Rapid Gyroscope Calibration: A Deep Learning Approach

2024-08-31

arXiv.org

AI Summary

To address the prolonged calibration time of low-cost gyroscopes in short-duration startup scenarios—which hinders system responsiveness—this paper proposes a lightweight, deep learning–based rapid calibration method. The approach introduces a physics-informed virtual gyroscope model and integrates heterogeneous data sources (real and synthetically generated) to jointly estimate multi-gyroscope biases while fusing virtual sensor outputs within a compact neural network architecture. This eliminates reliance on long temporal averaging windows inherent in conventional time-domain methods. Evaluated on 169 hours of real-world data from 24 physical devices, the method reduces calibration time to just 11% of that required by traditional approaches (an 89% reduction), while achieving bias estimation accuracy comparable to long-term averaging. Furthermore, the method demonstrates strong cross-platform generalization across two distinct hardware brands.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Computer Vision: Low Level & Physics-based Vision
• Intelligent Robots: State Estimation

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Systems and Infrastructure for Web, Mobile and WoT: Virtualization and resource management in Web systems and infrastructures

Abstract

Low-cost gyroscope calibration is essential for ensuring the accuracy and reliability of gyroscope measurements. Stationary calibration estimates the deterministic parts of measurement errors. To this end, a common practice is to average the gyroscope readings during a predefined period and estimate the gyroscope bias. Calibration duration plays a crucial role in performance, therefore, longer periods are preferred. However, some applications require quick startup times and calibration is therefore allowed only for a short time. In this work, we focus on reducing low-cost gyroscope calibration time using deep learning methods. We propose a deep-learning framework and explore the possibilities of using multiple real and virtual gyroscopes to improve the calibration performance of single gyroscopes. To train and validate our approach, we recorded a dataset consisting of 169 hours of gyroscope readings, using 24 gyroscopes of two different brands. We also created a virtual dataset consisting of simulated gyroscope readings. The two datasets were used to evaluate our proposed approach. One of our key achievements in this work is reducing gyroscope calibration time by up to 89% using three low-cost gyroscopes.

Problem

• Reducing gyroscope calibration time using deep learning
• Improving single gyroscope calibration with multiple sensors
• Achieving 89% faster calibration with low-cost gyroscopes

Innovation

• Deep learning reduces gyroscope calibration time
• End-to-end convolutional neural network for calibration
• Multiple real and virtual gyroscopes enhance performance