Machine Learning Driven Method for Indoor Positioning Using Inertial Measurement Unit

The application of inertial measurement unit (IMU) is widespread in many domains, but the main hindrance in localization is the errors accumulation in the integration process over a long time. Recently, we notice that many researchers have applied machine learning (ML) algorithms to indoor positioning by using IMU sensor data, which sufficiently proves that the 6-dim data collected by IMU sensor contain a lot of information. In this paper, we present a ML driven method to make a regression between IMU sensor data and 2-D coordinates. To build a regression model with better generalization and lower computational complexity, this paper carries out feature extraction in the time-and time-frequency domain. The simulation run on Intel core i5-4200h shows that the method is able to suppress the drift of the inertial navigation system after a long-time travel. In comparison of GPS+IMU using extended Kalman filtering (EKF), the positioning RMS of our method on circular trajectories with a radius of 7 meters and 10.5 meters is reduced by at most 70.1% and 86.1%, respectively.

[1]  Tapio Seppänen,et al.  Recognizing human motion with multiple acceleration sensors , 2001, 2001 IEEE International Conference on Systems, Man and Cybernetics. e-Systems and e-Man for Cybernetics in Cyberspace (Cat.No.01CH37236).

[2]  Fast alignment using rotation vector and adaptive Kalman filter , 2006, IEEE Transactions on Aerospace and Electronic Systems.

[3]  Song Tian Shang,et al.  Application of Adaptive Kalman Filter Technique in Initial Alignment of Single-Axial Rotation Strap-Down Inertial Navigation System , 2012 .

[4]  Lubin Chang,et al.  Huber-based novel robust unscented Kalman filter , 2012 .

[5]  An Li,et al.  Strapdown inertial navigation system alignment based on marginalised unscented kalman filter , 2013 .

[6]  Fabio Dovis,et al.  A Comparison between Different Error Modeling of MEMS Applied to GPS/INS Integrated Systems , 2013, Sensors.

[7]  Elhassane Abdelmounim,et al.  Discrete Wavelet Transform based algorithm for recognition of QRS complexes , 2014, 2014 International Conference on Multimedia Computing and Systems (ICMCS).

[8]  Ning Liu,et al.  Error Model and Compensation of Bell-Shaped Vibratory Gyro , 2015, Sensors.

[9]  Lin Ma,et al.  Coupled Integration of CSAC, MIMU, and GNSS for Improved PNT Performance , 2016, Sensors.

[10]  Yann Dauphin,et al.  Convolutional Sequence to Sequence Learning , 2017, ICML.

[11]  A. M. Aleshechkin,et al.  Trajectory optimization of dynamically controlled objects in INS/GNSS integrated navigation system , 2017 .

[12]  Yuming Bo,et al.  Implementation and performance evaluation of a fast relocation method in a GPS/SINS/CSAC integrated navigation system hardware prototype , 2017, IEICE Electron. Express.

[13]  Alfonso Bahillo,et al.  Step Length Estimation Methods Based on Inertial Sensors: A Review , 2018, IEEE Sensors Journal.

[14]  Agathoniki Trigoni,et al.  IONet: Learning to Cure the Curse of Drift in Inertial Odometry , 2018, AAAI.

[15]  Qi Shan,et al.  RIDI: Robust IMU Double Integration , 2017, ECCV.

[16]  Wei Wang,et al.  Multiscale modeling of fiber optic gyroscope temperature drift based on improved ensemble empirical mode decomposition. , 2018, Applied optics.

[17]  Michael Philippsen,et al.  A Bidirectional LSTM for Estimating Dynamic Human Velocities from a Single IMU , 2019, 2019 International Conference on Indoor Positioning and Indoor Navigation (IPIN).

[18]  IEEE Transactions on Vehicular Technology , 2020, IEEE Transactions on Vehicular Technology.

[19]  Andrew Markham,et al.  Deep-Learning-Based Pedestrian Inertial Navigation: Methods, Data Set, and On-Device Inference , 2020, IEEE Internet of Things Journal.