Exploring the Benefits of Deep Learning-Based Sensors Error Estimation for Improved Attitude and Position Accuracy

Inertial Navigation System (INS) is a primary component in various integrated navigation systems. However, the performance of INS is hindered due to the numerical integration of the measurements obtained from the Inertial Measurement Unit (IMU), which are contaminated by various sensor errors, especially with Micro-Electro-Mechanical Systems (MEMS) sensors. To address these challenges, we examine the performance of modern Deep Learning (DL) methods for mitigating such errors. Specifically, we propose a Deep Gyroscope Error (DGE) model designed to estimate and compensate for errors in the gyroscope measurements. The DGE model combines the feature extraction capabilities of a Convolutional Neural Network (CNN) with the sequential data modelling strengths of Long Short-Term Memory (LSTM). Instead of relying on high-grade IMU measurements, we distinctively employ an inverse mechanization algorithm that generates artificial IMU measurements from the integrated navigation solution states. This approach provides accurate ground truth data facilitating direct supervised learning. The proposed model was trained and verified using real data from MEMS-IMU on real road test experiments performed on a land vehicle in Kingston, Ontario, Canada. When subjected to evaluation against unseen data, the DGE model demonstrated significant improvements in standalone inertial navigation scenarios, particularly in mitigating attitude drift errors and subsequently improving position estimation. Over a uniform testing interval, the DGE model achieved an average reduction in attitude RMSE by 43.1% and in position RMSE by 25.4%. This emphasizes the efficacy of the proposed method in improving INS performance, particularly when operating in standalone mode.