A Hybrid Adaptive Velocity Aided Navigation Filter with Application to INS/DVL Fusion

TL;DR

Handcrafted features are generated and used to tune the momentary system noise covariance matrix and it is fed into the model-based navigation filter, showing the benefits of this approach compared to other adaptive approaches.

Abstract

Autonomous underwater vehicles (AUV) are commonly used in many underwater applications. Usually, inertial sensors and Doppler velocity log readings are used in a nonlinear filter to estimate the AUV navigation solution. The process noise covariance matrix is tuned according to the inertial sensors' characteristics. This matrix greatly influences filter accuracy, robustness, and performance. A common practice is to assume that this matrix is fixed during the AUV operation. However, it varies over time as the amount of uncertainty is unknown. Therefore, adaptive tuning of this matrix can lead to a significant improvement in the filter performance. In this work, we propose a learning-based adaptive velocity-aided navigation filter. To that end, handcrafted features are generated and used to tune the momentary system noise covariance matrix. Once the process noise covariance is learned, it is fed into the model-based navigation filter. Simulation results show the benefits of our approach compared to other adaptive approaches.

Figures (6)

• Figure 1: Boosting the hybrid adaptive navigation filter in the INS/DVL fusion with handcrafted features for online tuning of the process noise covariance matrix.
• Figure 2: Dataset generation and pre-processing phase.
• Figure 3: Our four baseline trajectories used to create the dataset.
• Figure 4: HCF Pipeline: readings of an inertial sensor are inserted into three high-level features and then, for each one of them, eight low-level features are calculated.
• Figure 5: AUV trajectory using the velocity aided navigation filter model vs. the ground truth trajectory.