基于NARX神经网络辅助组合导航方法研究

为解决短时全球导航卫星系统(GNSS)失效造成车载组合导航系统导航精度下降的问题,提出一种NARX神经网络辅助的组合导航方法。对神经网络辅助导航的原理进行了分类,并分析了神经网络可利用的输入输出信息,提出一种根据惯性测量单位(IMU)测量信息和惯性导航解算信息对GNSS位置速度增量进行预测的方法。通过实测数据实验验证了方法的有效性,GNSS失效60 s期间,导航最大位置误差5.1 m、最大速度误差0.15 m/s。     

Improving positioning accuracy of vehicular navigation system during GPS outages utilizing ensemble learning algorithm

Recently, methods based on Artificial Intelligence (AI) have been widely used to improve positioning accuracy for land vehicle navigation by integrating the Global Positioning System (GPS) with the Strapdown Inertial Navigation System (SINS). In this paper, we propose the ensemble learning algorithm instead of traditional single neural network to overcome the limitations of complex and dynamic data cased by vehicle irregular movement. The ensemble learning algorithm (LSBoost or Bagging), similar to the neural network, can build the SINS/GPS position model based on current and some past samples of SINS velocity, attitude and IMU output information. The performance of the proposed algorithm has been experimentally verified using GPS and SINS data of different trajectories collected in some land vehicle navigation tests. The comparison results between the proposed model and traditional algorithms indicate that the proposed algorithm can improve the positioning accuracy for cases of SINS and specific GPS outages.     

MEMS SINS-GPS组合导航系统设计

为实现满足中低精度要求的低成本导航系统,选用MEMS惯性传感器研制了捷联式惯性导航系统(SINS);针对MEMS惯性传感器噪声较大和惯性导航系统误差随时间迅速累积的问题,利用小波对MEMS陀螺信号进行了降噪处理,并采用SINS-GPS卡尔曼滤波组合导航系统以消除惯导系统的误差累积,输出较高精度的速度、位置信息.对SINS和组合导航系统进行了仿真实验,实验结果表明所建系统的长时间导航性能有一定改善.     

Seamless navigation and mapping using an INS/GNSS/grid-based SLAM semi-tightly coupled integration scheme

Mobile Mapping Systems (MMS) with Inertial Navigation System / Global Navigation Satellite System (INS/GNSS) and mapping sensors have been widely developed in recent years. However current systems and results are still prone to errors, especially in GNSS-denied or multipath environments. To provide robust and stable navigation information, particularly for mapping in long-term GNSS-denied environments, we propose a semi-tightly coupled integration scheme which integrates INS/GNSS with grid-based Simultaneous Localization and Mapping (SLAM). Although traditional SLAM using LiDAR can map the GNSS-denied environment efficiently, it is only in local localization. The proposed integration scheme is based on the Extended Kalman Filter (EKF) with motion constraints. In this scheme, a measurement model for grid-based SLAM is aided by the heading and velocity information. A special innovation of this scheme is the improved fusion of GNSS/INS with the use of grid-based SLAM serves like virtual odometer and virtual compass, thus gaining reliable measurements and error models to maintain good performance during INS-only mode. In addition, the initial values for example position and heading, are given to solve global localization and loop closure problems in SLAM. Finally, a smoothing and multi-resolution map strategy are applied offline to increase the robustness and performance of the proposed grid-based SLAM. Evaluation based on experimental data shows the significant improvement by the proposed semi-tightly coupled integration scheme with low-cost INS/GNSS and LiDAR, which is able to achieve 1–2 m’ accuracy in terms of positioning and mapping. An approximately 60% improvement was achieved during long-term GNSS-denied environments using the proposed integration scheme.     

基于惯性系的旋转式惯导系统快速对准算法

针对船舶大幅角晃动和线运动等复杂干扰,导致旋转式捷联惯导系统初始对准性能下降的问题,设计了基于惯性系的旋转式捷联惯导系统快速初始对准算法.针对旋转式捷联惯导系统的误差特性,设计了基于惯性系的粗对准方案;并提出了一种改进的罗经对准算法,达到缩短对准时间和提高对准精度的目的.仿真实验证明:该方法可以实现快速初始对准,7 min航向精度达到1.35′.     

移动USBL测距辅助的UUV协同导航定位方法

针对无人水下航行器(UUV) 导航精度受惯性导航(INS) 影响较大的问题, 本文提出一种基于无人水面船 (USV)携带超短基线(USBL)对UUV进行移动式辅助导航定位的方法. 文中以USV上高精度INS和全球导航卫星系 统(GNSS)组合后的导航结果作为基准, 利用USBL测量得到的USV和UUV相对位置和姿态信息, 结合UUV的INS误 差方程, 建立了UUV协同导航系统的状态方程和观测方程, 并基于自适应卡尔曼滤波方法对UUV状态进行滤波估 计. 仿真和湖上实验结果表明, 文中所提方法可有效提升UUV导航精度.     

组合导航中低成本磁航向系统的神经网络补偿

根据组合导航的特点,设计了低成本磁航向系统神经网络补偿方法。研究了磁航向系统的误差和补偿技术;在全球定位系统信号良好情况下,以捷联惯导/全球定位组合导航系统的航向信息为参考,使用卡尔曼滤波作为学习算法,建立多层前向神经网络模型补偿磁航向系统。实验结果表明,神经网络补偿方法将磁航向系统的航向角误差由±15°减小到约±1°,取得了明显的效果。     

The integration of strap-down INS and GPS based on adaptive error damping

The concept and results of integration of a strap-down inertial navigation system (INS) based on low-accuracy inertial sensors and the global positioning system (GPS) have been presented in this paper. This system is aimed for the purposes of navigation, automatic control, and remote tracking of land vehicles. The integration is made by the implementation of an extended Kalman filter (EKF) scheme for both the initial alignment and navigation phases. Traditional integration schemes (centralized and cascaded) are dominantly based on the usage of high-accuracy inertial sensors. The idea behind the suggested algorithm is to use low-accuracy inertial sensors and the GPS as the main source of navigation information, while the acceptable accuracy of INS is achieved by the proper damping of INS errors. The main advantage of integration consists in the availability of reliable navigation parameters during the intervals of absence of GPS data. The influence of INS error damping coefficients is different depending on the fact whether the moving object is maneuvering or is moving with a constant velocity at that time. It is proposed that INS error damping gain coefficients generally should take higher values always when GPS data are absent, while at the same time their values in the error model (EKF prediction phase) can be additionally adapted according to the actual values of vehicle acceleration. The analysis of integrated navigation system performances is made experimentally. The data are acquired along the real land vehicle’s trajectory while the intervals of absence of GPS data are introduced artificially on the parts characterized both by maneuver and by constant velocity.     

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.     

Sensor Integration for Satellite-Based Vehicular Navigation Using Neural Networks

Land vehicles rely mainly on global positioning system (GPS) to provide their position with consistent accuracy. However, GPS receivers may encounter frequent GPS outages within urban areas where satellite signals are blocked. In order to overcome this problem, GPS is usually combined with inertial sensors mounted inside the vehicle to obtain a reliable navigation solution, especially during GPS outages. This letter proposes a data fusion technique based on radial basis function neural network (RBFNN) that integrates GPS with inertial sensors in real time. A field test data was used to examine the performance of the proposed data fusion module and the results discuss the merits and the limitations of the proposed technique     

基于INS/GPS/COMPASS的AUV组合式导航定位算法

导航定位问题是自主式水下机器人研究(AUV)的主要内容之一,本文针对一种开架式AUV设计了一种采用间接反馈校正的捷联惯性导航与GPS、罗盘相组合的导航方案,其中采用卡尔曼滤波器接收两套导航子系统对同一导航参数输出值的差值,经过滤波计算估计出各误差量。仿真实验的结果表明,SINS/GPS/COMPASS组合导航对SINS误差随时间不断加大的现象起到了很好的抑制作用,能够满足AUV定位精度的要求。     

Advanced state estimation for navigation of automated vehicles

For the emerging topic of automated and autonomous vehicles in all major sectors, reliable and accurate state estimation for navigation of these vehicles becomes increasingly important. Inertial navigation, aided with measurements from global navigation satellite systems (GNSS), allows high-rate and low-cost estimation of position, velocity and orientation in real-time applications. As the available satellite constellations for navigation are modernized and their number is rising, usage of multi-constellation, dual-frequency and integration of correction data lead to increased accuracy, especially in areas with partial shadowing. Different coupling methods, e.g. tightly- and loosely-coupled integrations, were developed to combine inertial and GNSS measurements. Also different error estimation filters were applied to the navigation problem, and evaluated against each other. For the typical navigation task, the objective is to choose a suitable algorithm for the specific requirements of the target application, and deploy it using an appropriate implementation strategy. This contribution gives a short introduction into the field of aided inertial navigation techniques, provides useful hints for implementation, and evaluates their performance in experiments using two different railway vehicles, an autonomous maritime vessel, and an unmanned aerial quadrotor.     

新的改进K均值粒子群算法在组合导航的应用

在捷联惯导/卫星导航（SINS/GNSS）紧组合导航系统的非线性非高斯高动态模型中,一般K均值粒子群优化（PSO）算法易出现粒子退化、滤波发散等问题。针对上述问题,提出一种融入权值修正的K均值粒子群滤波方法。通过观测SINS/GNSS紧组合导航系统的精度因子(GDOP),来修正粒子权值,从而修正每个K均值的聚类中心的权重,进而优化粒子;并结合SINS/GNSS紧组合导航系统模型进行了仿真分析。结果表明在非线性非高斯高动态的情况下,该改进算法有效地抑制了滤波发散,提高了精度。     

Validation of nonlinear integrated navigation solutions

There exist numerous navigation solutions already implemented into various navigation systems. Depending on the vehicle in which the navigation system is used, it can be distinguished in most cases among; navigation, tactical, and commercial grade categories of such systems. The core of these systems is formed by inertial sensors, i.e. accelerometers and angular rate sensors/gyros. Navigation and tactical grade systems commonly rely on fiber optic/ring laser gyros and servo/quartz accelerometers with high resolution, sensitivity, and stability. In the case of cost-effective navigation systems, for example piloted light and ultralight aircraft, usually use commercial grade sensors, where the situation differs. The sensor outputs are less stable and sensitive, and suffer from manufacturing limits leading to temperature dependency, bias instability, and misalignment which introduces non-negligible disturbances. These conditions commonly limit the applicability of the navigation solution since its stand-alone operation using free integration of accelerations and angular rates is not stable. This paper addresses a cost-effective solution with commercial grade inertial sensors, and studies the performance of different approaches to obtain navigation solution with robustness to GNSS outages. A main goal of this paper is thus comparison of a nonlinear observer and two extended Kalman filter solutions with respect to the accuracy of estimated quantities and their sensitivity to GNSS outages. The performance analyses are carried out on real flight data and evaluated during phases of the flight when the solutions are challenged by different environmental disturbances.     

基于Elman神经网络的GNSS/INS全域高精度定位方法

针对当前智能网联汽车定位与导航系统无法接收全球导航卫星系统（GNSS）信号引起定位失效的问题，提出一种基于Elman神经网络的GNSS结合惯性导航系统（INS）的全域高精度定位方法。首先，采用神经网络方法，建立了基于Elman网络的GNSS/INS高精度定位训练模型和GNSS失效预测模型；然后，利用GNSS、INS和实时动态（RTK）等定位技术，设计了GNSS/INS高精度定位数据采集实验系统；最后，选取采集的有效实验数据进行了反向传播（BP）神经网络、级联BP（CFBP）神经网络、Elman神经网络的训练模型性能对比分析，并验证了基于Elman网络的GNSS失效预测模型。实验结果表明，所提方法训练误差指标均优于基于BP和CFBP神经网络的方法；在GNSS失效1 min、2 min、5 min时，基于预测模型的预测平均绝对误差（MAE）、方差（VAR）和均方根误差（RMSE）分别为18.88 cm、19.29 cm、58.83 cm，8.96、8.45、5.68和20.90、21.06、59.10，随着GNSS信号失效时长的增加，定位预测精度降低。     

融合5G/GNSS的车辆高精度鲁棒安全定位:进展与展望

不受环境和条件影响的准确、实时定位对于基于位置的车辆应用和自动驾驶至关重要.典型车辆定位通常依赖于全球卫星导航系统(GNSS),如美国GPS、中国北斗等,由于易受遮挡和阻塞,常将其与惯导、视觉等技术融合弥补GNSS缺陷.但车规级传感器易受驾驶状态、天气等因素影响,很难精确测量,影响定位性能.近年来,依托先进5G技术和广域基础设施建设,5G/GNSS融合定位可以提供更为精确鲁棒实时的位置结果,并逐渐成为车辆高精定位的主要手段.鉴于极少有车辆定位领域应用5G/GNSS融合方法的系统综述,面向车辆定位,从精度、鲁棒、实时安全等多方面分述基于5G/GNSS融合的先进定位方法,并探讨研究空白和未来研究方向.     

Concurrent Map Building and Behavior Learning for Navigation in Unknown Environments

In this paper, we report a robust and low-cost navigation algorithm for an unknown environment based on integration of a grid-based map building algorithm with behavior learning. The study focuses on mobile robots that utilize ultrasonic sensors as their prime interface with the outside world. The proposed algorithm takes into account environmental information to augment the readings from the low angular accuracy sonar measurements for behavior learning. The environmental information is obtained by an online grid-based map learning design that is concurrently operating with the behavior learning algorithm. The proposed algorithm is implemented and tested on an in-house-built mobile robot, and its performance is verified through online navigation in an indoor environment.     

导航算法对捷联惯导系统精度的影响分析

导航算法精度的高低直接影响着捷联惯导系统的性能。在惯性元件输出为增量形式的条件下对捷联惯导系统姿态更新、速度更新和位置更新算法进行分析。仿真实验得出:在影响导航精度的因素中,姿态更新算法最大,速度更新算法和位置更新算法次之。为导航算法的研究提供一定的借鉴。     

高超声速飞行器惯导系统误差参数两次优化辨识方法

为满足高超声速飞行器高精度和高可靠性的导航要求,提出一种在发射惯性系下利用智能优化算法实现捷联惯性系统误差参数两次优化辨识的方法.建立惯性测量单元(IMU)误差补偿模型和完整的非线性捷联惯性系统导航模型,为数值优化计算提供准确的模型基础.基于SINS/GPS/CNS组合导航系统信息,建立陀螺仪误差优化模型和加速度计误差优化模型,采用两次优化策略分步估计捷联惯性系统误差参数:首先利用粒子群算法对陀螺仪误差参数进行优化辨识和补偿;然后利用粒子群算法对加速度计误差参数进行优化辨识.仿真结果表明,基于组合导航系统信息和非线性优化模型,两次优化辨识方法能够在线辨识出高精度的捷联惯性系统误差参数,陀螺仪和加速度计优化参数值的相对误差均在20%以内,从而有效提高了高超声速飞行器导航精度.     

基于自适应神经网络的激光陀螺温度补偿研究

针对捷联惯性导航系统中激光陀螺的输出信号随温度漂移的问题,研究了激光陀螺的零偏与温度的关系,建立了一种新的考虑温度变化率的零偏温度补偿模型.在分析BP神经网络的基础上,提出了一种基于线性再励的自适应变步长神经网络算法进行激光陀螺的零偏温度模型系数的辨识.仿真结果表明,该方法能够有效地进行温漂补偿,从而提高惯组系统的导航精度.