• Journal of Positioning, Navigation, and Timing
• /
• v.13 no.2
• /
• pp.137-147
• /
• 2024

This paper presents a novel Long Short-Term Memory (LSTM) network architecture for the integration of an Inertial Measurement Unit (IMU) and Global Navigation Satellite Systems (GNSS). The proposed algorithm consists of two independent LSTM networks and the LSTM networks are trained to predict attitudes and velocities from the sequence of IMU measurements and mechanization solutions. In this paper, three GNSS receivers are used to provide Real Time Kinematic (RTK) GNSS attitude and position information of a vehicle, and the information is used as a target output while training the network. The performance of the proposed method was evaluated with both experimental and simulation data using a lowcost IMU and three RTK-GNSS receivers. The test results showed that the proposed LSTM network could improve positioning accuracy by more than 90% compared to the position solutions obtained using a conventional Kalman filter based IMU/GNSS integration for more than 30 seconds of GNSS outages.

• Proceedings of the KIEE Conference
• /
• 1999.07b
• /
• pp.822-825
• /
• 1999

This paper compares two methods of GPS/INS integration ; tightly-coupled integration ana loosely-coupled integration. In the tightly -coupled method an integrated Kalman filter is designed to process raw GPS measurement data for state update and INS data for propagation. The loosely-coupled integration method uses the solution outputs from a stand-alone GPS receiver for update. The loosely-coupled method is simpler and can readily be applied to off-the-self receivers and sensors while the tightly-coupled integration requires access to raw measurement mechanism of the receiver. Simulation result show that the tightly-coupled integration system exhibits better performance and robustness than loosely-coupled integration method.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 2005.04a
• /
• pp.688-695
• /
• 2005

The aim of this study is to develop a procedure to estimate the wind loads from the accelerations of a tall building structure. The wind loads may be directly calculated using the inverse analysis or simply integrating the wind pressures of the overall structure. But, these methods are too expensive and impossible to implement in some cases. In this study, a simple method is proposed to estimate the wind loads using the Kalman filter. This method is very stable compared to the direct integration of the acceleration to get the velocity or displacement. The proposed method is verified thorough numerical analysis, and results show that the proposed method is robust and estimates the wind loads accurately.

• Journal of Mechanical Science and Technology
• /
• v.16 no.3
• /
• pp.302-309
• /
• 2002

This paper presents a technique for localization of a mobile robot using sonar sensors. Localization is the continual provision of knowledges of position that are deduced from its a priori position estimation. The environment of a robot is modeled by a two-dimensional grid map. We define a physically based sonar sensor model and employ an extended Kalman filter to estimate positions of the robot. Since the approach does not rely on an exact geometric model of an object, it is very simple and offers sufficient generality such that integration with concurrent mapping and localizing can be achieved without major modifications. The performance and simplicity of the approach are demonstrated with the results produced by sets of experiments using a mobile robot equipped with sonar sensors.

• International Journal of Aeronautical and Space Sciences
• /
• v.2 no.1
• /
• pp.67-77
• /
• 2001

In recent navigation system, the profitable solution is to integrate the GPS and Stapdwon INS (SDINS) system and its integration allows compensation for shortcomings of each system. This paper describes the hardware preparation and presents the test results obtained from the automobile test of the developed system. The automobile tests was conducted with two kinds of inertial sensors and GPS receivers : short range and middle range test, to verify and evaluate the performance of the integrated navigation system. The reference of position is given by the Differential GPS(DGPS) which has cm-level accuracy to compare the accuracy of system. Kalman filtering is used for integrating GPS and SDINS and this filter effectively allows the long-term stability of GPS to correct and decrease the time deviation error of SDINS.

• International Journal of Aeronautical and Space Sciences
• /
• v.2 no.1
• /
• pp.55-66
• /
• 2001

The Global Positioning System(GPS) and the Strapdown Inertial Navigation System(SDINS) techniques have been widely utilized in many applications. However each system has its own weak point when used in a stand-alone mode. SDINS suffers from fast error accumulation dependent on an operating time while GPS has problem of cycle slips and just provides low update rate. The best solution is to integrate the GPS and SDINS system and its integration allows compensation for each shortcomings. This paper, first, is to define and derive error equations of integrated SDINS/GPS system before it will be applied on a real hardware system with gyro, accelerometer and GPS receiver. Second, the accuracy, availability and performance of this mechanization are verified on the simulation study.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.75-75
• /
• 2000

Recently, number of navigation system using GPS and other complementary sensors has been developed to offer high-position accuracy. In this paper, an integration of GPS and Dead-Reckoning, which consists of a fiber optical gyroscope and two high-precision wheel-motor encoders for a unmanned navigation system, is presented. The main objective of this integrated GPS/DR unmanned navigation system is to provide accurate position and heading navigation data continuously for autonomous mobile robot. We propose a method for increasing the accuracy of the estimated position of the mobile robot by its DR sensors, high-precision wheel-motor encoders and a fiber optical gyroscope. We used Kalman filter theory to combine GPS and DR measurements. The performance of GPS/DR navigation system is evaluated.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.51 no.6
• /
• pp.221-227
• /
• 2002

In this paper, the system model for the compensation of the low-cost personal navigation system is derived and the error compensation method using GPS is also proposed. WNS(Walking Navigation System) is a kind of personal navigation system using the number of a walk, stride and azimuth. Because the accuracy of these variables determines the navigation performance, computational methods have been investigated. The step is detected using the walking patterns, stride is determined by neural network and azimuth is calculated with gyro output. The neural network filters off unnecessary motions. However, the error compensation method is needed, because the error of navigation information increases with time. In this paper, the accumulated error due to the step detection error, stride error and gyro bias is compensated by the integrating with GPS. Loosely coupled Kalman filter is used for the integration of WNS and GPS. It is shown by simulation that the error is bounded even though GPS signal is blocked.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.32 no.2
• /
• pp.163-171
• /
• 2014

Based on the GPS/IMU integration, the car navigation has unstable conditions as well as drastically reduces accuracies in urban region. Nowadays, many cars mounted the camera to record driving states. If the ground coordinates of street furniture are known, the position and attitude of camera can be determined through SPR(Single Photo Resection). Therefore, an estimated position and attitude from SPR can be applied measurements in Kalman filter for updating errors of navigation solutions from GPS/IMU integration. In this study, the GPS/IMU/SPR integration algorithm was developed in loosely coupled modes through extended Kalman filters. Also, in order to analyze performances of GPS/IMU/SPR, simulation tests were conducted in GPS signal reception environments and the GCPs (Ground Control Points) distributions. In fact, the position and attitude gathered from GPS/IMU/SPR integration are more precise than the position and attitude from GPS/IMU integration. When IPs (image points), corresponded to GCPs, were concentrated in the center of image, the position error in the optical axis respectively increased. To understand effects from SPR, we plan to carry additional test on the magnitude of GCP, IP and initial exterior orientation errors.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• v.1
• /
• pp.251-256
• /
• 2006

In the work package 'Integrated Positioning' of the research project NAVIO (Pedestrian Navigation Systems in Combined Indoor/Outdoor Environements) we are dealing with the navigation and guidance of visitors of our University. Thereby start points are public transport stops in the surroundings of the Vienna University of Technology and the user of the system should be guided to certain office rooms or persons. For the position determination of the user different location sensors are employed, i.e., for outdoor positioning GPS and dead reckoning sensors such as a digital compass and gyro for heading determination and accelerometers for the determination of the travelled distance as well as a barometric pressure sensor for altitude determination and for indoor areas location determination using WiFi fingerprinting. All sensors and positioning methods are combined and integrated using a Kalman filter approach. Then an optimal estimate of the current location of the user is obtained using the filter. To perform an adequate weighting of the sensors in the stochastic filter model, the sensor characteristics and their performance was investigated in several tests. The tests were performed in different environments either with free satellite visibility or in urban canyons as well as inside of buildings. The tests have shown that it is possible to determine the user's location continuously with the required precision and that the selected sensors provide a good performance and high reliability. Selected tests results and our approach will be presented in the paper.