Deep Kalman Filter: Simultaneous Multi-Sensor Integration and Modelling; A GNSS/IMU Case Study

Bayes filters, such as the Kalman and particle filters, have been used in sensor fusion to integrate two sources of information and obtain the best estimate of unknowns. The efficient integration of multiple sensors requires deep knowledge of their error sources. Some sensors, such as Inertial Measurement Unit (IMU), have complicated error sources. Therefore, IMU error modelling and the efficient integration of IMU and Global Navigation Satellite System (GNSS) observations has remained a challenge. In this paper, we developed deep Kalman filter to model and remove IMU errors and, consequently, improve the accuracy of IMU positioning. To achieve this, we added a modelling step to the prediction and update steps of the Kalman filter, so that the IMU error model is learned during integration. The results showed our deep Kalman filter outperformed the conventional Kalman filter and reached a higher level of accuracy.

[1]  E. Rasel,et al.  Could cold atom interferometry sensors be the future inertial sensors? — First simulation results , 2017, 2017 DGON Inertial Sensors and Systems (ISS).

[2]  Yann LeCun,et al.  Dynamic Factor Graphs for Time Series Modeling , 2009, ECML/PKDD.

[3]  Aboelmagd Noureldin,et al.  GPS/INS integration utilizing dynamic neural networks for vehicular navigation , 2011, Inf. Fusion.

[4]  Jian-hua Cheng,et al.  A New Technique for Integrating MEMS-Based Low-Cost IMU and GPS in Vehicular Navigation , 2016, J. Sensors.

[5]  Zoubin Ghahramani,et al.  Learning Nonlinear Dynamical Systems Using an EM Algorithm , 1998, NIPS.

[6]  Yoshua Bengio,et al.  Architectural Complexity Measures of Recurrent Neural Networks , 2016, NIPS.

[7]  Bo Hou,et al.  Modeling and Compensation of Random Drift of MEMS Gyroscopes Based on Least Squares Support Vector Machine Optimized by Chaotic Particle Swarm Optimization , 2017, Sensors.

[8]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[9]  Gang Yin,et al.  An Accurate GPS-IMU/DR Data Fusion Method for Driverless Car Based on a Set of Predictive Models and Grid Constraints , 2016, Sensors.

[10]  Marvin Minsky,et al.  Perceptrons: expanded edition , 1988 .

[11]  Andreas Geiger,et al.  Vision meets robotics: The KITTI dataset , 2013, Int. J. Robotics Res..

[12]  C. Jekeli.  Inertial navigation systems with geodetic applications , 2000 .

[13]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[14]  Uri Shalit,et al.  Structured Inference Networks for Nonlinear State Space Models , 2016, AAAI.

[15]  N. El-Sheimy,et al.  Constructive neural-networks-based MEMS/GPS integration scheme , 2008, IEEE Transactions on Aerospace and Electronic Systems.

[16]  Ling Zhang,et al.  Performance Analysis of Adaptive Neuro Fuzzy Inference System Control for MEMS Navigation System , 2014 .

[17]  D.A. Grejner-Brzezinska,et al.  Pedestrian Tracking and Navigation Using Neural Networks and Fuzzy Logic , 2007, 2007 IEEE International Symposium on Intelligent Signal Processing.

[18]  Aboelmagd Noureldin,et al.  Fundamentals of Inertial Navigation, Satellite-based Positioning and their Integration , 2012 .

[19]  Siavash Hosseinyalamdary,et al.  Error Modeling of Reduced IMU using Recurrent Neural Network , 2017 .

[20]  Naser El-Sheimy,et al.  Adaptive Fuzzy Prediction of Low-Cost Inertial-Based Positioning Errors , 2007, IEEE Transactions on Fuzzy Systems.

[21]  Jan Kautz,et al.  Dynamic Facial Analysis: From Bayesian Filtering to Recurrent Neural Network , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).