Showing papers on "GPS/INS published in 2012"

Accurate Pedestrian Indoor Navigation by Tightly Coupling Foot-Mounted IMU and RFID Measurements

Abstract: We present a new method to accurately locate persons indoors by fusing inertial navigation system (INS) techniques with active RFID technology. A foot-mounted inertial measuring units (IMUs)-based position estimation method, is aided by the received signal strengths (RSSs) obtained from several active RFID tags placed at known locations in a building. In contrast to other authors that integrate IMUs and RSS with a loose Kalman filter (KF)-based coupling (by using the residuals of inertial- and RSS-calculated positions), we present a tight KF-based INS/RFID integration, using the residuals between the INS-predicted reader-to-tag ranges and the ranges derived from a generic RSS path-loss model. Our approach also includes other drift reduction methods such as zero velocity updates (ZUPTs) at foot stance detections, zero angular-rate updates (ZARUs) when the user is motionless, and heading corrections using magnetometers. A complementary extended Kalman filter (EKF), throughout its 15-element error state vector, compensates the position, velocity and attitude errors of the INS solution, as well as IMU biases. This methodology is valid for any kind of motion (forward, lateral or backward walk, at different speeds), and does not require an offline calibration for the user gait. The integrated INS+RFID methodology eliminates the typical drift of IMU-alone solutions (approximately 1% of the total traveled distance), resulting in typical positioning errors along the walking path (no matter its length) of approximately 1.5 m.

Faster GPS via the sparse fourier transform

Abstract: GPS is one of the most widely used wireless systems. A GPS receiver has to lock on the satellite signals to calculate its position. The process of locking on the satellites is quite costly and requires hundreds of millions of hardware multiplications, leading to high power consumption. The fastest known algorithm for this problem is based on the Fourier transform and has a complexity of O(n log n), where n is the number of signal samples. This paper presents the fastest GPS locking algorithm to date. The algorithm reduces the locking complexity to O(n√(log n)). Further, if the SNR is above a threshold, the algorithm becomes linear, i.e., O(n). Our algorithm builds on recent developments in the growing area of sparse recovery. It exploits the sparse nature of the synchronization problem, where only the correct alignment between the received GPS signal and the satellite code causes their cross-correlation to spike.We further show that the theoretical gain translates into empirical gains for GPS receivers. Specifically, we built a prototype of the design using software radios and tested it on two GPS data sets collected in the US and Europe. The results show that the new algorithm reduces the median number of multiplications by 2.2x in comparison to the state of the art design, for real GPS signals.

INS/GPS Integration System using Adaptive Filter for Estimating Measurement Noise Variance

Abstract: The inertial navigation system (INS)/GPS integration system is designed by employing an adaptive filter that can estimate measurement noise variance using the residual of the measurement To verify the efficiency of the proposed loosely-coupled INS/GPS integration system, simulations were performed by assuming that GPS information has large position errors The simulation results show that the proposed integration system with the adaptive filter is more effective in estimating the position and attitude errors than a system that uses the extended Kalman filter

Error compensation of an optical gyro INS by multi-axis rotation

Abstract: IMU rotation of an inertial navigation system (INS) can bound the free propagation of the INS error introduced by the drifts of inertial sensors. The rotation scheme of the IMU will directly affect the accuracy, structure and costs of the system. A reasonable rotation scheme should remove most of the system errors arising from the drifts of the inertial sensors, and at the same time, should not introduce other additional errors. First, this paper discusses the design and analysis approach of the rotation scheme based on the error propagation equations of the INS. Then, a conventional 8-position rotation scheme is analyzed for the applications of the optical gyro INS, and its drawbacks are discussed in detail. Following these, an improved 8-position rotation scheme and a novel 16-position rotation scheme are proposed for the optical gyro INS, and their merits are also discussed. Simulation results have shown that the 16-position rotation scheme, which can compensate not only the drifts but also the scale factor errors and the misalignment errors of the inertial sensors, is the best rotation scheme and can be used as a practical solution to compensate the drifts of the inertial sensors in the rotational INS.

Flight-Test Evaluation of Sensor Fusion Algorithms for Attitude Estimation

Abstract: In this paper, several Global Positioning System/inertial navigation system (GPS/INS) algorithms are presented using both extended Kalman filter (EKF) and unscented Kalman filter (UKF), and evaluated with respect to performance and complexity. The contributions of this study are that attitude estimates are compared with independent measurements provided by a mechanical vertical gyroscope using 23 diverse sets of flight data, and that a fundamental difference between EKF and UKF with respect to linearization is evaluated.

Direct georeferencing with on board navigation components of light weight uav platforms

Abstract: . Unmanned aerial vehicles (UAV) are a promising platform for close range airborne photogrammetry. Next to the possibility of carrying certain sensor equipment, different on board navigation components may be integrated. These devices are getting, due to recent developments in the field of electronics, smaller and smaller and are easily affordable. Therefore, UAV platforms are nowadays often equipped with several navigation devices in order to support the remote control of a UAV. Furthermore, these devices allow an automated flight mode that allows to systematically sense a certain area or object of interest. However, next to their support for the UAV navigation they allow the direct georeferencing of synchronised sensor data. This paper introduces the direct georeferencing of airborne UAV images with a low cost solution based on a quadrocopter. The system is equipped with a Global Navigation Satellite System (GNSS), an Inertial Measurement Unit (IMU), an air pressure sensor, a magnetometer, and a small compact camera. A challenge using light weight consumer-grade sensors is the acquisition of high quality images with respect to brightness and sharpness. It is demonstrated that an appropriate solution for data synchronisation and data processing allows a direct georeferencing of the acquired images with a precision below 1m in each coordinate. The precision for roll and pitch is below 1° and for the yaw it is 2.5°. The evaluation is based on image positions estimated based on the on board sensors and compared to an independent bundle block adjustment of the images.

Integrated GPS/INS navigation system with dual-rate Kalman Filter

Abstract: A dual-rate Kalman Filter (DRKF) has been developed to integrate the time-differenced GPS carrier phases and the GPS pseudoranges with INS measurements. The time-differenced GPS carrier phases, which have low noise and millimeter measurement precision, are integrated with INS measurements using a Kalman Filter with high update rates to improve the performance of the integrated system. Since the time-differenced GPS carrier phases are only relative measurements, when integrated with INS, the position error of the integrated system will accumulate over time. Therefore, the GPS pseudoranges are also incorporated into the integrated system using a Kalman Filter with a low update rate to control the accumulation of system errors. Experimental tests have shown that this design, compared to a conventional design using a single Kalman Filter, reduces the coasting error by two-thirds for a medium coasting time of 30 s, and the position, velocity, and attitude errors by at least one-half for a 45-min field navigation experiment.

Inertial Aided Cycle Slip Detection and Identification for Integrated PPP GPS and INS

Abstract: The recently developed integrated Precise Point Positioning (PPP) GPS/INS system can be useful to many applications, such as UAV navigation systems, land vehicle/machine automation and mobile mapping systems. Since carrier phase measurements are the primary observables in PPP GPS, cycle slips, which often occur due to high dynamics, signal obstructions and low satellite elevation, must be detected and repaired in order to ensure the navigation performance. In this research, a new algorithm of cycle slip detection and identification has been developed. With the aiding from INS, the proposed method jointly uses WL and EWL phase combinations to uniquely determine cycle slips in the L1 and L2 frequencies. To verify the efficiency of the algorithm, both tactical-grade and consumer-grade IMUs are tested by using a real dataset collected from two field tests. The results indicate that the proposed algorithm can efficiently detect and identify the cycle slips and subsequently improve the navigation performance of the integrated system.

An in situ hand calibration method using a pseudo-observation scheme for low-end inertial measurement units

Abstract: MEMS chips have become ideal candidates for various applications since they are small sized, light weight, have low power consumption and are extremely low cost and reliable. However, the performance of MEMS sensors, especially their biases and scale factors, is highly dependent on environmental conditions such as temperature. Thus a quick and convenient calibration is needed to be conducted by users in field without any external equipment or any expert knowledge of calibration. A novel and efficient in situ hand calibration method is presented to meet these demands in this paper. The algorithm of the proposed calibration method makes use of the navigation algorithm of the loosely-coupled GPS/INS integrated systems, but replaces the GPS observations with a kind of pseudo-observations, which can be stated as follows: if an inertial measurement unit (IMU) was rotating approximately around its measurement center, the range of its position and its linear velocity both would be within a limited scope. Using a Kalman filtering algorithm, the biases and scale factors of both accelerometer triad and gyroscope triad can be calibrated together within a short period (about 30 s), requiring only motions by hands. Real test results show that the proposed method is suitable for most consumer grade MEMS IMUs due to its zero cost, easy operation and sufficient accuracy.

Attitude determination by integration of MEMS inertial sensors and GPS for autonomous agriculture applications

Abstract: Integration of Global Positioning System (GPS) and Inertial Navigation System (INS) technologies, which has widespread usage in industry, is also regarded as an ideal solution for automated agriculture because it fulfils the accuracy, reliability and availability requirements of industrial and agricultural applications. Agriculture applications use position, velocity and heading information for automated vehicle guidance and control to enhance the yield and quality of the crop, and in order to vary the application of fertilizer and herbicides according to soil heterogeneity at sub-field level. A loosely coupled GPS/INS integration algorithm known as "AhrsKf" is introduced for automated agriculture vehicle guidance and control utilizing MEMS inertial sensors and GPS. The AhrsKf can produce high-frequency attitude solutions for the vehicle's guidance and control system, by using inputs from a single survey grade L1/L2 antenna, eliminating the need for the previous two antenna solutions. Given its agricultural application, the AhrsKf has been implemented with some specific design features to improve the accuracy of the attitude solution including, temperature compensation of the inertial sensors, and the aid of plough lines of farm lands. To evaluate the AhrsKf solution, two benchmarking tests have been conducted by using a three-antenna GPS system and NovAtel's SPAN-CPT. The results have demonstrated that the AhrsKf solution is stable and can correctly track the movement of the farming vehicle.

Performance Analysis of Constrained Loosely Coupled GPS/INS Integration Solutions

Abstract: The paper investigates approaches for loosely coupled GPS/INS integration. Error performance is calculated using a reference trajectory. A performance improvement can be obtained by exploiting additional map information (for example, a road boundary). A constrained solution has been developed and its performance compared with an unconstrained one. The case of GPS outages is also investigated showing how a Kalman filter that operates on the last received GPS position and velocity measurements provides a performance benefit. Results are obtained by means of simulation studies and real data.

Multi-stage approach to travel-mode segmentation and classification of gps traces

Abstract: . This paper presents a multi-stage approach toward the robust classification of travel-modes from GPS traces. Due to the fact that GPS traces are often composed of more than one travel-mode, they are segmented to find sub-traces characterized as an individual travel-mode. This is conducted by finding individual movement segments by identifying stops. In the first stage of classification three main travel-mode classes are identified: pedestrian, bicycle, and motorized vehicles; this is achieved based on the identified segments using speed, acceleration and heading related parameters. Then, segments are linked up to form sub-traces of individual travel-mode. After the first stage is achieved, a breakdown classification of the motorized vehicles class is implemented based on sub-traces of individual travel-mode of cars, buses, trams and trains using Support Vector Machines (SVMs) method. This paper presents a qualitative classification of travel-modes, thus introducing new robust and precise capabilities for the problem at hand.

Direct georeferencing of uavs

Abstract: UAV systems have become an attractive data acquisition platform in emerging applications. As measuring instrument they extend the lineup of possible surveying methods in the field of geomatics. However, most of UAVs are equipped with low-cost navigation sensors such as GPS or INS, allowing a positioning accuracy of 3 to 5 m. As a result the acquired position- and orientation data fea- tures a low accuracy which implicates that it cannot be used in applications that require high precision data on cm-level (e.g. direct georeferencing). In this paper we will analyze the potential of differential post-processing of GPS data from UAV in order to im- prove the positioning accuracy for applications basing on direct georeferencing. Subsequently, the obtained results are compared and verified with a track of the octocopter carried out with a total station simultaneously to the GPS data acquisition. The results show that the differential post-processing essentially improved the accuracy of the Falcon position data. Thereby the average offset be- tween the data sets (GPS data, track) and the corresponding standard deviation is 0.82 m and 0.45 m, respectively. However, under ideal conditions it is even possible to improve this positioning accuracy to the cm-range. Furthermore, there are still several sources of error such as the offset between the GPS antenna of the Falcon 8 and the prism which is used for the track. Considering this fact there is further room for improvement regarding the here discussed positioning method.

Gps and mems hybrid location-detection architecture

Abstract: The present application describes a computer-implemented method and system for obtaining position information for a moving mobile device with increased accuracy and reduced power consumption The subject of the present application combines information from a GPS location sensor with information from MEMS devices such as an acceleration detector and a gyroscope using statistical analysis techniques such as a Kalman filter to estimate the location of the device with greater accuracy while using numerical methods such as the Newton-Raphson Method to minimize power consumption Minimizing power consumption is possible because GPS signals sampled at a lower rate can conserve power, while GPS sampled at a lower rate and working together with MEMS devices can achieve the same level of location prediction accuracy as a GPS alone sampled at a higher rate

A particle filter approach to indoor navigation using a foot mounted inertial navigation system and heuristic heading information

Abstract: Foot mounted inertial navigation is an effective method for obtaining high quality pedestrian navigation solutions from MEMS sensors. Zero-Velocity information from stationary periods in the step-cycle can be used to regularly correct position drift and update estimates of the inertial sensor biases, hence dramatically improving the navigation solution.

Vehicle navigator using a mixture particle filter for inertial sensors/odometer/map data/GPS integration

Abstract: The market for vehicular navigators boomed over the last few years. These navigators rely mainly on satellite based navigation systems such as the Global Positioning System (GPS) to assist drivers. Due to interruption or degradation in such systems in dense urban scenarios, they have to be augmented with other systems to achieve continuous and accurate vehicular navigation. GPS is integrated with low-cost micro-electro mechanical system (MEMS)-based inertial sensors. However, these sensors provide inadequate performance in degraded GPS environments because of their complex error characteristics that often lead to large position drift errors. This paper proposes a continuous and accurate solution integrating low-cost MEMS-based inertial sensors, the vehicle odometer, GPS, and map data from road networks. Despite the traditional inadequate performance of MEMS-based sensors in this problem, the performance is enhanced through: (i) a special combination of inertial sensors and odometer that has better performance for land vehicles than traditional solutions; (ii) The use of map information from road networks to constrain the positioning solution; (iii) The use of an advanced particle filtering (PF) technique to perform the integration, which work with nonlinear models and better modeling of inertial sensor errors, in addition to better integration with the map data. The performance of the proposed positioning system has been verified extensively on real road tests in downtown trajectories with degraded or totally denied GPS for long durations.

Error analysis and attitude observability of a monocular GPS/visual odometry integrated navigation filter

Abstract: In this paper, we present a method for the recovery of position and absolute attitude (including pitch, roll and yaw) using a novel fusion of monocular visual odometry and GPS measurements in a similar manner to a classic loosely coupled GPS/INS error state navigation filter. The proposed filter does not require additional restrictions or assumptions such as platform-specific dynamics, map matching, feature tracking, visual loop closing, gravity vector or additional sensors such as an inertial measurement unit or magnetic compass. An observability analysis of the proposed filter is performed, showing that the scale factor, position and attitude errors are fully observable under acceleration that is non-parallel to the velocity vector in the navigation frame. The observability properties of the proposed filter are demonstrated using numerical simulations. We conclude the article with an implementation of the proposed filter using real flight data collected from a Cessna 172 equipped with a downwards-looking camera and GPS, showing the feasibility of the algorithm in real-world conditions.

Augmented Kalman Filter and Map Matching for 3D RISS/GPS Integration for Land Vehicles

Abstract: Owing to their complimentary characteristics, global positioning system (GPS) and inertial navigation system (INS) are integrated, traditionally through Kalman filter (KF), to obtain improved navigational solution. To reduce the overall cost of the system, microelectromechanical system- (MEMS-) based INS is utilized. One of the approaches is to reduce the number of low-cost inertial sensors, decreasing their error contribution which leads to a reduced inertial sensor system (RISS). This paper uses KF to integrate GPS and 3D RISS in a loosely coupled fashion to enhance navigational solution while further improvement is achieved by augmenting it with map matching (MM). The 3D RISS consists of only one gyroscope and two accelerometers along with the vehicle’s built-in odometer. MM limits the error growth during GPS outages by restricting the predicted positions to the road networks. The performance of proposed method is compared with KF-only 3D RISS/GPS integration to demonstrate the efficacy of the proposed technique.

Miniature IMU/INS with optimally fused low drift MEMS gyro and accelerometers for applications in GPS-denied environments

Abstract: TAI's multi-sensor fusion technology is accelerating the development of accurate MEMS sensor-based inertial navigation in situations where GPS does not operate reliably (GPS-denied environments). TAI has demonstrated that one inertial device per axis is not sufficient to produce low drift errors for long term accuracy needed for GPS-denied applications. TAI's technology uses arrays of off-the-shelf MEMS inertial sensors to create an inertial measurement unit (IMU) suitable for inertial navigation systems (INS) that require only occasional GPS updates. Compared to fiber optics gyros, properly combined MEMS gyro arrays are lower cost, fit into smaller volume, use less power and have equal or better performance. The patents TAI holds address this development for both gyro and accelerometer arrays. Existing inertial measurement units based on such array combinations, the backbone of TAI's inertial navigation system (INS) design, have demonstrated approximately 100 times lower sensor drift error to support very accurate angular rates, very accurate position measurements, and very low angle error for long durations. TAI's newest, fourth generation, product occupies small volume, has low weight, and consumes little power. The complete assembly can be potted in a protective sheath to form a rugged standalone product. An external exoskeleton case protects the electronic assembly for munitions and UAV applications. TAI's IMU/INS will provide the user with accurate real-time navigation information in difficult situations where GPS is not reliable. The key to such accurate performance is to achieve low sensor drift errors. The INS responds to quick movements without introducing delays while sharply reducing sensor drift errors that result in significant navigation errors. Discussed in the paper are physical characteristics of the IMU, an overview of the system design, TAI's systematic approach to drift reduction and some early results of applying a sigma point Kalman filter to sustain low gyro drift.

Determination of the uav position by automatic processing of thermal images

Abstract: . If images acquired from Unmanned Aerial Vehicles (UAVs) need to be accurately geo-referenced, the method of choice is classical aerotriangulation, since on-board sensors are usually not accurate enough for direct geo-referencing. For several different applications it has recently been proposed to mount thermal cameras on UAVs. Compared to optical images, thermal ones pose a number of challenges, in particular low resolution and weak local contrast. In this work we investigate the automatic orientation of thermal image blocks acquired from a UAV, using artificial ground control points. To that end we adapt the photogrammetric processing pipeline to thermal imagery. The pipeline achieves accuracies of about ±1 cm in planimetry and ±3 cm in height for the object points, respectively ±10 cm or better for the camera positions, compared to ±100 cm or worse for direct geo-referencing using on-board single-frequency GPS.

On-Line Smoothing for an Integrated Navigation System with Low-Cost MEMS Inertial Sensors

Abstract: The integration of the Inertial Navigation System (INS) and the Global Positioning System (GPS) is widely applied to seamlessly determine the time-variable position and orientation parameters of a system for navigation and mobile mapping applications. For optimal data fusion, the Kalman filter (KF) is often used for real-time applications. Backward smoothing is considered an optimal post-processing procedure. However, in current INS/GPS integration schemes, the KF and smoothing techniques still have some limitations. This article reviews the principles and analyzes the limitations of these estimators. In addition, an on-line smoothing method that overcomes the limitations of previous algorithms is proposed. For verification, an INS/GPS integrated architecture is implemented using a low-cost micro-electro-mechanical systems inertial measurement unit and a single-frequency GPS receiver. GPS signal outages are included in the testing trajectories to evaluate the effectiveness of the proposed method in comparison to conventional schemes.

INS/Wi-Fi based indoor navigation using adaptive Kalman filtering and vehicle constraints

Abstract: Due to the complementary nature of inertial navigation system (INS) and Wi-Fi positioning principles, an INS/Wi-Fi integrated system is expected to form a low-cost and continuous indoor navigation solution with better performance than using the standalone systems. In this paper, we explore the integration of Wi-Fi measurements with data from microelectromechanical systems (MEMS) based inertial measurement unit (IMU) for indoor vehicle navigation. Two enhancements, which employ adaptive Kalman filtering (AKF) and vehicle constraints, for supporting the integrated system are presented. One field experiment has been conducted for estimating the trajectory of a mobile robot vehicle. The numerical results show that the enhanced integrated system provides higher navigation accuracy, compared to using standalone Wi-Fi positioning and conventional INS/Wi-Fi integration.

Sensitivity Analysis of a Tightly-Coupled GPS/INS System for Autonomous Navigation

Abstract: The work presented here empirically analyzes the design of the tightly-coupled position, velocity, and attitude estimator used as a feedback signal for autonomous navigation in a large scale robot driving in urban settings. The estimator fuses GNSS/INS signals in an extended square root information filter (ESRIF), a numerically-robust implementation of an extended Kalman filter (EKF), and was used as the basis for Cornell University's 2007 DARPA Urban Challenge robot, "Skynet." A statistical sensitivity analysis is conducted on Skynet's estimator by examining the changes in its behavior as critical design elements are removed. The effects of five design elements are considered: map aiding via computer vision algorithms, inclusion of differential corrections, filter integrity monitoring, Wide Area Augmentation System (WAAS) augmentation, and inclusion of carrier phases; the effects of extensive signal blackouts are also considered. Metrics of comparison include the statistical differences between the full solution and variant; the Kullback-Leibler divergence; and the average and standard deviation of the position errors, attitude errors, and filter update discontinuities.

Fusion of GPS and redundant IMU data for attitude estimation

Abstract: Attitude estimation using Global Positioning System/Inertial Navigation System (GPS/INS) was used as an example application to study three different methods of fusing redundant multi-sensor data used in the prediction stage of a nonlinear recursive filter. Experimental flight data were collected with an Unmanned Aerial Vehicle (UAV) containing GPS position and velocity calculations and four redundant Inertial Measurement Unit (IMU) sensors. Additionally, the aircraft roll and pitch angles were measured directly with a high-quality mechanical vertical gyroscope to be used as a ‘truth’ reference for evaluating attitude estimation performance. A simple formulation of GPS/INS sensor fusion using an Extended Kalman Filter (EKF) was used to calculate the results for this study. Each of the three presented fusion methods was shown to be effective in reducing the roll and pitch errors as compared to corresponding results using single IMU GPS/INS sensor fusion. Additionally, the fusion methods were shown to be effective in estimating roll and pitch angles without the aid of GPS (dead reckoning).

Performance of rate detector algorithms for an integrated GPS/INS system in the presence of slowly growing error

Abstract: In the Global Positioning System, there is no provision for real-time integrity information within the Standard Positioning Service, by design. However, in safety critical sectors like aviation, stringent integrity performance requirements must be met. This can be achieved using the special augmentation systems or RAIM (Receiver Autonomous Integrity Monitoring) or both. RAIM, the most cost-effective method relies on data consistency, and therefore requires redundant measurements for its operation. An external aid to provide this redundancy can be in the form of an Inertial Navigation system. This should enable continued performance even when no redundant satellite measurements are available. An algorithm presented in previous papers by the authors detects the rate of slowly growing errors. The algorithm was shown to be effective for early detection of slowly growing errors that belong to the class of most difficult to detect errors. Firstly, rate detector is tested for varying faults. Secondly, real data are used to validate the rate detector algorithm. The data are extensively analyzed to ascertain whether it is suitable for integrity and fault diagnostics. A modification to the original rate detector algorithm is suggested by addition of a bias state to the dynamic model. The performance is then compared with the existing techniques and substantial improvement is shown.

Using inertial sensors of iPhone 4 for car navigation

Abstract: Smart phones start to equip with MEMS tri-axis accelerometer (i.e. G-sensor) and tri-axis gyroscope chips in recent years for user interface (UI) and game playing purposes. These two sensors actually compose a complete IMU and might be qualified as an INS to aid the GPS positioning of the phones, i.e. a GPS/INS integrated navigation system can be implemented. This paper explores the idea of using the inertial sensors in iPhone 4 from Apple Inc. to make GPS/INS integration for car navigation. A loosely-coupled integrated navigation algorithm with 15-states Kalman filter was used to fuse the data from the GPS and the MEMS inertial sensors. The results of road tests have shown that the MEMS sensors can bridge the GPS position gaps effectively, and can provide attitude estimation at degree level accuracy. The non-holonomic constraint can improve the navigation performance significantly, including both the position and heading. The attitude accuracy can reach the level of 1.4 degrees for tilt, and 2.0 degrees for heading. During the GPS signal outages (e.g. tunnel cases), the position drifts of the MEMS INS are at the level of 30 meters after 30 seconds, with the non-holonomic constraint. Results of this paper proved that the inertial sensors of iPhone 4 can be used for car navigation purpose. They can provide enhanced positioning capability and decent attitude estimation for various applications.

A new source difference artificial neural network for enhanced positioning accuracy

Abstract: Integrated inertial navigation system (INS) and global positioning system (GPS) units provide reliable navigation solution compared to standalone INS or GPS. Traditional Kalman filter-based INS/GPS integration schemes have several inadequacies related to sensor error model and immunity to noise. Alternatively, multi-layer perceptron (MLP) neural networks with three layers have been implemented to improve the position accuracy of the integrated system. However, MLP neural networks show poor accuracy for low-cost INS because of the large inherent sensor errors. For the first time the paper demonstrates the use of knowledge-based source difference artificial neural network (SDANN) to improve navigation performance of low-cost sensor, with or without external aiding sources. Unlike the conventional MLP or artificial neural networks (ANN), the structure of SDANN consists of two MLP neural networks called the coarse model and the difference model. The coarse model learns the input–output data relationship whereas the difference model adds knowledge to the system and fine-tunes the coarse model output by learning the associated training or estimation error. Our proposed SDANN model illustrated a significant improvement in navigation accuracy of up to 81% over conventional MLP. The results demonstrate that the proposed SDANN method is effective for GPS/INS integration schemes using low-cost inertial sensors, with and without GPS.