An Integrated INS/GNSS System With an Attention-Based Deep Network for Drones in GNSS Denied Environments

We propose a neural network-based approach to assist positioning in an integrated inertial navigation system/global navigation satellite system (INS/GNSS) during GNSS interruptions. One can aid a navigation system during GNSS outages by substituting the GNSS measurements with a well-trained neural network (NN). Outputs of this NN can then be used in a Kalman filtering scheme to acquire the best consistent and concise estimates according to the INS measurements. Since this problem has inherent spatial and temporal aspects, the proposed NN should account for both aspects simultaneously. Convolutional long short-term memory (CLSTM) structure is an excellent candidate to satisfy the aforementioned requirement. The designed CLSTM architecture uses the angular rates and specific forces measured by INS to output the pseudo GNSS position increment covering for the lost GNSS signal. An attention mechanism is added to the final layer of the CLSTM to counter the gradient vanishing problem in long time-series prediction. A field test utilizing a fixed-wing unmanned aerial vehicle is arranged to evaluate the proposed architecture's performance. The field test result shows a significant 3D positioning improvement during GNSS outages.

[1]  R. Safabakhsh,et al.  An integrated INS/GNSS system with an attention-based hierarchical LSTM during GNSS outage , 2023, GPS Solutions.

[2]  M. Mosavi,et al.  A low-cost integrated navigation system based on factor graph nonlinear optimization for autonomous flight , 2022, GPS Solutions.

[3]  Eberhard Gill,et al.  Evaluation of tightly- and loosely-coupled approaches in CNN-based pose estimation systems for uncooperative spacecraft , 2021, Acta Astronautica.

[4]  Jos Elfring,et al.  Real-Time Vehicle Positioning and Mapping Using Graph Optimization , 2021, Sensors.

[5]  Jian Guo,et al.  An adaptive nonlinear filter for integrated navigation systems using deep neural networks , 2021, Neurocomputing.

[6]  Giancarmine Fasano,et al.  Avionics Systems Panel Research and Innovation Perspectives , 2020, IEEE Aerospace and Electronic Systems Magazine.

[7]  Reza Safabakhsh,et al.  Correlational Convolutional LSTM for human action recognition , 2020, Neurocomputing.

[8]  Bian Hongwei,et al.  An INS/GNSS integrated navigation in GNSS denied environment using recurrent neural network , 2020 .

[9]  Haiyong Luo,et al.  A LSTM Algorithm Estimating Pseudo Measurements for Aiding INS during GNSS Signal Outages , 2020, Remote. Sens..

[10]  Jafar Keighobadi,et al.  INS/GNSS integration using recurrent fuzzy wavelet neural networks , 2019, GPS Solutions.

[11]  Rin-ichiro Taniguchi,et al.  End-to-End Learning Framework for IMU-Based 6-DOF Odometry , 2019, Sensors.

[12]  Ruiyu Liang,et al.  Speech Emotion Classification Using Attention-Based LSTM , 2019, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[13]  K.Amer,et al.  Deep convolutional neural network based autonomous drone navigation , 2019, International Conference on Machine Vision.

[14]  Ondřej Straka,et al.  Design of Rao–Blackwellized Point-Mass Filter With Application in Terrain Aided Navigation , 2019, IEEE Transactions on Aerospace and Electronic Systems.

[15]  Asifullah Khan,et al.  A survey of the recent architectures of deep convolutional neural networks , 2019, Artificial Intelligence Review.

[16]  Wei Wang,et al.  A new direct filtering approach to INS/GNSS integration , 2018, Aerospace Science and Technology.

[17]  Xu Li,et al.  Enhancing Localization Accuracy of MEMS-INS/GPS/In-Vehicle Sensors Integration During GPS Outages , 2018, IEEE Transactions on Instrumentation and Measurement.

[18]  Liang Li,et al.  An innovative information fusion method with adaptive Kalman filter for integrated INS/GPS navigation of autonomous vehicles , 2018 .

[19]  Xiaosu Xu,et al.  A hybrid fusion algorithm for GPS/INS integration during GPS outages , 2017 .

[20]  Abdelouahed Abounada,et al.  Fusion of GPS/INS/Odometer measurements for land vehicle navigation with GPS outage , 2016, 2016 2nd International Conference on Cloud Computing Technologies and Applications (CloudTech).

[21]  Yang Meng,et al.  Covariance matching based adaptive unscented Kalman filter for direct filtering in INS/GNSS integration , 2016 .

[22]  Yanming Feng,et al.  Analysis of a robust Kalman filter in loosely coupled GPS/INS navigation system , 2016 .

[23]  S. Mirzakuchaki,et al.  Optimization of the low-cost INS/GPS navigation system using ANFIS for high speed vehicle application , 2015, 2015 Signal Processing and Intelligent Systems Conference (SPIS).

[24]  Jiancheng Fang,et al.  A Hybrid Prediction Method for Bridging GPS Outages in High-Precision POS Application , 2014, IEEE Transactions on Instrumentation and Measurement.

[25]  Aboelmagd Noureldin,et al.  Vehicle navigator using a mixture particle filter for inertial sensors/odometer/map data/GPS integration , 2012, IEEE Transactions on Consumer Electronics.

[26]  Jan Skaloud,et al.  Optimization of two GPS/MEMS-IMU integration strategies with application to sports , 2009 .

[27]  Rong-Jong Wai,et al.  Design of Dynamic Petri Recurrent Fuzzy Neural Network and Its Application to Path-Tracking Control of Nonholonomic Mobile Robot , 2009, IEEE Transactions on Industrial Electronics.

[28]  Kai-Wei Chiang,et al.  An Artificial Neural Network Embedded Position and Orientation Determination Algorithm for Low Cost MEMS INS/GPS Integrated Sensors , 2009, Sensors.

[29]  N. El-Sheimy,et al.  Online INS/GPS integration with a radial basis function neural network , 2005, IEEE Aerospace and Electronic Systems Magazine.

[30]  S. Hochreiter,et al.  Long Short-Term Memory , 1997, Neural Computation.

[31]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[32]  Vasile Palade,et al.  A Quaternion Gated Recurrent Unit Neural Network for Sensor Fusion , 2021, Inf..

[33]  Yuexin Zhang,et al.  A Fusion Methodology to Bridge GPS Outages for INS/GPS Integrated Navigation System , 2019, IEEE Access.

[34]  V. Vaidehi,et al.  A novel approach to the integration of GPS and INS using recurrent neural networks with evolutionary optimization techniques , 2014 .

[35]  Sameh Nassar,et al.  Improving the Inertial Navigation System (INS) error model for INS and INS/DGPS applications , 2003 .