Vision Navigation Based PID Control for Line Tracking Robot

In a controlled indoor environment,line tracking has become the most practical and reliable navigation strategy for autonomous mobile robots.A line tracking robot is a self-mobile machine that can recognize and track a painted line on thefloor.In general,the path is set and can be visible,such as a black line on a white surface with high contrasting colors.The robot’s path is marked by a distinct line or track,which the robot follows to move.Several scientific contributions from the disciplines of vision and control have been made to mobile robot vision-based navigation.Localization,automated map generation,autonomous navigation and path tracking is all becoming more frequent in vision applications.A visual navigation line tracking robot should detect the line with a camera using an image processing technique.The paper focuses on combining computer vision techniques with a proportional-integral-derivative(PID)control-ler for automatic steering and speed control.A prototype line tracking robot is used to evaluate the proposed control strategy.

Dead-reckoning/vision integrated navigation for mobile robot

A dead reckoning system and a vision navigation system are proposed for use in a new integrated system for robot navigation. Since the dead reckoning system uses a recurrence algorithm to determine the position, the position will be divergent in two horizontal directions with time increasing. In order to overcome this defect, a vision navigation system is used to periodically correct the dead reckoning system, and a kalman filter is used to estimate the errors of navigation and the unknown biases of sensors, and precise position and heading estimations are obtained by updating navigation errors and sensors’ biases. It is concluded from the simulation results that all the navigation parameters can be obtained through kalman filtering, and the integrated navigation system proposed for robot navigation can be used in an actual robot working in a laboratory. The measurement noise analysis shows that with the distance between beacon and robot increasing, the measurement noise will increase, and in order to achieve a proper estimation accuracy, the distance should not be too great.

A Hybrid Vision Method for Autonomous Guided Vehicle Navigation

For the autonomous guided vehicle (AGV) used mainly in unfixed work fields, a machine vision method was proposed for the navigation system, in which a series of navigation-signs are placed along the travel route. The navigation system detects and recognizes these signs, and accordingly informs the travel control system. In order for the navigation to have balanced ability of 1) covering a large area and 2) recognizing details of the sign, the proposed vision method was designed to be a hybrid one, using both the stereo vision and the traditional 2D template matching. The former implemented a coarse recognition function for above 1), and the later implemented a fine recognition function for above 2). The results from the coarse recognition were used in the fine recognition for the gaze control to input suitable 2D image of the signs. Experiments on a prototype system show the feasibility of the proposed hybrid method in achieving the objective specifications for a typical AGV.

Accuracy study of a binocular-stereo-vision-based navigation robot for minimally invasive interventional procedures

BACKGROUND Medical robot is a promising surgical tool,but no specific one has been designed for interventional treatment of chronic pain.We developed a computed tomography-image based navigation robot using a new registration method with binocular vision.This kind of robot is appropriate for minimal invasive interventional procedures and easy to operate.The feasibility,accuracy and stability of this new robot need to be tested.AIM To assess quantitatively the feasibility,accuracy and stability of the binocularstereo-vision-based navigation robot for minimally invasive interventional procedures.METHODS A box model was designed for assessing the accuracy for targets at different distances.Nine(three sets)lead spheres were embedded in the model as puncture goals.The entry-to-target distances were set 50 mm(short-distance),100 mm(medium-distance)and 150 mm(long-distance).Puncture procedure was repeated three times for each goal.The Euclidian error of each puncture was calculated and statistically analyzed.Three head phantoms were used to explore the clinical feasibility and stability.Three independent operators conducted foramen ovale placement on head phantoms(both sides)by freehand or under the guidance of robot(18 punctures with each method).The operation time,adjustment time and one-time success rate were recorded,and the two guidancemethods were compared.RESULTS On the box model,the mean puncture errors of navigation robot were 1.7±0.9 mm for the short-distance target,2.4±1.0 mm for the moderate target and 4.4±1.4 mm for the long-distance target.On the head phantom,no obvious differences in operation time and adjustment time were found among the three performers(P>0.05).The median adjustment time was significantly less under the guidance of the robot than under free hand.The one-time success rate was significantly higher with the robot(P<0.05).There was no obvious difference in operation time between the two methods(P>0.05).CONCLUSION In the laboratory environment,accuracy of binocular-stereo-vision-based navigation robot is acceptable for target at 100 mm depth or less.Compared with freehand,foramen ovale placement accuracy can be improved with robot guidance.

Mobile Robot Localization and Navigation System Based on Monocular Vision

A system for mobile robot localization and navigation was presented.With the proposed system,the robot can be located and navigated by a single landmark in a single image.And the navigation mode may be following-track,teaching and playback,or programming.The basic idea is that the system computes the differences between the expected and the recognized position at each time and then controls the robot in a direction to reduce those differences.To minimize the robot sensor equipment,only one omnidirectional camera was used.Experiments in disturbing environments show that the presented algorithm is robust and easy to implement,without camera rectification.The rootmean-square error(RMSE) of localization is 1.4,cm,and the navigation error in teaching and playback is within 10,cm.

Vision navigation algorithm for mine agent based on quaternion

Autonomous relative navigation is the key technology in mining or rescuing. On the basis of mine requirement and the theories of machine vision, an autonomous relative navigation algorithm for mine agent based on quaternion was proposed. In rotation transformation, this algorithm was represented by using quaternion. Because the Jacobi matrix of this method is lower than that of Hall algorithm, the calculation efficiency is improved by using this algorithm. The results of these experiments show that the computation burden of this algorithm based on quaternion is about half that of Hall algorithm. This algorithm based on quaternion is improved as a valid way to solve the problem of mine real-time navigation.

Second-order divided difference filter for vision-based relative navigation

A second-order divided difference filter (SDDF) is derived for integrating line of sight measurement from vision sensor with acceleration and angular rate measurements of the follower to estimate the precise relative position,velocity and attitude of two unmanned aerial vehicles (UAVs).The second-order divided difference filter which makes use of multidimensional interpolation formulations to approximate the nonlinear transformations could achieve more accurate estimation and faster convergence from inaccurate initial conditions than standard extended Kalman filter.The filter formulation is based on relative motion equations.The global attitude parameterization is given by quarternion,while a generalized three-dimensional attitude representation is used to define the local attitude error.Simulation results are shown to compare the performance of the second-order divided difference filter with a standard extended Kalman filter approach.

Method for the navigation line recognition of the ridge without crops via machine vision

Some agriculture machinery like the transplanter,needs to operate by following the crop-free ridges.In order to improve working efficiency and quality,some autonomous navigation systems were developed and applied to ridge-following machinery.At present,agricultural navigation systems are mainly the satellite navigation system and the machine vision system.The satellite navigation system is difficult to apply to the machinery that needs to work by following the ridge because it cannot distinguish the shape of the navigated ridge and guide the machinery working along the ridge.In this study,697 cloudy ridge images and 235 sunny ridge images were taken in the field,and these images were used as the dataset.Moreover,a machine vision navigation method based on the color of ridges was proposed.Firstly,the regions of interest(ROI)in the ridge image were extracted according to the reaction time and the forward speed of the machine.Then,a gray reconstruction method was used to enlarge the color difference between the ridge and the furrow.The optimal threshold for the gray image segmenting was calculated real-timely by using the threshold segmentation method.Then,based on the contour detection method,the ridge contour which was not surrounded by holes was extracted.Finally,the approximate quadrilateral method was proposed to recognize the ridge center line as the navigation line.The method proposed in this study was verified by four types of ridges with different colors and textures.The experimental results showed that the recognition success rates of the light ridge,the dark ridge,the film-covered ridge,and the sunny ridge were 100%,97.5%,100%,and 98.7%,respectively.The recognition success rate of the proposed method was at least 8%higher than that of the existing ridge-furrow recognition methods.The results indicate that this method can effectively realize navigation line recognition.This method can provide technical support for the autonomous navigation of agricultural machinery,such as transplanters,seeders,etc.,operating on the ridge without crops.

GPS/VISNAV integrated relative navigation and attitude determination system for ultra-close spacecraft formation flying

For the improvement of accuracy and better fault-tolerant performance, a global position system （GPS）/vision navigation （VISNAV） integrated relative navigation and attitude determination approach is presented for ultra-close spacecraft formation flying. Onboard GPS and VISNAV system are adopted and a federal Kalman filter architecture is used for the total navigation system design. Simulation results indicate that the integrated system can provide a total improvement of relative navigation and attitude estimation performance in accuracy and fault-tolerance.

Binocular Visual Navigation and Obstacle Avoidance of Mobile Robots Based on Speeded-Up Robust Features

This article presents a good robust and real-time system scheme of the mobile robot obstacle detection and navigation, which principle of work is based on the feature descriptor SURF. In this scheme, firstly, the image information of the mobile robot path was captured by the binocular camera; then the feature points were extracted and corresponding matched using SURF to the binocular images as the undetected obstacles; finally fixed the position of the objective by the parallax between the matching points combining with the binocular vision calibration model. Theoretical derivation and experimental results show that this scheme is more accurate for the detection and navigation of the interest points. It has fast matching speed and high accuracy and low error. So, it has certain practical effect and popularizing value for the mobile robot real-time obstacle avoidance and navigation.

Eye Tracking during High Speed Navigation at Sea--Field Trial in Search of Navigational Gaze Behaviour

Purpose: Professional high speed sea navigational procedures are based on turn points, courses, dangers and steering cues in the environment. Since navigational aids have become less expensive and due to the fact that electronic sea charts can be integrated with both radar and transponder information, it may be assumed that traditional navigation by using paper based charts and radar will play a less significant role in the future, especially among less experienced navigators. Possible navigational differences between experienced and non-experienced boat drivers is thus of interest with regards to their use of navigational aids. It may be assumed that less experienced navigators rely too much on the information given by the electronic sea chart, despite the fact that it is based on GPS information that can be questioned, especially in littoral waters close to land. Method: This eye tracking study investigates gaze behaviour from 16 ex perienced and novice boat drivers during high speed navigation at sea. Results: The results show that the novice drivers look at objects that are close to themselves, like instrumentation, while the experienced look more at objects far away from the boat. This is in accordance with previous research on car drivers. Further, novice boat drivers used the electronic navigational aids to a larger extent than the experienced, especially during high speed conditions. The experienced drivers focused much of their attention on objects outside the boat. Conclusions: The findings verify that novice boat drivers tend to rely on electronic navigational aids. Experienced drivers presumably use the navigational aids to verify what they have observed in the surrounding environment and further use the paper based sea chart to a larger extent than the novice drivers.

GNSS/SINS/视觉导航鲁棒算法

全球导航卫星系统(Global Navigation Satellite System, GNSS)、捷联惯性导航系统(Strapdown Inertial Navigation System, SINS)和视觉传感器优势互补,3者信息融合可获得高精度、无漂移的导航定位信息.针对GNSS/SINS/视觉融合导航易受运动速度、光照变化、遮挡等影响导致定位精度和鲁棒性降低问题,本文在图优化框架的代价函数中加入SoftLOne鲁棒核函数,设置量测值粗差检验程序,降低离群点带来的负面影响.进一步,对量测值计算残差进行卡方检验,对超限残差降权处理,提高系统精度和鲁棒性.实验结果表明,本文算法较不施加鲁棒核函数、不采用异常值剔除策略和卡方检验的传统算法,以及加入其他鲁棒核函数的算法精度更高、鲁棒性更好,能够较大程度提升GNSS/SINS/视觉导航定位精度和鲁棒性,在大尺度环境下,未出现较大漂移误差,绝对位姿均方根误差0.735 m,绝对位姿误差标准差0.336 m.

无人机立体视觉识别船舶航行风险仿真

由于船舶交通受碰撞、搁浅、走锚等随机干扰因素的影响,导致对船舶航行目标的跟踪与风险预警具有较大难度。为增强海上航行的安全性,提出一种基于无人机立体视觉的船舶航行风险识别方法。引入双目视觉立体技术,获得目标船舶在航行过程中的图像数据。利用卡尔曼预测器优化连续性自适应均值漂移算法,跟踪目标船舶,通过高斯混合模型识别船舶航行风险。实验结果表明,研究方法对不同海域的船舶跟踪曲线与船舶实际航行曲线具有较高拟合度,且上述方法的船舶航行风险识别正确率高于90%,且误报率低于0.2%,说明提出方法的应用可靠性较高。

惯导与视觉信息融合的掘进机精确定位方法

针对煤矿巷道复杂环境下掘进机精确定位难题,提出了一种惯导与视觉融合的掘进机精确定位方法,该方法采用惯导与“视觉+激光标靶”的定位方案。该方案将设计的四特征点大尺寸激光标靶固定于巷道顶板,相机固定于掘进机机身采集激光标靶图像,并运用圆拟合法定位光斑中心和基于四特征点的EPnP算法解算掘进机位置。为了验证“视觉+激光标靶”方法对掘进机位置检测效果,在模拟掘进工作面环境下开展了“视觉+激光标靶”位置检测试验,结果表明:在30 m内沿巷道宽度方向、掘进方向、高度方向最大误差不超过28.549 mm、78.868 mm、44.459 mm,实现了掘进机位置精确检测。针对惯导测量掘进机位姿误差随时间累积和掘进机振动对组合定位系统产生干扰导致位姿检测不准问题,提出改进Sage-Husa自适应滤波的惯导与视觉信息融合方法,该方法通过检测新息方差值修正量测误差来提高定位准确性。在模拟掘进工作面环境下开展了惯导与“视觉+激光标靶”组合定位实验,采用改进前后Sage-Husa自适应滤波算法融合惯导与视觉信息进行对比分析,结果表明:改进后Sage-Husa自适应滤波算法融合得到的定位误差更小,俯仰角、横滚角、航向角最大误差分别为0.029°、0.051°、0.0113°,在距离激光标靶30 m内巷道宽度位置误差在0.033 m范围内,巷道掘进方向位置误差在0.062 m范围内。所提出的惯导与视觉融合定位方法能够满足巷道掘进定位精度要求。

改进DeepLabV3+算法提取无作物田垄导航线

机器视觉导航是智慧农业的重要部分,无作物田垄的导航线检测是旱地移栽导航的关键。针对无作物田垄颜色信息相近、纹理差距小,传统图像处理方法适用性差、准确率低,语义分割算法检测速度慢、实时性差的问题,该研究提出一种基于改进DeepLabV3+的田垄分割模型。首先对传统DeepLabV3+网络进行轻量化设计,用MobileNetV2网络代替主干网络Xception,以提高算法的检测速度和实时性;接着引入CBAM(convolutional block attention module,CBAM)注意力机制,使模型能够更好地处理垄面边界信息;然后利用垄面边界信息获得导航特征点,对于断垄情况,导航特征点会出现偏差,因此利用四分位数对导航特征点异常值进行筛选,并采用最小二乘法进行导航线拟合。模型评估结果显示,改进后模型的平均像素精确度和平均交并比分别为96.27%和93.18%,平均检测帧率为84.21帧/s,优于PSPNet、U-Net、HRNet、Segformer以及DeepLabV3+网络。在不同田垄环境下,最大角度误差为1.2°,最大像素误差为9,能够有效从不同场景中获取导航线。研究结果可为农业机器人的无作物田垄导航提供参考。

面向低光弱纹理环境的SLAM系统实验教学平台设计

为提升机器人专业实验教学质量和人才培养质量,针对机器人状态估计和精确定位工程问题提出一种面向低光弱纹理环境的视觉惯性融合鲁棒SLAM算法,并设计一种面向低光弱纹理环境的SLAM系统实验软件教学平台,实现稳健鲁棒4DOF状态估计和高精度实时定位,并在公开数据集上验证了该算法的有效性。实验结果表明,与现有的视觉惯性SLAM算法相比,所提算法在结构化弱纹理场景中有着更高的精度和鲁棒性,能有效降低机器人系统的累积误差,保证地图构建的一致性。通过上述SLAM系统教学平台在实验教学中的应用,可提升机器人专业本科生在工程问题中的创新能力和实践能力。

农业信息采集机器人关键技术研究现状与发展趋势

智慧农业是农业现代化的标志,农业信息采集是智慧农业的重要环节之一,相较于人工信息采集具有的低效、准确度不高等不足,利用农业信息采集机器人代替人工进行农情信息采集,可降低农作强度、提升生产效率。本文针对不同场景下的农业信息采集机器人,概括了近几十年国内外农业信息采集机器人的应用现状,总结了自主导航技术、机器视觉技术、智能控制技术、智能云处理技术四大关键技术的研究现状,并结合农业生产中环境非结构化、作业对象具有娇嫩性等特点,指出了目前关键技术存在的问题,并提出复合导航技术、多机智能感知、视觉监测算法优化、通用化智能控制、智能云管控平台是未来的发展趋势。

基于计算机视觉的管道机器人导航与目标识别

随着社会的不断发展,计算机、人工智能等先进技术愈加成熟。在人工智能技术的支撑下,管道机器人的性能不断完善,其中基于计算机视觉的管道机器人不仅能够根据运行需求对运动路线进行导航,还能够对目标信息进行有效识别。管道机器人企业只有不断加强对计算机视觉、导航及目标识别等技术的研发,才能使管道机器人在各行各业中发挥重要的作用。文章将围绕机器人视觉概述、基于计算机视觉的管道机器人导航与目标识别等方面进行具体的研究及分析。

基于Sigma-point卡尔曼滤波的INS/Vision相对导航方法研究

针对无人机编队常用的leader-follower(领航-跟随)飞行模式,提出了一种考虑视觉导航设备输出时间延迟问题的INS/Vision相对导航方法,给出了leader与follower之间的相对惯导方程以及相对视线矢量测量原理。由于INS/Vision相对导航系统是一个强非线性系统,采用Unscented卡尔曼滤波融合相对惯导信息和相对视线矢量信息,从而估计出leader与follower之间的相对位置、相对速度和相对姿态,受姿态四元数的归一化限制,在滤波中采用罗德里格斯参数作为姿态误差状态,对于视觉导航系统量测量存在时间延迟的问题,给出了延迟后的量测量与当前惯导信息融合的方法,最后通过仿真研究证明了方法的有效性。

INS/Vision相对导航系统在无人机上的应用

提出了一种考虑视觉导航设备输出时间延迟问题的INS/Vision相对导航方法,推导了长机与僚机之间的相对惯导方程.给出了长机与僚机之间相对视线矢量测量原理,僚机上设置若干特征光点,长机上的视觉导航设备通过对特征光点观测,得到相对视线矢量.应用扩展卡尔曼滤波融合相对惯导信息和相对视线矢量信息,估计出长机与僚机之间的相对姿态、相对速度和相对位置.针对视觉导航设备量测量存在时间延迟的问题,给出了延迟后量测量与惯导信息融合的方法,最后通过仿真研究证明了该相对导航方法的有效性.