Multi-sensor fusion methodology for enhanced land vehicle positioning

It is a main challenge for land vehicles to achieve reliable and low-cost navigation solution in various situations, especially when Global Positioning System (GPS) is not available. To address this challenge, we propose an enhanced multi-sensor fusion methodology to fuse the information from low-cost GPS, MEMS Inertial Measurement Unit (IMU), and digital compass in this paper. First, a key data preprocessing algorithm based on Empirical Mode Decomposition (EMD) interval threshold filter is developed to remove the noises in inertial sensors so as to offer more accurate information for subsequent modeling. Then, a Least-Squares Support Vector Machine (LSSVM)-based nonlinear autoregressive with exogenous input (NARX) model (LSSVM-NARX) is designed and augmented with Kalman filter (KF) to construct a novel LSSVM-NARX/KF hybrid strategy. In case of GPS outages, the recently updated LSSVM-NARX is adopted to predict and compensate for the INS position errors. Finally, the performance of proposed methodology was evaluated with real-world data collected in urban settings including typical driving maneuvers. The results indicate that the proposed methodology can achieve remarkable enhancement in positioning accuracy in GPS-denied environments.     

An intelligent navigator for seamless INS/GPS integrated land vehicle navigation applications

The Kalman filter (KF) has been implemented as the primary integration scheme of the global positioning system (GPS) and inertial navigation systems (INS) for many land vehicle navigation and positioning applications. However, it has been reported that KF-based techniques have certain limitations, which reflect on the position error accumulation during GPS signal outages. Therefore, this article exploits the idea of incorporating artificial neural networks to develop an alternative INS/GPS integration scheme, the intelligent navigator, for next generation land vehicle navigation and positioning applications. Real land vehicle test results demonstrated the capability of using stored navigation knowledge to provide real-time reliable positioning information for stand-alone INS-based navigation for up to 20 min with errors less than 16 m (as compared to 2.6 km in the case of the KF). For relatively short GPS outages, the KF was superior to the intelligent navigator for up to 30 s outages. In contrast, the intelligent navigator was superior to the KF when the length of GPS outages was extended to 90 s. The average improvement of the intelligent navigator reached 60% in the latter scenario. The results presented in this article strongly indicate the potential of including the intelligent navigator as the core algorithm for INS/GPS integrated land vehicle navigation systems.     

Optimizing neuro-fuzzy modules for data fusion of vehicular navigation systems using temporal cross-validation

The last two decades have shown an increasing trend in the use of positioning and navigation technologies in land vehicles. Most of the present navigation systems incorporate global positioning system (GPS) and inertial navigation system (INS), which are integrated using Kalman filtering (KF) to provide reliable positioning information. Due to several inadequacies related to KF-based INS/GPS integration, artificial intelligence (AI) methods have been recently suggested to replace KF. Various neural network and neuro-fuzzy methods for INS/GPS integration were introduced. However, these methods provided relatively poor positioning accuracy during long GPS outages. Moreover, the internal system parameters had to be tuned over time of the navigation mission to reach the desired positioning accuracy. In order to overcome these limitations, this study optimizes the AI-based INS/GPS integration schemes utilizing adaptive neuro-fuzzy inference system (ANFIS) by implementing, a temporal window-based cross-validation approach during the update procedure. The ANFIS-based system considers a non-overlap moving window instead of the commonly used sliding window approach. The proposed system is tested using differential GPS and navigational grade INS field test data obtained from a land vehicle experiment. The results showed that the proposed system is a reliable modeless system and platform independent module that requires no priori knowledge of the navigation equipment utilized. In addition, significant accuracy improvement was achieved during long GPS outages.     

A low-cost INS/GPS integration methodology based on random forest regression

This paper, for the first time, introduces a random forest regression based Inertial Navigation System (INS) and Global Positioning System (GPS) integration methodology to provide continuous, accurate and reliable navigation solution. Numerous techniques such as those based on Kalman filter (KF) and artificial intelligence approaches exist to fuse the INS and GPS data. The basic idea behind these fusion techniques is to model the INS error during GPS signal availability. In the case of outages, the developed model provides an INS error estimates, thereby maintaining the continuity and improving the navigation solution accuracy. KF based approaches possess several inadequacies related to sensor error model, immunity to noise, and computational load. Alternatively, neural network (NN) proposed to overcome KF limitations works unsatisfactorily for low-cost INS, as they suffer from poor generalization capability due to the presence of high amount of noise.In this study, random forest regression has shown to effectively model the highly non-linear INS error due to its improved generalization capability. To evaluate the proposed method effectiveness in bridging the period of GPS outages, four simulated GPS outages are considered over a real field test data. The proposed methodology illustrates a significant reduction in the positional error by 24–56%.     

Real-Time Implementation of GPS Aided Low-Cost Strapdown Inertial Navigation System

This work details the study, development, and experimental implementation of GPS aided strapdown inertial navigation system (INS) using commercial off-the-shelf low-cost inertial measurement unit (IMU). The data provided by the inertial navigation mechanization is fused with GPS measurements using loosely-coupled linear Kalman filter implemented with the aid of MPC555 microcontroller. The accuracy of the estimation when utilizing a low-cost inertial navigation system (INS) is limited by the accuracy of the sensors used and the mathematical modeling of INS and the aiding sensors’ errors. Therefore, the IMU data is fused with the GPS data to increase the accuracy of the integrated GPS/IMU system. The equations required for the local geographic frame mechanization are derived. The direction cosine matrix approach is selected to compute orientation angles and the unified mathematical framework is chosen for position/velocity algorithm computations. This selection resulted in significant reduction in mechanization errors. It is shown that the constructed GPS/IMU system is successfully implemented with an accurate and reliable performance.     

神经网络在MEMS-IMU/GPS组合导航中的应用研究

针对基于MEMS传感器组成的INS/GPS组合中GPS信号缺失的情况下,系统误差瞬时增大,滤波迅速退化无法继续工作的问题,本文提出利用神经网络辅助INS/GPS导航系统以解决这一问题的方法.该方法首先建立系统模型,用组合导航的输入作为网络模型的输入,通过网络训练得到输出需要参数,结合卡尔曼滤波用于组合导航以继续使导航系统工作,仿真结果表明该方法可行和有效性的.     

Enhancing positioning accuracy of GPS/INS system during GPS outages utilizing artificial neural network

Integrated global positioning system and inertial navigation system (GPS/INS) have been extensively employed for navigation purposes. However, low-grade GPS/INS systems generate erroneous navigation solutions in the absence of GPS signals and drift very fast. We propose in this paper a novel method to integrate a low-grade GPS/INS with an artificial neural network (ANN) structure. Our method is based on updating the INS in a Kalman filter structure using ANN during GPS outages. This study focuses on the design, implementation and integration of such an ANN employing an optimum multilayer perceptron (MLP) structure with relevant number of layers/perceptrons and an appropriate learning. As a result, a land test is conducted with the proposed ANN + GPS/INS system and we here provide the system performance with the land trials.     

列车组合导航系统研究与仿真

提出了一种列车组合导航系统.首先,采用低精度的惯性传感器构成简易惯性测量装置(IMU),设计了该简易IMU的安装结构,并给出了其导航定位解算方法.然后,将简易IMU与GPS构成组合导航系统,分析了IMU和GPS各自的误差源,并建立了组合系统误差模型,从而利用卡尔曼滤波技术设计了IMU/GPS列车组合导航算法.仿真结果表明,该IMU/GPS列车组合导航系统具有精度高、可靠性好、成本低等显著优点,非常适用于列车导航定位.     

基于UKF的UWB和GPS融合定位算法

智能汽车的发展对高精度定位需求日益显现. 针对汽车在城市建筑群、立交桥等特定环境下, 可见GPS卫星数量下降、车载GPS和惯性测量单元(inertial measurement unit, IMU)组合定位系统中IMU产生积累误差导致不能精确定位问题, 本文提出一种基于无迹卡尔曼滤波(unscented Kalman ...     

Merits and limitations of using fuzzy inference system for temporal integration of INS/GPS in vehicular navigation

Most of the present vehicular navigation systems rely on global positioning system (GPS) combined with inertial navigation system (INS) for reliable determination of the vehicle position and heading. Integrating both systems provide several advantages and eliminate their individual shortcomings. Kalman filter (KF) has been widely used to fuse data from both systems. However, KF-based integration techniques suffer from several limitations related to its immunity to noise, observability and the necessity of accurate stochastic models of sensor random errors. This article investigates the potential use of adaptive neuro-fuzzy inference system (ANFIS) for temporal integration of INS/GPS in vehicular navigation. An ANFIS-based module named “P–δP” is designed, developed, implemented and tested for fusing INS and GPS position information. The fusion process aims at providing continuous correction of INS position to prevent its long-term growth using GPS position updates. In addition, it provides reliable prediction of the vehicle position during GPS outages. The P–δP module was examined using real navigation system data compromising an Ashtech Z12 GPS receiver and a Honeywell LRF-III INS. The proposed module proved to be successful as a modeless and platform independent module that does not require a priori knowledge of the navigation equipment utilized. Limitations of the ANFIS module are also discussed.     

采用卡方检验的模糊自适应无迹卡尔曼滤波组合导航算法

针对低成本惯性测量单元精度受载体机动影响大、先验知识难以准确获知的问题,提出一种采用卡方检验的模糊自适应无迹卡尔曼滤波组合导航算法.首先,根据惯性测量单元的基本情况构造系统噪声的粗略模型;然后,引入卡方检验对系统状态模型进行评估,得到相应的卡方检验值;最后,通过预设的模糊逻辑函数和卡方检验值求取系统噪声估计值,得到具有系统噪声统计特性调整的自适应无迹卡尔曼滤波算法.所提出的算法可以克服低成本惯性测量单元难以准确获知先验知识的缺陷.通过SINS/GPS组合导航系统的仿真实例,验证了所提出算法的有效性.     

自适应联邦卡尔曼滤波在机器人组合导航系统中的应用研究

利用里程计(OD)与全球定位系统(GPS)辅助捷联惯性导航系统(SINS)构成一种高可靠性的组合导航系统.推导并建立了局部滤波器的数学模型,并针对联邦滤波器在载体发生异常扰动时滤波精度较低的问题,设计了基于SINS/GPS/OD组合导航系统的自适应联邦滤波器,有效补偿了系统异常扰动或动力学模型误差.仿真模拟了机器人的全航线运行轨迹进行验证,仿真结果表明,SINS/GPS/OD组合导航系统的自适应联邦卡尔曼滤波算法与相同组合导航系统的非自适应联邦卡尔曼滤波算法相比,在保障机器人导航定位可靠性及容错能力的前提下,能有效抑制异常扰动的影响,导航精度得到进一步改善.     

直接法UKF在组合导航中的应用

提出直接法卡尔曼滤波(UKF)应用于GPS/捷联惯导(SINS)组合导航,避免对非线性系统的线性化。选择SINS惯导系统输出位置和速度作为系统状态,GPS输出的导航参数作为观测量,使用IMU提供的姿态,用UKF方法结合反馈法对组合导航参数直接进行估计,不仅可以避免了每次导航复杂的初始对准过程,同时保持参数误差不会无限增大。根据是否出现GPS中断两种情况进行,实验结果表明,可以直接使用IMU提供的姿态对智能清洁船的定位导航。     

一种应用磁强计提高导航系统航向精度的方法

针对静止与匀速运动状态下低成本SINS/GPS组合导航系统航向角可观性差的问题,采用磁强计与低成本SINS/GPS构成新的组合导航系统,以提高系统的航向精度.给出了完整的组合导航系统卡尔曼滤波模型,利用Simulink进行了仿真实验.仿真结果表明:在静止与匀速运动状态下,SINS/GPS组合导航系统航向角误差发散,而SINS/GPS/磁强计组合导航系统的航向角有效收敛.利用某型系统进行了静态实验,实验表明:在传感器精度较差的条件下,SINS/GPS/磁强计组合系统航向角仍可以有效收敛,收敛后姿态角误差标准差小于0.2.静态实验验证了该方法在实际应用中的有效性.     

Multiconfiguration Kalman filter design for high-performance GPS navigation

This paper describes the design, implementation, and performance of a real-time multiconfiguration Kalman filter for high-performance Navstar global positioning system (GPS) navigation. The design provides extreme flexibility in order to operate with a wide variety of host sensors. It configures automatically (four filter configurations) based upon the host vehicle requirements and sensor availability, in order to process GPS measurements and provide the best estimate of the navigation states. Two new techniques, namely an unaided dead-reckoning Kalman filter implementation and an automatic inertial platform tilt estimation control scheme, are developed to improve the navigation accuracy, especially for high-dynamics applications. Performance results are presented to demonstrate the advantages of these techniques.     

基于SLAM的旋翼无人机组合导航算法研究

在旋翼无人机组合导航中,针对缺乏GPS作为导航信号源的室内飞行环境,为了达到精确定位的目的,提出一种基于SLAM（simultaneous localization and mapping）的旋翼无人机组合导航算法。首先,引入双线性插值算法,实现基于扫描匹配的即时定位与地图构建;其次,对陀螺仪、加速度计和磁罗盘建立捷联惯导系统误差模型,针对旋翼无人机的使用环境对误差模型进行简化;最后,应用联邦卡尔曼滤波算法,设计组合导航系统模型,将SLAM算法和捷联惯导系统估计出的位置数据进行融合。仿真结果表明所设计基于SLAM的旋翼无人机组合导航算法能够进一步提高组合导航系统对旋翼无人机位姿估计的精度。     

基于最大熵卡尔曼滤波的机载SINS星敏感器辅助空中标定技术

为增强机载捷联惯导系统（SINS）在自标定过程中的可观测性,提升陀螺仪漂移和加速度计零偏估计的速度和精度,引入星敏感器姿态信息和GPS速度信息,辅助完成捷联惯导系统的空中标定。同时,考虑在实际空中飞行条件下,受气流、电磁干扰等影响,姿态和速度的量测噪声呈非高斯分布且噪声统计特性不精确,导致经典卡尔曼滤波性能降低。为有效利用量测信号中的高阶矩信息,在卡尔曼滤波中采用最大熵准则代替最小均方误差准则,对星敏感器辅助下的机载捷联惯导系统的误差进行标定。仿真结果表明,经最大熵卡尔曼滤波后,惯性器件误差的标定精度明显提升;在采用星敏感器后,对陀螺仪漂移的标定速度和精度都得到了提升。     

惯导系统辅助CSS的室内定位方法

提出一种惯性导航系统INS(Inertial Navigation System)辅助线性调频扩频CSS(Chirp Spread Spectrum)的高精度室内定位方法.首先设计了基于MPU9250多轴传感器的惯性测量单元IMU(Inertial Measurement Unit),利用数字运动处理(DMP)数据库经四元数解算可求得准确稳定的航向角,由于MPU9250自带的磁力计,规避了航向角的累积误差问题.随后在分析CSS非视距定位误差基础上,提出了基于三角形三边准则的选星方法,有效降低了室内复杂环境下非视距的影响;最后利用扩展卡尔曼滤波对惯导系统与CSS定位进行融合,以输出稳定、准确的定位结果.通过在50 m×20 m的地下车库实验分析比较,结果表明:惯导与CSS单独定位的平均误差分别为0.3456 m、0.3659 m,本文组合导航方法平均误差为0.158 l m,较前两种单一的定位方式性能提高了50%以上,该方法降低了定位的成本,系统实现复杂度降低,定位精度提高.     

非完整约束下滤波算法在组合导航中的应用

MEMS IMU/GPS组合导航系统的应用环境愈来愈复杂,对其精度的要求也愈来愈高,只使用普通卡尔曼滤波不能满足精度和稳定性要求。针对此问题,将Sage-husa自适应卡尔曼滤波算法和非完整约束应用到前向导航滤波算法和后向导航滤波算法中,并将前向滤波和后向滤波结果加权组合,提出了一种非完整约束下加权组合滤波算法,用于事后IMU/GPS联合解算中,用来提高组合导航的精度。并利用实验室设备进行车载实验,通过实测车载数据解算结果来验证该方法的可行性。实验结果表明非完整约束下加权组合滤波后的经纬度误差小于1.4 m,航向角误差小于1.0°,满足MEMS IMU/GPS车载组合导航系统的精度要求。     

组合导航系统NNM信息融合算法

提出了将神经网络模型（NNM）概念应用于组合导航系统，并给出了基于RBP网的NNM训练过程，基于传统模型的卡尔曼滤波算法与神经网络相结合，有效地解决了GPS信号被屏蔽时的航迹预测问题，最后对GPS/DR组合导航系统进行动态仿真，仿真结果表明，采用该算法的组合导航系统定位精度高、可靠性好。