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.     

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.     

路网辅助的车载INS/GPS组合导航方法

针对车载INS/GPS组合导航系统在GPS无效时精度迅速下降的问题,提出了将车辆行驶的路网约束作为虚拟传感器,采用多传感器数据融合的方式,与INS和GPS组成INS/GPS/路网组合导航系统.当GPS失效时,使用路网辅助INS.仿真结果表明,在GPS无效时间段,该方法能有效减小系统定位误差.     

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%.     

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.     

Amplified wavelet-ANFIS-based model for GPS/INS integration to enhance vehicular navigation system

Inertial navigation system (INS) relying on gyroscopes and accelerometers has been recently utilized in land vehicles. These INS sensors are integrated with Global Positioning System (GPS) to provide reliable positioning solutions in case of GPS outages that commonly occur in urban canyons. The major inadequacies of INS navigation sensors are the high noise level and the large bias instabilities that are stochastic in nature. The effects of these inadequacies manifest themselves as large position errors during GPS outages. Wavelet analysis is a signal processing method which is recently auspicious by many researchers due to its advantageous adaptation to non-stationary signals and able to perform analysis in both time and frequency domain over other signal processing methods such as the fast Fourier transform in some fields. This research proposes the utilization of wavelet de-nosing to improve the signal-to-noise ratio of each of the INS sensors. In addition, a neuro-fuzzy module is used to provide a reliable prediction of the vehicle position during GPS outages. The results from a road test experiment show the effectiveness of the proposed wavelet—neuro-fuzzy module.     

Development of a navigation and control system for an autonomous outdoor vehicle in a steel plant

This paper describes the navigation and control system for an autonomous guided outdoor vehicle (AGV) which is used to transport heavy steel slabs in a steel plant area. The vehicle has unconventional kinematics. It has six axles all pair wise steerable by three bogie structures. The weight of the machine is 17,000 kg and its load may weigh up to 95,000 kg. The navigation is based on a fusion of dead reckoning and transponder positioning. The transponders are passive and are buried in the ground every 5–10 m along the routes of the AGV. A wireless communication has been built to connect the vehicle control system and a remote control station. This article concentrates mainly on describing the navigation system including the kinematics and position control as well as the safety system and the remote control system.     

Cascading artificial neural networks optimized by genetic algorithms and integrated with global navigation satellite system to offer accurate ubiquitous positioning in urban environment

Location-based services (LBSs) have long been identified as an important component of emerging mobile services. While outdoor positioning has become strongly established, systems dealing with indoor positioning in urban environment are still under development. The upcoming LBSs require positioning systems (PSs) that are available ubiquitously, which requires the integration of the PS available in an outdoor environment with the PS available in indoor environment. Global navigation satellite systems (GNSSs) such as GPS, GLONASS, Galileo, and QZSS are some of the prominent systems that provide outdoor positioning. Indoor positioning systems (IPSs), however, are undergoing rapid development, and these systems can be supplied using short-range wireless technologies such as Wi-Fi, Bluetooth, RFID, and Infrared. Among these technologies, intense research is being conducted into Wi-Fi-based positioning systems due to their ubiquitous presence. This paper presents a model and results for a ubiquitous positioning system (UPS) that integrates a novel WLAN-based IPS and GNSS. The IPS is developed using cascading artificial neural networks, which are further optimized using genetic algorithms. The systems were thoroughly investigated on an actual Wi-Fi network at Asian Institute of Technology, Thailand. The IPS demonstrated a mean accuracy of 2.10 m and the UPS demonstrated a mean accuracy of 3.26 m, with 89% of the distance error within the range of 0–3.5 m.     

GNSS accuracy enhancement based on pseudo range error estimation in an urban propagation environment

For new ITS applications, positioning solutions will require to be more accurate and available. The most common technique used today is composed of a GPS receiver, sometimes aided by other sensors. GPS, and GNSS in general, suffer from masking effects and propagation disturbances in urban areas that cause biases on pseudo range measurements. Mitigation solutions sometimes propose to detect and exclude outliers but in land transportation applications, such a decision reduces dramatically the service availability and thus, the interest of satellite-based solutions. In order to optimize the use the satellites received, we propose a new positioning algorithm based on signals only with pseudo range error modeling in association with an adapted filtering process. The model and the filter have been validated with simulation data performed along an urban bus line and have shown that both positioning error and availability can be improved. Along the trajectory tested, the mean accuracy has been reduced from 5.3 m with a classical filter to 2.6 m with our algorithm with 89% of the points more accurate than 5 m instead of 64% before.     

Adaptive Fuzzy Prediction of Low-Cost Inertial-Based Positioning Errors

Kalman filter (KF) is the most commonly used estimation technique for integrating signals from short-term high performance systems, like inertial navigation systems (INSs), with reference systems exhibiting long-term stability, like the global positioning system (GPS). However, KF only works well under appropriately predefined linear dynamic error models and input data that fit this model. The latter condition is rather difficult to be fulfilled by a low-cost inertial measurement unit (IMU) utilizing microelectromechanical system (MEMS) sensors due to the significance of their long- and short-term errors that are mixed with the motion dynamics. As a result, if the reference GPS signals are absent or the Kalman filter is working for a long time in prediction mode, the corresponding state estimate will quickly drift with time causing a dramatic degradation in the overall accuracy of the integrated system. An auxiliary fuzzy-based model for predicting the KF positioning error states during GPS signal outages is presented in this paper. The initial parameters of this model is developed through an offline fuzzy orthogonal-least-squares (OLS) training while the adaptive neuro-fuzzy inference system (ANFIS) is implemented for online adaptation of these initial parameters. Performance of the proposed model has been experimentally verified using low-cost inertial data collected in a land vehicle navigation test and by simulating a number of GPS signal outages. The test results indicate that the proposed fuzzy-based model can efficiently provide corrections to the standalone IMU predicted navigation states particularly position.     

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.     

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.     

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.     

Design,fabrication, and testing of a 3-DOF HARM micromanipulator on (1 1 1) silicon substrate

In this study, a novel HARM (high aspect ratio micromachining) micromanipulator fabricated on (1 1 1) silicon wafer is reported. The micromanipulator consists of a positioning stage, a robot arm, supporting platforms, conducting wires, and bonding pads. These components are monolithically integrated on a chip through the presented processes. The three-degrees-of-freedom (3-DOF) positioning of the micromanipulator is realized by using the integration of two linear comb actuators and a vertical comb actuator. The robot arm is used to manipulate samples with dimension in the order of several microns to several hundred microns, for instance, optical fibers and biological samples. The robot arm could be a gripper, a needle, a probe, or even a pipette. Since the micromanipulator is made of single crystal silicon, it has superior mechanical properties. A micro gripper has also been successfully designed and fabricated.     

Development of a slender continuum robotic system for on-wing inspection/repair of gas turbine engines

The maintenance works (e.g. inspection, repair) of aero-engines while still attached on the airframes requires a desirable approach since this can significantly shorten both the time and cost of such interventions as the aerospace industry commonly operates based on the generic concept “power by the hour”. However, navigating and performing a multi-axis movement of an end-effector in a very constrained environment such as gas turbine engines is a challenging task. This paper reports on the development of a highly flexible slender (i.e. low diameter-to-length ratios) continuum robot of 25 degrees of freedom capable to uncoil from a drum to provide the feeding motion needed to navigate into crammed environments and then perform, with its last 6 DoF, complex trajectories with a camera equipped machining end-effector for allowing in-situ interventions at a low-pressure compressor of a gas turbine engine. This continuum robot is a compact system and presents a set of innovative mechatronics solutions such as: (i) twin commanding cables to minimise the number of actuators; (ii) twin compliant joints to enable large bending angles (±90°) arranged on a tapered structure (start from 40 mm to 13 mm at its end); (iii) feeding motion provided by a rotating drum for coiling/uncoiling the continuum robot; (iv) machining end-effector equipped with vision system. To be able to achieve the in-situ maintenance tasks, a set of innovative control algorithms to enable the navigation and end-effector path generation have been developed and implemented. Finally, the continuum robot has been tested both for navigation and movement of the end-effector against a specified target within a gas turbine engine mock-up proving that: (i) max. deviations in navigation from the desired path (1000 mm length with bends between 45° and 90°) are ±10 mm; (ii) max. errors in positioning the end-effector against a target situated at the end of navigation path is 1 mm. Thus, this paper presents a compact continuum robot that could be considered as a step forward in providing aero-engine manufacturers with a solution to perform complex tasks in an invasive manner.     

Predictive functional control of an axis positioning system with an estimator-based internal model

This paper deals with an application of the predictive functional control with a state estimator-based internal model (PFC_ EBIM). The PFC_ EBIM has been shown to be effective in simulation. However, neither detailed experimental validation nor comparison with other controllers has been reported thus far. Here, the PFC_ EBIM is implemented in a single-axis positioning system, and a few experimental tests are conducted. Tracking performance of the PFC_ EBIM, standard PFC, and P – PI control for both smooth and non-smooth reference signals are compared. The experimental results prove the effectiveness of the PFC_ EBIM.     

Damaged corporate reputation: Can celebrity Tweets repair it?

These days, many corporations engage in Twitter activities as a part of their communication strategy. Corporations can use this medium to share information with stakeholders, to answer customer questions, or to build on their image. In this study we examined the extent to which celebrity Tweet messages can be used to repair a damaged corporate reputation, and how this message should be designed and what celebrity should be ‘used’.In two experiments, a 2 × 2 (attractive celebrity versus intelligent celebrity) × (personal message versus general message) design was used. In total, 163 respondents first expressed their feelings regarding the two organisations in a baseline reputation measurement (M = 4.72 on 7 point Likert scale). After that a news items was presented communicating a big fraud and mismanagement, resulting in a decreased reputation score (M = 4.10). In the final stage one of the four experimental Tweets was presented, aimed at repairing the damaged reputation, which succeeded (M = 4.43). For both organisations, the crisis prime significantly decreased reputation scores, and the Tweet significantly increased reputation score again. The analysis of variance shows a main effect for type of celebrity. In our experiment the intelligent celebrity’s Tweet was best to use.The study reveals that celebrities’ Tweets can restore a positive public opinion about corporations. This study shows that when it comes to serious matters, an intelligent celebrity, who has the best fit with the topic, is of best impact. Consequences for corporate communication and future research are discussed.     

Life-space characterization from cellular telephone collected GPS data

Life-space is an emerging method for measuring older adults’ functional status. Although global positioning system (GPS)-enabled smartphones can collect life-space data passively and accurately, researchers lack an effective process to derive activity information from the raw GPS data. In addition, the influence of GPS retrieving frequency on life-space characterization is unknown. We describe a GPS data processing procedure to estimate life-space. A cellular telephone was used to collect GPS data by a subject during a 4-month period. The GPS data processing procedure was then implemented and evaluated in terms of classification accuracy, reliability, and sensitivity to observation frequency. The proposed scheme generated sufficient zone-based activity information to characterize an individual’s life-space. The speed-based sensitivity assessment suggests 75 s as an appropriate GPS observation interval for smartphone based life-space data collection.     

PERFORMANCE ANALYSIS OF VARIOUS ARTIFICIAL INTELLIGENT NEURAL NETWORKS FOR GPS/INS INTEGRATION

An aircraft system mainly relies on a Global Positioning System (GPS) to provide accurate position values consistently. However, GPS receivers may encounter frequent GPS absence because of ephemeric error, satellite clock error, multipath error, and signal jamming. To overcome these drawbacks, generally a GPS is integrated with an Inertial Navigation System (INS) mounted inside the vehicle to provide a reliable navigation solution. INS and GPS are commonly integrated using a Kalman filter (KF) to provide a robust navigation solution. In the KF approach, the error models of both INS and GPS are required; this leads to the complexity of the system. This research work presents new position update architecture (NPUA) which consists of various artificial intelligence neural networks (AINN) that integrate both GPS and INS to overcome the drawbacks of the Kalman filter. The various AINNs that include both static and dynamic networks described for the system are radial basis function neural network (RBFNN), backpropagation neural network (BPN), forward-only counter propagation neural network (FCPN), full counter propagation neural network (Full CPN), adaptive resonance theory-counter propagation neural network (ART-CPN), constructive neural network (CNN), higher-order neural networks (HONN), and input-delayed neural networks (IDNN) to predict the INS position error during GPS absence, resulting in different performances. The performances of the different AINNs are analyzed in terms of root mean square error (RMSE), performance index (PI), number of epochs, and execution time (ET).     

GPS/AVL系统解决方案

全球定位系统，又称GPS，是新一代的导航定位系统，它能够为全球任意地点、任意多个用户同时提供高精度的，全天候的，连续的，实时的三维定位、测速和时间基准，它在测绘和导航方面具有广泛的应用，该文介绍了GPS在智能交通系统（ITS）中的应用－车辆自动定位（GPS／AVL）系统，在该系统中给出了硬件的选型和GPS与GIS集成技术。