Parisa Doostdar

Bio: Parisa Doostdar is an academic researcher from University of Tabriz. The author has contributed to research in topics: Attitude and heading reference system & Extended Kalman filter. The author has an hindex of 3, co-authored 3 publications receiving 43 citations.

INS/GNSS integration using recurrent fuzzy wavelet neural networks

Abstract: In recent years, aided navigation systems through combining inertial navigation system (INS) with global navigation satellite system (GNSS) have been widely applied to enhance the position, velocity, and attitude information of autonomous vehicles. In order to gain the accuracy of the aided INS/GNSS in GNSS gap intervals, a heuristic neural network structure based on the recurrent fuzzy wavelet neural network (RFWNN) is applicable for INS velocity and position error compensation purpose. During frequent access to GNSS data, the RFWNN should be trained as a highly precise prediction model equipped with the Kalman filter algorithm. Therefore, the INS velocity and position error data are obtainable along with the lost intervals of GNSS signals. For performance assessment of the proposed RFWNN-aided INS/GNSS, real flight test data of a small commercial unmanned aerial vehicle (UAV) were conducted. A comparison of test results shows that the proposed NN algorithm could efficiently provide high-accuracy corrections on the INS velocity and position information during GNSS outages.

Fuzzy Sliding Mode Observer for Vehicular Attitude Heading Reference System

Abstract: In low-cost Attitude Heading Reference Systems (AHRS), the measurements made by Micro Electro-Mechanical Systems (MEMS) type sensors are affected by uncertainties, noises and unknown disturbances. In this paper, considering the robustness of sliding mode observers against structured and unstructured uncertainties, and also exogenous inputs, the process of design and implementation of a sliding mode observer (SMO) is proposed based on a linearized model of the AHRS. To decrease the chattering phenomenon is the main difficulty of the SMO. Through smoothing the discontinuity term, the tracking performance of the observer is attenuated. Boundary layer technique, for example, using a saturation term, is the common smoother to remove the chattering drawbacks. However, through poor tracking performance, the high range chattering could not be removed by this method. Therefore, a knowledge-based Mamdani-type fuzzy SMO (FSMO) is proposed to decrease the chattering effects intelligently, which in turn could obtain the high accuracy tracking performance of the SMO. Following proving the stability of the proposed SMOs based on direct Lyapunov’s method, the performance of the proposed observers is compared with that of the extended Kalman filter through simulation and real experiments of an AHRS.

MEMS gyros temperature calibration through artificial neural networks

Abstract: In this paper, the application of Artificial Neural Networks to perform the thermal calibration of bias for Micro Electro-Mechanical gyros that are installed in Inertial Measurement Units is discussed. In recent years, the interest in using these systems to perform integrated inertial navigation has increased. Several new applications, related to the use of autonomous systems and personal navigation systems in GPS-challenging environments, have been developed. Thermal calibration of bias is a key issue to be assessed to achieve the best performance of a Micro Electro-Mechanical gyro. It can reduce sensor bias to one order of magnitude lower than non-calibrated conditions. Usually, thermal calibration is performed by exploiting polynomial fitting, i.e. finding the least-square polynomial that fits experimental data collected during laboratory tests in a climatic chamber. Polynomials have some drawbacks when they are applied to Micro Electro-Mechanical gyro calibration. They are not adequate to model abrupt change of bias trend in small temperature intervals and sensor hysteresis. For this reason, in the present paper, the use of Back Propagation Artificial Neural Networks is suggested as an improvement of polynomial fitting. Indeed, Neural Networks have intrinsic adaptive configurations and standard training and testing techniques, so that they can be adequately adopted for mapping thermal bias variations. In this paper, the polynomial fitting and Neural Network compensation algorithms are compared on selected testing points where the two techniques have the largest difference. Results highlight that the proposed method has better performance on these points. Therefore, the time in which the flight attitude accuracy meets the requirements imposed by the current regulations is improved by 20%.

Toward Accurate Position Estimation Using Learning to Prediction Algorithm in Indoor Navigation.

Abstract: Internet of Things is advancing, and the augmented role of smart navigation in automating processes is at its vanguard. Smart navigation and location tracking systems are finding increasing use in the area of the mission-critical indoor scenario, logistics, medicine, and security. A demanding emerging area is an Indoor Localization due to the increased fascination towards location-based services. Numerous inertial assessments unit-based indoor localization mechanisms have been suggested in this regard. However, these methods have many shortcomings pertaining to accuracy and consistency. In this study, we propose a novel position estimation system based on learning to the prediction model to address the above challenges. The designed system consists of two modules; learning to prediction module and position estimation using sensor fusion in an indoor environment. The prediction algorithm is attached to the learning module. Moreover, the learning module continuously controls, observes, and enhances the efficiency of the prediction algorithm by evaluating the output and taking into account the exogenous factors that may have an impact on its outcome. On top of that, we reckon a situation where the prediction algorithm can be applied to anticipate the accurate gyroscope and accelerometer reading from the noisy sensor readings. In the designed system, we consider a scenario where the learning module, based on Artificial Neural Network, and Kalman filter are used as a prediction algorithm to predict the actual accelerometer and gyroscope reading from the noisy sensor reading. Moreover, to acquire data, we use the next-generation inertial measurement unit, which contains a 3-axis accelerometer and gyroscope data. Finally, for the performance and accuracy of the proposed system, we carried out numbers of experiments, and we observed that the proposed Kalman filter with learning module performed better than the traditional Kalman filter algorithm in terms of root mean square error metric.