昆虫视觉启发的光流复合导航方法

昆虫能够使用视觉感受的光流(Optical flow, OF)信息执行导航任务. 启发于昆虫的视觉导航, 本文提出了一种生物视觉启发的光流复合导航方法, 它由光流导航和光流辅助导航两部分组成, 以实现高效精确的视觉导航定位. 该方法中, 光流导航的作用是使用昆虫视觉启发的光流法, 测量系统每一时刻的运动位移, 然后使用路径积分累加位移得到位置信息; 光流辅助导航的作用是针对路径积分会产生累积误差的缺点, 使用光流匹配的方法来估计和修正导航中的位置误差. 该光流辅助导航也参考了昆虫启发的光流法, 通过基于光流的卡尔曼滤波器来执行实际和预测光流的迭代匹配. 由于光流导航和光流辅助导航中的光流计算来源于同一昆虫启发光流法, 使得光流复合导航的两部分可共享输入信号和部分执行过程. 文中使用移动机器人进行导航实验,证明了该复合导航方法的效率.     

Integrated position estimation using aerial image sequences

Presents an integrated system for navigation parameter estimation using sequential aerial images, where the navigation parameters represent the positional and velocity information of an aircraft for autonomous navigation. The proposed integrated system is composed of two parts: relative position estimation and absolute position estimation. Relative position estimation recursively computes the current position of an aircraft by accumulating relative displacement estimates extracted from two successive aerial images. Simple accumulation of parameter values reduces the reliability of the extracted parameter estimates as an aircraft goes on navigating, resulting in a large positional error. Therefore, absolute position estimation is required to compensate for the positional error generated by the relative position estimation. Absolute position estimation algorithms using image matching and digital elevation model (DEM) matching are presented. In the image matching, a robust-oriented Hausdorff measure (ROHM) is employed, whereas in the DEM matching, an algorithm using multiple image pairs is used. Experiments with four real aerial image sequences show the effectiveness of the proposed integrated position estimation algorithm     

基于累积绝对差图像与交叉熵分割的运动目标检测与定位

提出了一种新的运动目标检测与定位方法。针对位移变化较小的运动目标，先对运动序列中所有相邻两帧图像作绝对值差分运算，然后再将绝对值差分结果进行累加，从而得到累积绝对差图像。利用交叉熵分割法对累积绝对差图像二值化，并结合形态学方法去除噪声，求取出目标的运动区域。对运动序列的首帧和尾帧进行差分运算并二值化．为了去噪，将首尾帧差图像与累积绝对差图像进行逻辑与运算，确定出目标在首尾图像中的位置。实验结果表明了本方法的有效性和鲁棒性。     

视觉方向导航新方法

针对运行方向上导航目标本身不具有明显视觉特征的情况,提出了一种新的视觉导航方法。该方法利用环境中与目标位置关系已知的显著特征点作为参考点,根据参考点的成像位置确定系统运动的姿态调整量,实现机器人运行方向的导航。为了提高算法对环境的适应能力,该算法只利用一个参考点,具有结构简单和计算复杂度小等特点。实验结果表明,该文方法能够有效地消除导航过程的方向误差,能够配合位置导航装置实现机器人的方向导航,具有较高的实用性和稳定性。     

一种快速精确的KVM远程鼠标同步方法

针对键盘显示器鼠标(KVM)中远程被控鼠标与主机鼠标的同步要求,提出一种基于高速USB2.0-HID类规范的鼠标同步方法.在传统相对鼠标同步方法中加入自适应“残差处理”,去除相对偏移的累积误差,增加一种绝对鼠标同步方法,用双字节绝对坐标值代替传统单字节相对坐标偏移进行定位.实验结果表明,该方法使同步延迟时间降至3 ms...     

一种面向移动平台的无人机自主降落控制方法

准确获取无人机的位姿信息是顺利执行无人机自主导航、着陆的首要前提。由于GPS/INS导航系统的局限性和IMU惯性导航系统的误差,提出了一种基于视觉导航的方法。设计了"H"形图像的着陆标志,对机载摄像机采集的实时影像进行图像处理,利用世界坐标系到图像像素坐标系的映射关系得到基于视觉的无人机位姿估计模型,进而解算无人机当前的位姿估计值。上述方法提高了无人机的着陆安全性。仿真结果验证了算法的有效性和位态信息的精确度。     

Rover navigation using stereo ego-motion

Robust navigation for mobile robots over long distances requires an accurate method for tracking the robot position in the environment. Promising techniques for position estimation by determining the camera ego-motion from monocular or stereo sequences have been previously described. However, long-distance navigation requires both a high level of robustness and a low rate of error growth. In this paper, we describe a methodology for long-distance rover navigation that meets these goals using robust estimation of ego-motion. The basic method is a maximum-likelihood ego-motion algorithm that models the error in stereo matching as a normal distribution elongated along the (parallel) camera viewing axes. Several mechanisms are described for improving navigation robustness in the context of this methodology. In addition, we show that a system based on only camera ego-motion estimates will accumulate errors with super-linear growth in the distance traveled, owing to increasing orientation errors. When an absolute orientation sensor is incorporated, the error growth can be reduced to a linear function of the distance traveled. We have tested these techniques using both extensive simulation and hundreds of real rover images and have achieved a low, linear rate of error growth. This method has been implemented to run on-board a prototype Mars rover.     

单目视觉人工路标辅助INS的组合导航定位方法

提出一种单目视觉人工路标辅助惯性导航系统(Inertial Navigation System,INS)的定位方法。首先设计人工路标,并用相机拍摄各预先设置的人工路标,记录拍摄每个路标时相机位置和姿态,建立视觉路标库。在利用惯性导航系统定位过程中,对单目相机采集到的图像进行路标提取、与路标库中相应路标进行匹配,估计当前相机位置和姿态,然后利用卡尔曼滤波将视觉匹配估计的位置信息和INS有效地融合。实验结果表明:传统航位推算方法的平均误差为0.715 m,本文组合导航方法的平均误差为0.154 m,该方法有效地提高了惯性导航定位的精度。     

Cleaning robot navigation using panoramic views and particle clouds as landmarks

The paper describes a visual method for the navigation of autonomous floor-cleaning robots. The method constructs a topological map with metrical information where place nodes are characterized by panoramic images and by particle clouds representing position estimates. Current image and position estimate of the robot are interrelated to landmark images and position estimates stored in the map nodes through a holistic visual homing method which provides bearing and orientation estimates. Based on these estimates, a position estimate of the robot is updated by a particle filter. The robot’s position estimates are used to guide the robot along parallel, meandering lanes and are also assigned to newly created map nodes which later serve as landmarks. Computer simulations and robot experiments confirm that the robot position estimate obtained by this method is sufficiently accurate to keep the robot on parallel lanes, even in the presence of large random and systematic odometry errors. This ensures an efficient cleaning behavior with almost complete coverage of a rectangular area and only small repeated coverage. Furthermore, the topological-metrical map can be used to completely cover rooms or apartments by multiple meander parts.     

基于粒子滤波的无人机自主轨迹视觉导航控制方法研究

针对现有无人机导航控制方法存在的控制效果不佳的问题,本文提出一种基于粒子滤波的无人机自主轨迹视觉导航控制方法研究。利用粒子滤波算法,实现对无人机自主轨迹视觉导航控制方法的优化设计。采用栅格法构建无人机飞行环境地图,根据无人机的机械组成结构和工作原理,构建运动状态模型。利用内置的摄像机设备采集视觉图像,执行图像灰度转换、几何校正、滤波等预处理步骤。通过对视觉图像的特征提取,判断当前环境是否存在障碍物。利用粒子滤波算法确定无人机位姿,结合障碍物识别结果规划无人机的自主飞行轨迹。将位置、速度和姿态角的控制量计算结果,输入到安装的导航控制器中,完成无人机的自主轨迹视觉导航控制任务。通过实测分析得出结论：应用设计的导航控制方法,其位置误差、速度误差以及姿态角误差均维持在预设值以下,即设计的导航控制方法具有良好的控制效果。     

Vision‐aided Guidance and Navigation for Close Formation Flight

Close formation flight can extend an unmanned aerial vehicle's (UAV) range and endurance by utilizing lift from a wingman's wake vortices and by autonomous midair refueling or recharging. The prohibitive challenge in each of these applications is the highly accurate and reliable relative positioning that is required to station‐keep in the wingman's wake and to dock, amid external disturbances. Global navigation satellite systems are well‐suited to reliable absolute positioning, but they fall short for accurate relative positioning. This work proposes a relative positioning solution for UAV rendezvous and close formation flight that has been verified in multiple flight tests. A nonlinear estimation framework uses precise air‐to‐air measurements to correct onboard sensor measurements and produce an accurate relative state estimate that is resilient to intermittent relative measurement outages and degrades gracefully during extended outages. A guidance strategy compensates for wingman turn dynamics, acts explicitly on the estimated relative state, and is applicable to both rendezvous and formation flight. Ground testing showed a relative position estimate accuracy that is 2% of the separation distance, with successful detection and correspondence at up to 36 m. Autonomous close formation flight tests verified the relative positioning solution over extended periods, as close as two wingspans, in winds that were 30%–40% of the cruise airspeed, and at altitudes as low as 15 m. Root‐mean‐square relative position errors were 1.2 m horizontally and 0.44 m vertically during flights at the closest separation.     

A new autonomous celestial navigation method for the lunar rover

A secure and autonomous navigation system is needed for the lunar rover in future lunar missions in case of emergencies. Celestial navigation is a very attractive solution for long distance navigation on the Moon without the need of ground navigation aids. It only uses star altitudes, which are measured by a high accuracy star sensor and inertial measurement unit (IMU) to estimate the position of the rover. The navigational accuracy of this method depends largely on the accuracy of measurements, so the measurement errors have a great impact on the navigational performance. A new autonomous celestial navigation method for the lunar rover is presented in this paper, which uses the augmented state unscented particle filter (ASUPF) to deal with the systematic error and random error in the measurements. The validity and feasibility of this new method is tested and examined by the hardware-in-loop test. A position estimation error within 60 m is obtained. Compared to the conventional method, this method shows better navigation performance and higher adaptability to these measurement errors.     

基于陆标图像的火星绕飞自主导航方法

针对火星绕飞自主导航的高精度要求,利用火星表面的陆标作为新的测量信息源,通过对陆标特征提取识别获取测量信息.在仅观测火星地表陆标图像信息的基础上,建立了相应的自主导航方案并利用可观测性矩阵分析了该方案的可观测性.考虑到在图像拍摄和视线提取过程中可能会产生的不确定性测量误差,采用基于极大相关熵的无迹卡尔曼滤波算法抑制不确定性误差影响,并实现对火星探测器的位置、速度的状态估计.数学仿真结果表明该自主导航方法具有可靠性,极大相关熵无迹卡尔曼滤波算法通过结合无迹变换和极大相关熵鲁棒权重函数可以有效抑制测量模型中不确定误差影响,能够达到较高的火星绕飞定轨精度.     

基于不确定性知识的实时道路场景理解

由于室外机器人的工作环境非常复杂，因此机器人的视觉导航必须具有足够的智能和鲁棒性，为此，提出了一种基于不确定性知识的实时道路理解算法，该算法通过不确定性知识推理来融合多种信息和知识，以满足在复杂道路环境下的鲁棒性要求，它即使在有强烈阴影、水迹等干扰下也能给出比较好的结果；通过图象边缘信息的提取可以得到精确的道路边界，以满足视觉导航的精确性要求；同时在算法设计时，兼顾了实时性要求；使得算法得以实时实现，该算法已在实际的机器人上进行了测试，并得到了很好的结果。     

室外移动机器人TYIRV-I的定位系统的设计与实现

定位系统是保证准确避障和导航的必要条件,只有准确稳定的定位才能够准确避障和导航,所以定位系统在室外移动机器人中是不可缺少的组成部分。本文介绍室外移动机器人TYIRV-I的组合定位系统,即GPS、磁罗盘和光码盘组合定位,其中,GPS虽然能够提供较精确的位置信息,但是会由于遮挡等原因导致数据无效。磁罗盘和光码盘通过航位推算得到位置信息,短距离定位效果较好,但存在严重的累计误差。对以上两种定位方法进行信息融合形成GPS、磁罗盘和光码盘组合定位,取长补短,取得较好的效果。实践证明,该定位系统具有较高的准确性和稳定性,能够满足移动机器人的定位和导航需要。     

基于单领航者相对位置测量的多AUV协同导航系统定位性能分析

自主水下航行器 (Autonomous underwater vehicle, AUV) 的协同导航是解决水下导航定位问题的重要方法, 其中导航系统的定位误差增长特性是衡量其定位性能的关键指标. 本文针对单领航者相对位置测量的多 AUV 协同导航系统, 利用扩展卡尔曼滤波方法建立了导航系统的整体定位误差关于相对位置量测误差的传递方程. 在此基础上, 通过求解系统定位误差随时间演化的代数黎卡提方程, 得到了其在稳态情形下的方差上界估计. 理论分析表明, 单领航 AUV 协同导航系统的整体定位误差有界收敛且与初始化滤波方差无关, 具有良好的综合性能. 最后, 仿真实例验证了文中理论分析结果的正确性.     

单目视觉人工路标辅助的移动机器人导航方法

室内机器人在采用里程计法长距离导航时,定位精度下降很快,以及以往人工路标定位方案的识别准确率低,又难以满足导航实时性的要求. 针对这些问题,本文设计了能快速准确识别的人工路标,从而来修正机器人里程计法导航的累计误差,并通过卡尔曼滤波将人工路标和里程计法的定位信息有效地融合起来. 实验结果表明,数字人工路标的识别准确率高,且识别速度满足导航实时性的要求,该方法有效地提高了移动机器人里程计法导航时的精度和鲁棒性.     

基于综合几何关系稀疏自注意力机制的图像标注方法研究

针对基于Transformer框架的图像标注任务中提取视觉特征容易引入噪声问题且为了进一步提高视觉的上下文信息,提出了一种基于综合几何关系稀疏自注意力机制的图像标注方法。首先通过结合图像区域的绝对位置、相对位置和空间包含关系提取详细全面的视觉表示,获取图像中潜在的上下文信息;其次提出了注意力层权重矩阵的稀疏化方法,该方法解决了Transformer忽略图像区域的局部性并引入噪声信息的问题;最后,采用了强化学习方法作为指导策略,实现模型在句子级别优化目标序列。通过在MS-COCO数据集上进行的对比实验结果表明,提出的方法在BLEU1、BLEU4、METEOR、ROUGE-L、CIDEr和SPICE指标上分别比基线模型提升了0.2、0.7、0.1、0.3、1.2和0.4,有效提升了图像自动标注的性能。     

基于姿态测量模块和闭环检测算法的仿生SLAM研究

基于传感器模型的SLAM导航策略精度较高,但由于摩擦等因素误差长时间累计会造成里程计的漂移现象.依靠视觉里程计进行导航的RatSLAM系统,通过在局部场景细胞中引入闭环检测策略实现累计误差的校正,在静态环境下具有一定的鲁棒性,但在复杂场景里,如移动障碍物的出现,视觉里程计会提取到错误的速度等姿态信息,导致航迹出现较大偏移,有时无法通过场景重定位进行闭环校正.结合两种模型的优势提出一种带姿态测量模块和闭环检测算法的仿生SLAM模型.实验表明,相较于仅带带闭环检测的RatSLAM系统或仅由姿态测量模块构成的导航系统,本文提出的新系统更能适应长期复杂场景下的导航,且鲁棒性更强.     

Image-based memory for robot navigation using properties of omnidirectional images

This paper proposes a new technique for vision-based robot navigation. The basic framework is to localise the robot by comparing images taken at its current location with reference images stored in its memory. In this work, the only sensor mounted on the robot is an omnidirectional camera. The Fourier components of the omnidirectional image provide a signature for the views acquired by the robot and can be used to simplify the solution to the robot navigation problem. The proposed system can calculate the robot position with variable accuracy (‘hierarchical localisation’) saving computational time when the robot does not need a precise localisation (e.g. when it is travelling through a clear space). In addition, the system is able to self-organise its visual memory of the environment. The self-organisation of visual memory is essential to realise a fully autonomous robot that is able to navigate in an unexplored environment. Experimental evidence of the robustness of this system is given in unmodified office environments.