基于多传感器信息融合的移动机器人快速精确自定位

通过分析全向视觉、电子罗盘和里程计等传感器的感知模型,设计并实现了一种给定环境模型下移动机器人全局自定位算法.该算法利用蒙特卡罗粒子滤波,融合多个传感器在不同观测点获取的观测数据完成机器人自定位.与传统的、采用单一传感器自定位的方法相比,它把多个同质或异质传感器所提供的不完整测量及相关联数据库中的信息加以综合,降低单个...     

Multi-sensor data fusion methods for indoor localization under collinear ambiguity

Sensor node localization in mobile ad-hoc sensor networks is a challenging problem. Often, the anchor nodes tend to line up in a linear fashion in a mobile sensor network when nodes are deployed in an ad-hoc manner. This paper discusses novel node localization methods under the conditions of collinear ambiguity of the anchors. Additionally, the work presented herein also describes a methodology to fuse data available from multiple sensors for improved localization performance under conditions of collinear ambiguity. In this context, data is first acquired from multiple sensors sensing different modalities. The data acquired from each sensor is used to compute attenuation models for each sensor. Subsequently, a combined multi-sensor attenuation model is developed. The fusion methodology uses a joint error optimization approach on the multi-sensor data. The distance between each sensor node and anchor is itself computed using the differential power principle. These distances are used in the localization of sensor nodes under the condition of collinear ambiguity of anchors. Localization error analysis is also carried out in indoor conditions and compared with the Cramer–Rao lower bound. Experimental results on node localization using simulations and real field deployments indicate reasonable improvements in terms of localization accuracy when compared to methods likes MLAR and MGLR.     

基于主成分分析的多源特征融合故障诊断方法

目前故障诊断的实际应用中,因噪声的千扰,基于单传感器的故障诊断稳定性较差,很难达到满意的诊断精确度。提出了一种多传感器多特征数据融合的故障诊断方法。该方法利用多传感器从不同部位获取同一部件的运行状况,并通过构建多源特征融合模型,提高特征信息的抗干扰性,最后通过融合特征信息来完成部件的故障诊断。在将新方法应用于滚动轴承故障诊断的试验中,可以看到新方法能够获得较好的性能,比基于单传感器故障诊断的精确度更高。     

舰载机多雷达传感器任务分配与采样间隔融合优化算法

针对舰载机协同探测中多雷达传感器资源配置问题,提出一种多目标跟踪场景下的多传感器数据率管理与任务分配融合优化算法.在基于协方差控制的多传感器分配模型基础上,加以目标优先级和传感器效能条件约束,建立一种多传感器数据率管理与任务分配融合优化模型.将驻留时间改进因子引入序贯卡尔曼滤波算法,计算不同采样间隔下传感器组合状态估计...     

Random weighting estimation for fusion of multi-dimensional position data

This paper adopts the concept of random weighting estimation to multi-sensor data fusion. It presents a new random weighting estimation methodology for optimal fusion of multi-dimensional position data. A multi-sensor observation model is constructed for multi-dimensional position. Based on this observation model, a random weighting estimation algorithm is developed for estimation of position data from single sensors. Using the random weighting estimations from each single sensor, an optimization theory is established for optimal fusion of multi-sensor position data. Experimental results demonstrate that the proposed methodology can effectively fuse multi-sensor dimensional position data, and the fusion accuracy is much higher than that of the Kalman fusion method.     

一种融合激光和深度视觉传感器的SLAM地图创建方法

针对移动机器人的不确定复杂环境,一般采用单一传感器进行同时定位和地图创建(SLAM)存在精度较低,并且易受干扰,可靠性不足等问题,本文提出一种基于Bayes方法的激光传感器和RGB-D传感器的信息融合SLAM方法,利用Bayes方法通过概率启发式模型提取光束投影到栅格地图单元,充分利用激光与视觉信息中的冗余信息,提取一致性特征信息,并进行特征级的信息融合;在地图更新阶段,本文提出一种融合激光传感器和视觉传感器的贝叶斯估计方法,对栅格地图进行更新。在使用ROS(移动机器人操作系统)的实验平台上实验表明,多传器信息融合可以有效提高SLAM的准确度和鲁棒性。     

多传感器融合的建筑入住率感知模型研究

提出一种多传感器融合的建筑入住率感知模型.通过基于相关性的特征选择方法对建筑内已存在的数据流进行筛选,利用多种监督类机器学习算法建立入住率感知模型.研究发现:多传感器融合能够有效建立入住率感知模型,各算法的准确率均在60％以上,其中支持向量机(包括线性和径向基)和朴素贝叶斯的效果较好,准确率均大于75％,均方差误差均小...     

Localization of mobile robots: Development and comparative evaluation of algorithms based on odometric and inertial sensors

An autonomous mobile robot must be able to elaborate the measures provided by the sensor equipment to localize itself with respect to a coordinate system. The precision of the location estimate depends on the sensor accuracy and on the reliability of the measure processing algorithm. The purpose of this article is to propose a low cost positioning system using internal sensors like odometers and optical fiber gyroscopes. Three simple localization algorithms based on different sensor data processing procedures are presented. Two of them operate in a deterministic framework, the third operates in a stochastic framework where the uncertainty is induced by sensing and unmodeled robot dynamics. The performance of the proposed localization algorithms are tested through a wide set of laboratory experiments and compared in terms of localization accuracy and computational cost. © 2005 Wiley Periodicals, Inc.     

基于无迹卡尔曼滤波传感器信息融合的车辆导航算法

针对复杂道路条件下车辆的导航问题,将全球定位系统(GPS)与车载终端传感器系统相结合,提出了基于多传感器系统的车辆精确定位模型,并针对扩展类卡尔曼滤波易产生突发性误差而导致的安全问题,采用基于Sigma点的无迹卡尔曼滤波器(UKF)传感器信息融合算法。根据实时的道路状况和车辆自身的运动状态给出符合要求的状态估值,实验与基于多项式扩展卡尔曼滤波车辆传感器信息融合算法在精度和效率方面进行了比较,结果表明,基于UKF传感器信息融合的算法在复杂路况下的估计精度和运行效率都有显著提高,能够根据当前的路线情况和车载传感器的反馈信息快速地估计出车辆的运动状态,实时计算出动态的车辆控制输入。     

一种面向互联概率加权的JPDA多传感器数据融合方法

针对单传感器联合概率数据互联(Joint Probabilistic Data Association, JPDA)在复杂环境下难以跟踪多个目标的问题,提出一种基于JPDA量测目标互联概率统计加权并行式和序贯式多传感器数据融合方法。首先,给出单传感器JPDA算法。然后,介绍多传感器JPDA数学模型,基于这一模型,使用互联概率加权,推导并行式和序贯式多传感器数据融合公式,这对多传感器数据融合有一定指导意义。最后,对单传感器JPDA方法在不同杂波密度、不同过程和不同观测噪声下目标跟踪的距离RMSE进行仿真,结果表明,随着这3项指标皆增大,目标距离RMSE增大;同时,对本文的2类多传感器JPDA方法与其他几类跟踪方法在数据集PETS2009下有关行人跟踪性能进行仿真,结果表明,本文并行式和序贯式多传感器JPDA方法相较于其他方法在跟踪准确性、跟踪位置准确性、航迹维持以及航迹遗失上皆为最优,而且序贯式融合略优于并行式多传感器JPDA。     

基于不确定融合的GPS/INS 组合导航滤波算法

针对实际车载组合导航系统测量中不确定噪声的问题,提出一种基于不确定融合估计的GPS/INS组合导航滤波算法,建立了导航系统的状态方程和观测方程;通过多信源不确定融合估计,得到多传感器的等效测量值以及误差方差阵;对系统方程进行滤波处理,得到车辆的准确位置。车载系统的实测数据表明,不确定噪声下的融合估计结果优于独立白噪声假设下的融合估计,并验证了所提出算法的有效性和实用性。     

基于多传感信息融合的语义词袋SLAM优化算法

针对室外大范围场景移动机器人建图中,激光雷达里程计位姿计算不准确导致SLAM (simultaneous localization and mapping)算法精度下降的问题,提出一种基于多传感信息融合的SLAM语义词袋优化算法MSW-SLAM(multi-sensor information fusion SLAM based on semantic word bags)。采用视觉惯性系统引入激光雷达原始观测数据,并通过滑动窗口实现了IMU (inertia measurement unit)量测、视觉特征和激光点云特征的多源数据联合非线性优化;最后算法利用视觉与激光雷达的语义词袋互补特性进行闭环优化,进一步提升了多传感器融合SLAM系统的全局定位和建图精度。实验结果显示,相比于传统的紧耦合双目视觉惯性里程计和激光雷达里程计定位,MSW-SLAM算法能够有效探测轨迹中的闭环信息,并实现高精度的全局位姿图优化,闭环检测后的点云地图具有良好的分辨率和全局一致性。     

靶场末区多传感器数据配准研究

从工程应用观点出发,研究靶场末区多传感器数据融合系统设计,通过分析各传感器的特点,给出了一种具有全天候和可靠测量的靶场末区融合系统结构,主要研究了融合系统中光电经纬仪时间和空间的数据配准方法,并给出靶场末区多传感器数据融合处理的主要步骤。试验结果证明:该融合系统能够提高落点测量的可靠性和精度。     

基于视频分析和多传感器融合的移动式监控系统

安防场景下,大多数传感器系统（视频、红外、烟雾传感）只能实现单一数据采集、简单处理.提出的移动式智能监控系统以小车为载体,通过对采集视频进行智能分析处理（包括基于背景差分的入侵检测算法和改进的TLD目标跟踪算法）,并辅助多传感器模块进行多信息融合协同监控,可以实现入侵检测、移动跟踪监测等功能.实验表明该系统能提供多种终端形式与用户进行友好交互,实现真正的智能安防.     

Cooperative localization based on robust GPS and Radar fusion for multiple aerial vehicles

This paper presents a localization framework for multiple aerial vehicles (AVs) based on sensor fusion of global positioning system (GPS) and the identification friend-or-foe (IFF) Radar system. The IFF-Radar play two roles: firstly, it detects the angle and the range between two AVs, and thus the path between the two vehicles can be modeled as a curve. Secondly, it detects which AV helps form the above curve, and receives the corresponding GPS information from the friend vehicle. Through the cooperation of the multiple AVs, not only GPS can work well with fewer satellites due to the block of canyon environments, but also differential GPS (DGPS) performance can be achieved when the place is beyond the coverage of the DGPS. Theoretical analysis shows that two GPS satellites are sufficient to obtain the location information with the help of two or more friend vehicles, and the performance is as accurate as DGPS with the help of two or more friend vehicles. Simulations show that the proposed approach can achieve better localization by the cooperation among multiple aerial vehicles than single aerial vehicle.

     

压缩感知下的自适应声源定位估计

声源定位是一个应用非常广泛的研究课题。针对阵列定位精度不高的问题,提出一种基于压缩感知的声源定位算法。通过构建冗余字典,该算法将网络中的多个未知源节点的位置作为一个系数向量,然后采用稀疏贝叶斯学习算法估计声源位置。为了增快算法的运行速度,提出一种有效的多分辨率字典构建方法,并迭代地减小定位空间,提高定位精度。实验结果显示,基于压缩感知的声源定位算法可以改善多源节点的定位能力,且有效地减少所需的传感器节点。此外,与基于子空间的算法比较显示,该算法的性能更优越。     

Vehicle Localization in Outdoor Mountainous Forested Paths and Extension of Two-Dimensional Road Centerline Maps to Three-Dimensional Maps

This paper presents an approach for vehicle three-dimensional (3-D) localization in outdoor woodland environments where a previously available two-dimensional road centerline map is used in combination with a loosely coupled multi-sensor system to estimate the vehicle position in mountainous forested paths. The localization system is composed of a wheel encoder, an inertial measurement unit, a DGPS, a laser sensor and a barometer. An extended Kalman filter is used for sensor data fusion and pose estimation. When available, DGPS is used for 3-D dead reckoning accumulated error correction. During DGPS blackouts, the laser sensor is used for road extraction and measurement of the displacement of the vehicle to the road centerline, then the position is corrected towards the map. Moreover, the barometer that measures the height difference towards a reference is used to correct the estimated height in absence of DGPS 3-D data. The estimated height is added to the available road map to obtain a 3-D road centerline map that includes the road width measured with the laser sensor. Experimental results in large-scale real mountainous woodland environments show the robustness and simplicity of the proposed approach for vehicle localization and 3-D map extension.     

用于胎压监测系统的一种改进贝叶斯估计数据融合算法的研究

针对小型汽车胎压监测系统(TPMS)利用单一传感器测量数据不确定性的问题,提出一种将贝叶斯估计和卡尔曼滤波相结合的多传感器数据融合的方法.设计满足系统功能要求的方案,运用贝叶斯估计对SP370轮胎模块中传感器采集的数据进行融合,排除失效的数据以及故障的传感器,提高系统的精度.结合卡尔曼滤波器优化融合的结果,消除噪声信号.研究结果表明,采用上述的数据融合方法能够有效的解决单一传感器测量数据的局限性,抑制传感器引入的噪声,并通过仿真验证了本系统的可行性、可靠性.     

多传感器集中式增量卡尔曼滤波融合算法

在单个传感器的状态估计系统中,标准的增量卡尔曼滤波方法可以有效消除量测系统误差。对于多传感器情况,标准算法失效。针对该问题,提出了多传感器集中式增量卡尔曼滤波融合算法,即:增量卡尔曼滤波的扩维融合算法和增量卡尔曼滤波的序贯融合算法。在标准增量卡尔曼滤波算法的基础上,结合扩维融合和序贯融合的思想来实现多传感器数据的融合。实验结果表明,当存在量测系统误差时,提出的集中式融合算法与传统的集中式融合算法相比,提高了滤波精度,并且能够成功地消除量测系统误差。     

基于多传感器融合的移动机器人定位

针对移动机器人定位系统中单一传感器定位精度低与环境地图的重要性问题, 提出了一种基于多传感器融合的移动机器人定位方法. 首先, 在未知环境下, 分别利用单一里程计, 扩展卡尔曼滤波(extended Kalman filter,EKF)算法融合里程计、惯性测量单元(inertial measurement unit, ...