Low-cost Global Positioning System Receivers Research Articles

Performance Analysis of Relative GPS Positioning for Low-Cost Receiver-Equipped Agricultural Rovers.

Global navigation satellite systems (GNSSs) became an integral part of all aspects of our lives, whether for positioning, navigation, or timing services. These systems are central to a range of applications including road, aviation, maritime, and location-based services, agriculture, and surveying. The Global Positioning System (GPS) Standard Position Service (SPS) provides position accuracy up to 10 m. However, some modern-day applications, such as precision agriculture (PA), smart farms, and Agriculture 4.0, have demanded navigation technologies able to provide more accurate positioning at a low cost, especially for vehicle guidance and variable rate technology purposes. The Society of Automotive Engineers (SAE), for instance, through its standard J2945 defines a maximum of 1.5 m of horizontal positioning error at 68% probability (1σ), aiming at terrestrial vehicle-to-vehicle (V2V) applications. GPS position accuracy may be improved by addressing the common-mode errors contained in its observables, and relative GNSS (RGNSS) is a well-known technique for overcoming this issue. This paper builds upon previous research conducted by the authors and investigates the sensitivity of the position estimation accuracy of low-cost receiver-equipped agricultural rovers as a function of two degradation factors that RGNSS is susceptible to: communication failures and baseline distances between GPS receivers. The extended Kalman filter (EKF) approach is used for position estimation, based on which we show that it is possible to achieve 1.5 m horizontal accuracy at 68% probability (1σ) for communication failures up to 3000 s and baseline separation of around 1500 km. Experimental data from the Brazilian Network for Continuous Monitoring of GNSS (RBMC) and a moving agricultural rover equipped with a low-cost GPS receiver are used to validate the analysis.

The Advantages and Limitations of Low-Cost Single Frequency GPS/MEMS-Based INS Integration

Global Positioning System (GPS) provides a method for directly obtaining instantaneous position and velocity estimates using satellites-based passive range measurements. GPS is a whole day, all-weather, passive, satellite positioning system. Inertial Navigation System (INS) is a navigation aid system that uses a computer and Inertial Measurement Unite (IMU). IMU includes motion sensors and rotation sensors to continuously calculate relative position, orientation, and velocity. The integration of GPS/INS can help to overcome the limitations of the two systems providing integrated system better than either on a stand-alone basis. The integration of low-cost INS with dual frequency GPS has been widely studied and the same for the integration of tactical grid INS with low-cost GPS. However, during the last a few years, a number of low-cost GPS\low-cost INS integrated systems have been introduced and become popular in various engineering applications. However, reliable investigations into the advantages, limitations and quality of such integration level are still needed and more efforts are required, which will be the focus of this paper. The methodology followed in this paper for evaluating the integration of low-cost GPS/INS sensors depends on evaluating the two sensors individually and comparing the results with the integrated system. The results show that low-cost single frequency GPS receivers are able to provide a comparable accuracy level in both static and kinematic carrier phase differential GPS (DGPS). As for low-cost Micro-Electro-Mechanical System (MEMS)-based IMU, the accelerometers have provided instability comparing to gyros. The performance of gyros can be improved based on modelling the nearly-linear behaviour of the gyro drift. Tests show that the integration of low-cost GPS sensors with MEMS-based INS degrades the quality of gyro measurements and may not add any improvements to the quality of the individual GPS positioning.

Evaluating Two Low-Cost GPS Receivers for Accuracy and Eventual Use in Pastured Cattle Research

HighlightsA stand-alone GPS receiver produced comparably lower location errors than a smartphone GPS.Low-cost GPS receivers are suitable for use in research on large-herd cattle behavioral response to UAVs.Different testing placements can influence the horizontal accuracy of low-cost GPS receivers and smartphones.Abstract. Using animal-borne global positioning system (GPS) collars, cattle behavioral response to anthropogenic disturbances can be accurately quantified at fine scale. However, the use of dedicated commercial GPS collars in large herd studies is cost-prohibitive. Therefore, low-cost GPS receiver alternatives were evaluated in static placements to determine how their accuracy compares to published data for commercial animal-borne GPS collars. The static accuracies of identical low-cost stand-alone GPS receivers and smartphones were evaluated in an open field without obstructions, under trees with and without canopy, and near an electric fence at 5 min and 1 s sample intervals. The mean circular error probable (CEP) value of the stand-alone GPS receiver was =2 m at 5 min and at 1 s in open field placement. The mean CEP value of the stand-alone GPS receiver was =3 m at 5 min and at 1 s when placed near the electric fence. The smartphone produced mean CEP values of =4 m at 5 min and =3 m at 1 s for the fence line and open field placements. Static testing under trees with canopy at the 5 min sample interval produced mean CEP values 100% greater than under trees without canopy at the 1 s sample interval. Low-cost commercial GPS receivers and smartphones with horizontal accuracy of =5 m at high sample resolution may offer accurate means of quantifying the behavioral response of cattle to UAVs in large herd studies. Keywords: Cattle behavior, Global positioning system, Horizontal accuracy, Smartphone GPS, Stand-alone GPS receiver, UAV, Unmanned aerial vehicle.

Comparative Appraisal of Three Low-Cost GPS Speed Sensors with Different Data Update Frequencies

Low-cost GPS (Global Positioning System) speed sensors have been available to quantify vehicle speed on different platforms including agricultural tractors in precision agriculture applications such as yield monitoring, variable rate fertilizer and pesticide applications. One of the advances in low-cost GPS receivers is the higher data update frequencies. However, we found no studies on the accuracy of low-cost GPS speed sensors with different update frequencies, especially under variable speed conditions. Thus, this work investigated the effect of the update frequency on the accuracy of low-cost GPS speed sensors under both constant and varying speed conditions. Three GPS speed sensors with update frequencies of 1 Hz, 5 Hz and 7 Hz (GPS1Hz, GPS5Hz and GPS7Hz) were simultaneously tested under the same conditions. A total of 144 tests were conducted on three different days and at three different times of each day with four speed levels and four repetitions. The percent errors were found to be up to 2.3%, 1.8% and 1.4% at constant speeds; up to −47%, −16% and −12% at the increasing speeds and 24%, 6% and 5% at the decreasing speeds, depending on the acceleration and deceleration levels, for GPS1Hz, GPS5Hz and GPS7Hz, respectively. The differences among the error values of the GPS speed sensors were found to be statistically significant (p < 0.05). The GPS speed sensors with higher update frequencies (5 and 7 Hz) provided higher accuracy compared to the one with lower frequency (1 Hz), particularly in the case of higher acceleration conditions. In sum, low-cost GPS speed sensors with higher update frequencies should be used for better accuracy, especially in variable speed conditions.

A Low-Cost, High-Precision Vehicle Navigation System for Deep Urban Multipath Environment Using TDCP Measurements.

In this study, we developed a low-cost, high-precision vehicle navigation system for deep urban multipath environments using time-differenced carrier phase (TDCP) measurements. Although many studies are being conducted to navigate autonomous vehicles using the global positioning system (GPS), it is difficult to obtain accurate navigation solutions due to multipath errors in urban environments. Low-cost GPS receivers that determine the solution based on pseudorange measurements are vulnerable to multipath errors. We used carrier phase measurements that are more robust for multipath errors. Without correction information from reference stations, the limited information of a low-cost, single-frequency receiver makes it difficult to quickly and accurately determine integer ambiguity of carrier phase measurements. We used TDCP measurements to eliminate the need to determine integer ambiguity that is time-invariant and we combined TDCP-based GPS with an inertial navigation system to overcome deep urban multipath environments. Furthermore, we considered a cycle slip algorithm for its accuracy and a multi-constellation navigation system for its availability. The results of dynamic field tests in a deep urban area indicated that it could achieve horizontal accuracy of at the submeter level.

An Enhanced Map-Matching Algorithm for Real-Time Position Accuracy Improvement with a Low-Cost GPS Receiver.

This paper proposes a real-time position accuracy improvement method for a low-cost global positioning system (GPS), which uses geographic data for forming a digital road database in the digital map information. We link the vehicle’s location to the position on the digital map using the map-matching algorithm to improve the position accuracy. In the proposed method, we can distinguish the vehicle direction on the road and enhance the horizontal accuracy using the geographic data composed of the vector point set of the digital map. We use the iterative closest point (ICP) algorithm that calculates the rotation matrix and the translation vector to compensate for the disparity between the GPS and the digital map information. We also use the least squares method to correct the error caused by the rotation of the ICP algorithm and link on the digital map to eliminate the residual disparity. Finally, we implement the proposed method in real time with a low-cost embedded system and demonstrate the effectiveness of the proposed method through various experiments.

Investigations into the Integration of Low-Cost GPS/INS Sensors


 
 
 
 Global Positioning System (GPS) provides a method for directly obtaining instantaneous position and velocity estimates using satellites based passive range measurements. GPS is a whole day, all weather, passive, satellite-positioning system. Inertial Navigation System (INS) is a navigation aid system that uses a computer, Inertial Measurement Unite (IMU) that include motion sensors and rotation sensors to continuously calculate the position, orientation, and velocity relative to a known starting point. The integration of GPS/INS can help to overcome the limitations of the two systems providing integrated system better than either on a stand-alone basis. The integration of low-cost INS with dual frequency GPS has been widely studied and the same for the integration of tactical grid INS with low-cost GPS. However, during the last a few years, a number of low-cost GPS\low-cost INS integrated system have been introduced and become more and more common. For such integration level to be used in engineering applications, reliable investigations into the advantages and limitations are still needed and more efforts are required, which will be the focus of this paper.
 
 
 
 
 The methodology followed in this paper for evaluating the integration of low-cost GPS/INS sensors depends on evaluating the two sensors individually and comparing the results with those of the integrated system. The results show that low-cost single frequency GPS receivers are able to provide a comparable accuracy level in both static and kinematic carrier phase differential GPS(DGPS). As for low-cost Micro-Electro-Mechanical System (MEMS) based IMU, the accelerometers have provided instability comparing to gyros. The performance of gyros can be improved based on modelling the linear behaviour of the gyro drift. Tests show that such integration level degrades the precision of the gyro measurements and may not add any improvements to the quality of the individual GPS positioning.

Low-Cost GPS Receivers for the Monitoring of Sunflower Cover Dynamics

The aim of this research is to analyze the potential use of Global Navigation Satellite System (GNSS) signals for the monitoring of in situ vegetation characteristics. An instrument, based on the use of a pair of low-cost receivers and antennas, providing continuous measurements of all the available Global Positioning System (GPS) satellite signals is proposed for the determination of signal attenuation caused by a sunflower cover. Experimental campaigns with this instrument, combined with ground truth measurements of the vegetation, were performed over a nonirrigated sunflower test field for a period of more than two months, corresponding to a significant portion of the vegetation cycle. A method is proposed for the analysis of the signal attenuation data as a function of elevation and azimuth angles. A high correlation is observed between the vegetation’s water content and the GPS signals attenuation, and an empirical modeling is tested for the retrieval of signal behavior as a function of vegetation water content (VWC). The VWC was estimated from GNSS signals on a daily basis, over the full length of the study period.

High-Precision Vehicle Navigation in Urban Environments Using an MEM's IMU and Single-Frequency GPS Receiver

Many applications demand high-precision navigation in urban environments. Two frequency real-time kinematic (RTK) Global Positioning System (GPS) receivers are too expensive for low-cost or consumer-grade projects. As single-frequency GPS receivers are getting less expensive and more capable, more people are utilizing single-frequency RTK GPS techniques to achieve high accuracy in such applications. However, compared with dual-frequency receivers, it is much more difficult to resolve the integer ambiguity vector using single-frequency phase measurements and therefore more difficult to achieve reliable high-precision navigation. This paper presents a real-time sliding-window estimator that tightly integrates differential GPS and an inertial measurement unit to achieve reliable high-precision navigation performance in GPS-challenged urban environments using low-cost single-frequency GPS receivers. Moreover, this paper proposes a novel method to utilize the phase measurements, without resolving the integer ambiguity vector. Experimental results demonstrate real-time position estimation performance at the decimeter level. Furthermore, the novel use of phase measurements improves the robustness of the estimator to pseudorange multipath error.

Accuracy of a low-cost global positioning system receiver for estimating grade during outdoor walking

The aim of this study was to assess, for the first time, the accuracy of a low-cost global positioning system (GPS) receiver for estimating grade during outdoor walking.Thirty subjects completed outdoor walks (2.0, 3.5 and 5.0 km · h−1) in three randomized conditions: 1/level walking on a 0.0% grade; 2/graded (uphill and downhill) walking on a 3.4% grade; and 3/on a 10.4% grade. Subjects were equipped with a GPS receiver (DG100, GlobalSat Technology Corp., Taiwan; ~US$75). The GPS receiver was set to record at 1 Hz and its antenna was placed on the right shoulder. Grade was calculated from GPS speed and altitude data (grade = altitude variation/travelled distance × 100). Two methods were used for the grade calculation: one using uncorrected altitude data given by the GPS receiver and another one using corrected altitude data obtained using map projection software (CartoExploreur, version 3.11.0, build 2.6.6.22, Bayo Ltd, Appoigny, France, ~US$35). Linear regression of GPS-estimated versus actual grade with R2 coefficients, bias with 95% limits of agreement (±95% LoA), and typical error of the estimate with 95% confidence interval (TEE (95% CI)) were computed to assess the accuracy of the GPS receiver.444 walking periods were performed. Using uncorrected altitude data, we obtained: R2 = 0.88 (p < 0.001), bias = 0.0 ± 6.6%, TEE between 1.9 (1.7–2.2)% and 4.2 (3.6–4.9)% according to the grade level. Using corrected altitude data, we obtained: R2 = 0.98 (p < 0.001), bias = 0.2 ± 1.9%, TEE between 0.2 (0.2–0.3)% and 1.0 (0.9–1.2)% according to the grade level.The low-cost GPS receiver used was weakly accurate for estimating grade during outdoor walking when using uncorrected altitude data. However, the accuracy was greatly improved when using corrected altitude data. This study supports the potential interest of using GPS for estimating energy expenditure during outdoor walking.

Predicting metabolic rate during level and uphill outdoor walking using a low-cost GPS receiver.

The objective of this study was to assess the accuracy of using speed and grade data obtained from a low-cost global positioning system (GPS) receiver to estimate metabolic rate (MR) during level and uphill outdoor walking. Thirty young, healthy adults performed randomized outdoor walking for 6-min periods at 2.0, 3.5, and 5.0 km/h and on three different grades: 1) level walking, 2) uphill walking on a 3.7% mean grade, and 3) uphill walking on a 10.8% mean grade. The reference MR [metabolic equivalents (METs) and oxygen uptake (V̇o2)] values were obtained using a portable metabolic system. The speed and grade were obtained using a low-cost GPS receiver (1-Hz recording). The GPS grade (Δ altitude/distance walked) was calculated using both uncorrected GPS altitude data and GPS altitude data corrected with map projection software. The accuracy of predictions using reference speed and grade (actual[SPEED/GRADE]) data was high [R(2) = 0.85, root-mean-square error (RMSE) = 0.68 MET]. The accuracy decreased when GPS speed and uncorrected grade (GPS[UNCORRECTED]) data were used, although it remained substantial (R(2) = 0.66, RMSE = 1.00 MET). The accuracy was greatly improved when the GPS speed and corrected grade (GPS[CORRECTED]) data were used (R(2) = 0.82, RMSE = 0.79 MET). Published predictive equations for walking MR were also cross-validated using actual or GPS speed and grade data when appropriate. The prediction accuracy was very close when either actual[SPEED/GRADE] values or GPS[CORRECTED] values (for level and uphill combined) or GPS speed values (for level walking only) were used. These results offer promising research and clinical applications related to the assessment of energy expenditure during free-living walking.

Performance of two low-cost GPS receivers for ground speed measurement under varying speed conditions

A global positioning system (GPS) receiver is an important sensor used in modern farming, particularly in precision agriculture to determine geographic location and ground speed. The aim of this study was to investigate the effectiveness of two low-cost GPS receivers for measuring ground speed under varying speed conditions on four different dates. A rotary shaft encoder on an auxiliary wheel mounted on an agricultural tractor was used as a reference. A significant time lag between the rotary encoder speed and the GPS speed was found over a range of speeds. It was observed that the GPS speed lagged the encoder speed in both increasing and decreasing speeds. The average time lag was found to be between 3.6 and 5.2 s for Receiver 1 while Receiver 2 had a time lag from 1.7 to 2.5 s. A significant difference was found between the two receivers for increasing and decreasing speeds in terms of time lags (P < 0.05). A post correction by shifting the GPS speed increased the accuracy of the speed measurement capability of both receivers resulting in an average correlation coefficient of 0.30–0.90 for Receiver 1 and 0.65–0.98 for Receiver 2. Effect of USB-to-COM converter was also studied and it did not have a significant effect on time delay. The GPS receivers provided reliable data during constant speed operating conditions; however, caution should be exercised in varying speed conditions when using low-cost GPS receivers. Also, the companies that produce GPS-based speed sensors should supply technical specifications related to velocity estimates during acceleration and deceleration.

Experimental Study on Low-Cost Satellite-Based Geodetic Monitoring over Short Baselines

The use of geodetic techniques, in particular of the global positioning system (GPS), or other global navigation satellite systems (GNSS), for monitoring different kinds of deformations is a common practice. This is typically performed by setting a network of geodetic GPS/GNSS receivers, allowing accuracies in the order of millimeters. The use of lower-cost devices has been recently studied, showing that good results can be achieved. In this paper, the impact of the software used for the data analysis is also investigated to verify whether a fully low-cost monitoring system, i.e., both hardware and software, can be set up. This is done by performing a series of relative positioning experiments in which data are processed by different software packages. The main result is that by using a low-cost u-blox EVK-6T GPS receiver and analyzing its data with free and open-source software, movements of the order of a few millimeters can be detected when a short baseline with daily solutions is used.

Retrieving real-time precise co-seismic displacements with a standalone single-frequency GPS receiver

Nowadays, Global Positioning System (GPS) plays an increasingly important role in retrieving real-time precise co-seismic displacements for geo-hazard monitoring and early warning. Several real-time positioning approaches have been demonstrated for such purpose, such as real-time kinematic relative positioning, precise point positioning, etc., where dual-frequency geodetic receivers are applied for the removal of ionosphere delays by inter-frequency combination. At the same time, it would be also useful to develop efficient algorithms for estimating precise displacements with low-cost GPS receivers since they can make a denser network or multi-sensors combination without putting too much financial burden. In this contribution, we present a new method to retrieve precise co-seismic displacements in real-time using a standalone single-frequency receiver. In the new method, observations prior to an earthquake are utilized to establish a precise ionospheric delay prediction model, so that precise co-seismic displacements can be obtained without any convergence process. Our method was validated with an outdoor experiment as well as by re-processing of 1-Hz GPS data collected by the GEONET network during the 2011 Tohoku Mw 9.0 earthquake. For the latter, RMS against dual-frequency receivers constituted 2cm for horizontal components and 3cm for the vertical component.We specially address the observation biases and their impact on the accuracy of single frequency positioning. Our approach makes real-time GPS displacement monitoring with dense network much more affordable in terms of financial costs.

Navigation of mobile robot using Low-cost GPS

A method of fusing data from a Global Positioning System (GPS) and a Dead Reckoning (DR) system for outdoor navigation of a Wheeled Mobile Robot (WMR) is proposed. The low-cost GPS receiver cannot be utilized by itself for navigating the mobile robot. Since, it produces an error of approximately 10–20 meters. DR can provide precise navigation data to the mobile robot but its errors accumulate over time. Since, all the previous data are utilized to calculate the current position information. DR needs to be complemented by other navigation sensors to navigate the mobile robot. The proposed GPS/DR data fusion method is based on the characteristics of the single GPS receiver output. The fused data provides accurate and robust navigation information to the outdoor mobile robot. Simulations were conducted using real GPS data which were then compared with the results using a Kalman filter that verified the potential of the proposed GPS/DR data fusion method.

A performance improvement method for low-cost land vehicle GPS/MEMS-INS attitude determination.

Global positioning system (GPS) technology is well suited for attitude determination. However, in land vehicle application, low-cost single frequency GPS receivers which have low measurement quality are often used, and external factors such as multipath and low satellite visibility in the densely built-up urban environment further degrade the quality of the GPS measurements. Due to the low-quality receivers used and the challenging urban environment, the success rate of the single epoch ambiguity resolution for dynamic attitude determination is usually quite low. In this paper, a micro-electro-mechanical system (MEMS)—inertial navigation system (INS)-aided ambiguity resolution method is proposed to improve the GPS attitude determination performance, which is particularly suitable for land vehicle attitude determination. First, the INS calculated baseline vector is augmented with the GPS carrier phase and code measurements. This improves the ambiguity dilution of precision (ADOP), resulting in better quality of the unconstrained float solution. Second, the undesirable float solutions caused by large measurement errors are further filtered and replaced using the INS-aided ambiguity function method (AFM). The fixed solutions are then obtained by the constrained least squares ambiguity decorrelation (CLAMBDA) algorithm. Finally, the GPS/MEMS-INS integration is realized by the use of a Kalman filter. Theoretical analysis of the ADOP is given and experimental results demonstrate that our proposed method can significantly improve the quality of the float ambiguity solution, leading to high success rate and better accuracy of attitude determination.

Measuring snow liquid water content with low-cost GPS receivers.

The amount of liquid water in snow characterizes the wetness of a snowpack. Its temporal evolution plays an important role for wet-snow avalanche prediction, as well as the onset of meltwater release and water availability estimations within a river basin. However, it is still a challenge and a not yet satisfyingly solved issue to measure the liquid water content (LWC) in snow with conventional in situ and remote sensing techniques. We propose a new approach based on the attenuation of microwave radiation in the L-band emitted by the satellites of the Global Positioning System (GPS). For this purpose, we performed a continuous low-cost GPS measurement experiment at the Weissfluhjoch test site in Switzerland, during the snow melt period in 2013. As a measure of signal strength, we analyzed the carrier-to-noise power density ratio (C/N0) and developed a procedure to normalize these data. The bulk volumetric LWC was determined based on assumptions for attenuation, reflection and refraction of radiation in wet snow. The onset of melt, as well as daily melt-freeze cycles were clearly detected. The temporal evolution of the LWC was closely related to the meteorological and snow-hydrological data. Due to its non-destructive setup, its cost-efficiency and global availability, this approach has the potential to be implemented in distributed sensor networks for avalanche prediction or basin-wide melt onset measurements.

A Pedestrian Dead Reckoning System Integrating Low - Cost MEMS Inertial Sensors and GPS Receiver

The body-mounted inertial systems for pedestrian navigation do not require any preinstalled facilities and can run autonomously. The advantages over other technologies make it especially attractive for the applications such as first responders, military and consumer markets. The hardware platform integrating the low-cost, low-power and small-size MEMS (micro-electro-mechanical systems) inertial sensors and GPS (global positioning system) receiver is proposed. When the satellite signals are available, the location of the pedestrian is directly obtained from the GPS receiver. The inertial sensors are the complement of the GPS receiver in places where the GPS signals are not available, such as indoors, urban canyons and places under dense foliages. The height tracking is achieved by the barometer. The proposed PDR (pedestrian dead reckoning) algorithm is real-timely implemented in the platform. The simple but effective step detection and step length estimation method are realized to reduce the computation and memory requirements on the microprocessor. A complementary filter is proposed to fuse the data from the accelerometer, gyroscope and digital compass for decreasing the heading error, which is the main error source in positioning. The reliability and accuracy of the proposed system is verified by field pedestrian walking tests in outdoors and indoors. The positioning error is less than 4% of the total traveled distance. The results indicate that the pedestrian dead reckoning system is able to provide satisfactory tracking performance.

Improving RTDGPS accuracy using hybrid PSOSVM prediction model

Users of Global Positioning System (GPS) require more accuracy from positioning service of this system. Accurate and real time positioning is realized through implementing Real Time Differential GPS (RTDGPS). Accuracy of this system depends on successive and punctual transmission of Pseudo Range Corrections (PRCs) from Reference Station (RS) to user station. Corrections are transmitted using Radio Technical Commission for Maritime services (RTCM) protocol. To compensate signal absence and transmission delay of differential corrections which is created while transferring, processing and reception, a hybrid prediction algorithm combined of Support Vector Machine (SVM) and Particle Swarm Optimization (PSO) has been implemented in RS. Corrections are predicted using SVM while, PSO is used for determination and optimization of the basic parameters in SVM algorithm. A Low Cost GPS receiver is used in RS. Prediction time step was five seconds. Simulation results show that the total Root Mean Square (RMS) prediction error for PSOSVM is less than 0.126 m for one step ahead and 0.46 m for 10 step ahead predictions. Experimental results indicate that by employing PSOSVM, accuracy of RTDGPS has been improved.

Enhanced, Delay Dependent, Intelligent Fusion for INS/GPS Navigation System

Low-cost navigation systems, deployed for ground vehicles' applications, are designed based on the loosely coupled fusion between the global positioning system (GPS) and the inertial measurement unit (IMU). However, low-cost GPS receivers provide the position and velocity of the vehicle at a lower sampling rate than the IMU-sampled vehicle dynamics. In addition, the GPS measurements might be missed or delayed due to the receiver's inability to lock on the signal or due to obstruction from neighboring vehicles or infrastructures. In this paper, an architecture based on an adaptive neuro-fuzzy inference system is proposed for fusing the GPS/IMU measurements. This integration incorporates the variable delay between the IMU and GPS signals as an additional input to the fusion system. In addition, once the GPS signal becomes available, the measurement is used as a correction reference value to provide an enhancement to the estimation accuracy. The performance of the proposed method is initially demonstrated using a GPS/IMU simulation environment. Subsequently, an experimental test is also conducted to validate the performance of the method.