End-to-End Deep Learning Framework for Real-Time Inertial Attitude Estimation using 6DoF IMU

Abstract

Inertial Measurement Units (IMU) are commonly used in inertial attitude estimation from engineering to medical sciences. There may be disturbances and high dynamics in the environment of these applications. Also, their motion characteristics and patterns also may differ. Many conventional filters have been proposed to tackle the inertial attitude estimation problem based on IMU measurements. There is no generalization over motion and environmental characteristics in these filters. As a result, the presented conventional filters will face various motion characteristics and patterns, which will limit filter performance and need to optimize the filter parameters for each situation. In this paper, two end-to-end deep-learning models are proposed to solve the problem of real-time attitude estimation by using inertial sensor measurements, which are generalized to motion patterns, sampling rates, and environmental disturbances. The proposed models incorporate accelerometer and gyroscope readings as inputs, which are collected from a combination of five public datasets. The models consist of convolutional neural network (CNN) layers combined with Bi-Directional Long-Short Term Memory (LSTM) followed by a Fully Forward Neural Network (FFNN) to estimate the quaternion. To evaluate the validity and reliability, we have performed an extensive and comprehensive evaluation over five publicly available datasets, which consist of more than 120 hours and 200 kilometers of IMU measurements. The results show that the proposed method outperforms the state-of-the-art methods in terms of accuracy and robustness. Furthermore, it demonstrates that this model generalizes better than other methods over various motion characteristics and sensor sampling rates.

Recent Advancements in Deep Learning Applications and Methods for Autonomous Navigation -- A Comprehensive Review

“…URWalking: Indoor Navigation for Research and Daily Use [21] Indoor Navigation A Simple Self-Supervised IMU Denoising Method For Inertial Aided Navigation [22] Inertial Navigation Multi-Scale Fully Convolutional Network-Based Semantic Segmentation for Mobile Robot Navigation [23] Visual Navigation Drone Navigation Using Octrees and Object Recognition for Intelligent Inspections [24] Visual Navigation Deep learning-enabled fusion to bridge GPS outages for INS/GPS integrated navigation [25] Inertial Navigation Deep learning based wireless localization for indoor navigation [26] Indoor Navigation Efficient and robust LiDAR-based end-to-end navigation [27] Terrain modelling End-to-End Deep Learning Framework for Real-Time Inertial Attitude Estimation using 6DoF IMU [28] Inertial Navigation Table 2: Recent surveys on navigation or deep learning for navigation…”

“…However, the integration process can be susceptible to a range of error sources such as sensor noise, drift, and biases. To ensure reliable and precise attitude estimation, sensor fusion techniques can be employed to combine the measurements from various sensors to minimize the impact of individual sensor errors [28]. Additionally, advanced machine learning algorithms, including Kalman filters or particle filters, can be applied to further improve the accuracy of attitude estimation.…”