Ultra-High-Precision 2D Indoor Positioning Using Inertial Information Only
TL;DR
This paper presents the development of an innovative indoor localization system that employs a self-rotating inertial sensor for direction estimation and an LSTM-based deep learning model for distance estimation, demonstrating significant improvements in direction and distance estimation accuracy.
Abstract
This paper presents the development of an innovative indoor localization system that employs a self-rotating inertial sensor for direction estimation and an LSTM-based deep learning model for distance estimation. The primary objective is to enhance the positioning accuracy of two-dimensional moving objects, such as Automatic Guided Vehicles (AGVs), in environments where GPS is unavailable. Traditional indoor localization methods, including wireless-based approaches, Simultaneous Localization and Mapping (SLAM), and inertial navigation, each have limitations in terms of accuracy and robustness. The proposed system overcomes these limitations in inertial navigation by combining a unique hardware configuration with deep learning techniques. The system's effectiveness was validated through various performance evaluations, demonstrating significant improvements in direction and distance estimation accuracy. Specifically, in a stationary experiment, the direction error was reduced from 52° to 5° over a 30 min evaluation period, confirming the offset-cancellation effect of the SRIS. Additionally, it was confirmed that the average error in estimating the travel distance for straight and rectangular paths was reduced from over 3% with conventional methods to approximately 1%, while some variability was observed across repeated trials, as discussed in Section 4.2B.