及控制,设计了基于单目视觉的机载视觉定位方法.该方法通过矩特征提取、图形分类来识别地面标记图形,进而利用EPn P方法解算摄像机坐标.为验证机载视觉定位方法的有效性,利用Kinect传感器搭建了旋翼飞行器外部定位系统,设计了针对旋翼飞行器目标的视觉跟踪算法,定位精度达2 mm.实验结果表明,机载视觉定位方法能够很好地进行飞行器定位.     

基于Dubins曲线的无人直升机轨迹规划

为提高无人直升机的控制性能,提出了一种基于Dubins曲线的轨迹规划算法,并对其各个部分的实现进行了研究和设计。该算法利用Dubins曲线原理对定点飞行任务的两点或者多点目标进行分析计算,寻找出一条最短的飞行路径,从而提高了飞行效率。根据无人直升机系统多变量、非线性和强耦合的特点,采用串级PID方法设计了飞行控制器,该控制器能够修正无人直升机的姿态和位置,从而提高了轨迹规划的稳定性和准确性。最后,以某小型无人直升机为实验平台表明了该轨迹规划算法和控制器的可行性。     

基于SURF特征点的自主空中加油定位研究

针对硬式空中加油技术中加油插座的定位问题,提出了一种结合SURF(Speeded-up Robust Features)特征点的双目立体视觉定位方法,确定了加油插座的空间位置,实现伸缩管和加油插座的精确对准。基于SURF匹配算法,对双目视觉系统采集的左右图像进行目标检测,并获取匹配目标的SURF特征点,通过空间误匹配点对的剔除和目标点坐标的计算,确定左右图像中具有空间位置一致性的目标点(即加油插座),从而恢复目标点的三维信息。实验结果表明,结合SURF方法能够有效地对加油插座的空间位置进行定位,具有一定的实用价值。     

旋翼空中机器人系统架构及设计

设计并验证了某型旋翼空中机器人的系统架构。整个空中机器人系统由直升机和地面站两部分组成。直升机是空中机器人的主体,可以自主飞行并完成指定任务。地面站用于监控无人直升机的飞行,并实现人机交互等多项功能。此外,地面站还可通过视觉导航系统引导直升机的自主着陆。直升机与地面站之间通过指令数字链路和视频模拟链路进行信息交互和实时通讯。经实际飞行验证,该空中机器人系统具有鲁棒和实时的特点,能实现直升机自主飞行和自主起降功能。     

一种视觉引导的作业型飞行机器人设计

针对作业型飞行机器人执行抓取、投放等作业任务时飞行机器人与被抓取目标之间难以相对定位的问题,提出了一种视觉引导的作业型飞行机器人设计方法.首先,介绍作业型飞行机器人系统的整体机构设计,建立飞行器和空中作业装置的运动学和动力学模型.然后,根据针孔成像模型,在ArUco标记尺寸已知的前提下,通过机载的单目摄像头检测被抓目标上的ArUco标记,利用n点透视(PnP)算法解算摄像头位姿,进而利用摄像头位姿信息对飞行器和作业装置进行分级控制.最后,通过静止实验和户外悬停实验验证了位姿估计算法的有效性,并通过自主抓取直径2 cm、质量100 g的管状物体进一步验证视觉引导的有效性和合理性.     

Hovering control of model helicopter by vision

In this paper, we introduce an autonomous flying model helicopter with a vision control system. A feature of the helicopter is that autonomous hovering is realized by a vision control system. Owing to this vision control system, the model helicopter is able to take off, land, and hover without any human assistance. The vision control sstem is composed of a CCD camera mounted on the helicopter and an image processor on the ground. We first introduce the configuration of the helicopter system, which has a vision sensor, a clinometer, and an azimuth sensor. To determine the 3-D position and posture of helicopter, a technique of image recognition using a monocular image is used. Finally, we give an experiment result which we obtained in a hovering test with the vision control system. This result shows the effectiveness of the vision control system in the model helicopter.     

基于ARM小型直升机飞控系统设计与实现

介绍基于ARM7某型直升机自主飞行控制系统的设计及实现;先简要说明飞控系统的ARM硬件实现和软件架构,然后在该INS基础上,设计并实现扩展卡尔曼滤波器,融合INS数据以准确获得飞机姿态角;进一步设计实现基于位置和速度跟踪的飞行控制器,通过对飞机位置和速度的规划,实现飞机的多任务、长距离飞行任务;地面测试和试飞表明该飞控系统达到设计的要求,性能稳定。     

基于深度学习的多旋翼无人机单目视觉目标定位追踪方法

针对无人机对目标的识别定位与跟踪,本文提出了一种基于深度学习的多旋翼无人机单目视觉目标识别跟踪方法,解决了传统的基于双目摄像机成本过高以及在复杂环境下识别准确率较低的问题。该方法基于深度学习卷积神经网络的目标检测算法,使用该算法对目标进行模型训练,将训练好的模型加载到搭载ROS的机载电脑。机载电脑外接单目摄像机,单目摄像头检测目标后,自动检测出目标在图像中的位置,通过采用一种基于坐标求差的优化算法进行目标位置准确获取,然后将目标位置信息转化为控制无人机飞行的期望速度和高度发送给飞控板,飞控板接收到机载电脑发送的跟踪指令,实现对目标物体的跟踪。试验结果验证了该方法可以很好的进行目标识别并实现目标追踪     

一种基于靶标识别定位算法的视觉测量技术

视觉测量在飞行试验高精度测试中发挥着重要作用。针对常规视觉测量中多标志点识别定位存在误识别、定位精度低等问题,设计了一种新的环形编码对角标志,并提出了一种基于环形编码对角标志识别定位算法的视觉测量技术。重点介绍了基于EDCircles圆检测算法的标志点识别、基于Harries角点检测算法的亚像素级定位和基于坐标变换的编码信息解码等技术的实现。经过实验验证,研究成果编码标志点识别定位算法识别准确、鲁棒性强、定位精度高,在大投影角度下仍能达到92%的识别率,可以满足飞行试验动态视觉测量任务相关需求。     

Ellipse proposal and convolutional neural network discriminant for autonomous landing marker detection

Autonomous landing in complex environments is a critical problem for unmanned aerial vehicle autonomous control, and efficiently detecting landing identification mark in real‐world scenario is still challenging. Due to the limited computational power of airborne computing equipment, current target detection algorithms cannot meet the demand efficiently. In this paper, we proposed a new landing marker detection algorithm for autonomous landing systems in a real environment. We used an ellipse detection algorithm to detect the ellipse landmark or other elliptical objects. Furthermore, convolution neural networks were utilized to obtain the correct landmarks, which is robust, fast and can achieve a speed of 25 fps with 720p resolution video on an Intel NUC onboard computer. Unlike the other methods, the accuracy and speed of our algorithm is verified in a real‐time application with more harsh conditions. During system testing, the flight system can detect the object above 20 m, track it, and automatically land on it with this vision algorithm. The algorithm has helped us achieve the first position at Mohamed Bin Zayed International Robotics Challenge in Abu Dhabi this year.     

Development of a vision-based ground target detection and tracking system for a small unmanned helicopter

It is undoubted that the latest trend in the unmanned aerial vehicles (UAVs) community is towards visionbased unmanned small-scale helicopter, utilizing the maneuvering capabilities of the helicopter and the rich information of visual sensors, in order to arrive at a versatile platform for a variety of applications such as navigation, surveillance, tracking, etc. In this paper, we present the development of a visionbased ground target detection and tracking system for a small UAV helicopter. More specifically, we propose a real-time vision algorithm, based on moment invariants and two-stage pattern recognition, to achieve automatic ground target detection. In the proposed algorithm, the key geometry features of the target are extracted to detect and identify the target. Simultaneously, a Kalman filter is used to estimate and predict the position of the target, referred to as dynamic features, based on its motion model. These dynamic features are then combined with geometry features to identify the target in the second-stage of pattern recognition, when geometry features of the target change significantly due to noise and disturbance in the environment. Once the target is identified, an automatic control scheme is utilized to control the pan/tilt visual mechanism mounted on the helicopter such that the identified target is to be tracked at the center of the captured images. Experimental results based on images captured by the small-scale unmanned helicopter, SheLion, in actual flight tests demonstrate the effectiveness and robustness of the overall system.     

Adaptive control system for autonomous helicopter slung load operations

This paper presents design and verification of an estimation and control system for a helicopter slung load system. The estimator provides position and velocity estimates of the slung load and is designed to augment existing navigation in autonomous helicopters. Sensor input is provided by a vision system on the helicopter that measures the position of the slung load. The controller is a combined feedforward and feedback scheme for simultaneous avoidance of swing excitation and active swing damping. Simulations and laboratory flight tests show the effectiveness of the combined control system, yielding significant load swing reduction compared to the baseline controller.