Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Neural-Assisted in-Motion Self-Heading Alignment

Zeev Yampolsky, Felipe O. Silva, Adriano Frutuoso, Itzik Klein

Abstract

Autonomous platforms operating in the oceans require accurate navigation to successfully complete their mission. In this regard, the initial heading estimation accuracy and the time required to achieve it play a critical role. The initial heading is traditionally estimated by model-based approaches employing orientation decomposition. However, methods such as the dual vector decomposition and optimized attitude decomposition achieve satisfactory heading accuracy only after long alignment times. To allow rapid and accurate initial heading estimation, we propose an end-to-end, model-free, neural-assisted framework using the same inputs as the model-based approaches. Our proposed approach was trained and evaluated on real-world dataset captured by an autonomous surface vehicle. Our approach shows a significant accuracy improvement over the model-based approaches achieving an average absolute error improvement of 53%. Additionally, our proposed approach was able to reduce the alignment time by up to 67%. Thus, by employing our proposed approach, the reduction in alignment time and improved accuracy allow for a shorter deployment time of an autonomous platform and increased navigation accuracy during the mission.

Neural-Assisted in-Motion Self-Heading Alignment

Abstract

Autonomous platforms operating in the oceans require accurate navigation to successfully complete their mission. In this regard, the initial heading estimation accuracy and the time required to achieve it play a critical role. The initial heading is traditionally estimated by model-based approaches employing orientation decomposition. However, methods such as the dual vector decomposition and optimized attitude decomposition achieve satisfactory heading accuracy only after long alignment times. To allow rapid and accurate initial heading estimation, we propose an end-to-end, model-free, neural-assisted framework using the same inputs as the model-based approaches. Our proposed approach was trained and evaluated on real-world dataset captured by an autonomous surface vehicle. Our approach shows a significant accuracy improvement over the model-based approaches achieving an average absolute error improvement of 53%. Additionally, our proposed approach was able to reduce the alignment time by up to 67%. Thus, by employing our proposed approach, the reduction in alignment time and improved accuracy allow for a shorter deployment time of an autonomous platform and increased navigation accuracy during the mission.

Paper Structure

This paper contains 21 sections, 22 equations, 10 figures, 6 tables.

Table of Contents

  1. Introduction
  2. Problem Formulation and Classical In-Motion Alignment Methods
  3. Reference Frames and Attitude Decomposition
  4. Attitude Decomposition-based Initial Alignment (ADIA)
  5. Dual-Vector ADIA (DVA)
  6. Optimization-Based ADIA (OBA)
  7. Observation Vectors
  8. Proposed Approach
  9. HeadingNet Backbone Architecture
  10. Neural network Formulation and Training Process
  11. Fully Connected Neural Network
  12. Two Dimensional Convolution Neural Network
  13. Nonlinear Activation Functions
  14. Regularization
  15. Training Process
  16. ...and 6 more sections

Figures (10)

  • Figure 1: Block diagram showing our proposed data-driven approach for self-heading estimation.
  • Figure 2: Detailed block diagram showing the proposed neural-assisted in-motion self-heading alignment architecture, that is HeadingNet, and the possible variation due to $T_{Align}$ variations.
  • Figure 3: Illustration of an average pooling operation with a kernel of size $k$, applied over a $T$ second measurement window containing $n$ IMU measurements and $m$ transport-rate and gravity measurements, where $n>m$.
  • Figure 4: Data flow diagram of starting from the raw measurements from the ASV sensors, the IMU and GNSS-RTK, to our proposed approach HeadingNet.
  • Figure 5: Heading angles plot of the first $350$ seconds for the five recorded trajectories, R1 to R5.
  • ...and 5 more figures