Precise Onboard Aircraft Cabin Localization using UWB and ML

TL;DR

This work demonstrates precise onboard aircraft-cabin localization using Ultra-Wideband (UWB) and machine learning (ML). It presents a real Airbus A321 measurement campaign, showing that raw UWB ranging is strongly affected by multipath and obstacles, yet end-to-end ML approaches can achieve mean localization errors around 16–17 cm and seat-label accuracy near 97–100%. Key contributions include a per-anchor offset and linear regression correction, plus an end-to-end neural-network localization framework that directly predicts tag positions or seat labels from ranges and CIR data. Monte Carlo simulations further explore anchor-count and ranging-accuracy improvements, indicating practical paths to meet industrial requirements and demonstrating the viability of UWB-based IPS for aircraft operations and maintenance.

Abstract

Precise indoor positioning systems (IPSs) are key to perform a set of tasks more efficiently during aircraft production, operation and maintenance. For instance, IPSs can overcome the tedious task of configuring (wireless) sensor nodes in an aircraft cabin. Although various solutions based on technologies of established consumer goods, e.g., Bluetooth or WiFi, have been proposed and tested, the published accuracy results fail to make these technologies relevant for practical use cases. This stems from the challenging environments for positioning, especially in aircraft cabins, which is mainly due to the geometries, many obstacles, and highly reflective materials. To address these issues, we propose to evaluate in this work an Ultra-Wideband (UWB)-based IPS via a measurement campaign performed in a real aircraft cabin. We first illustrate the difficulties that an IPS faces in an aircraft cabin, by studying the signal propagation effects which were measured. We then investigate the ranging and localization accuracies of our IPS. Finally, we also introduce various methods based on machine learning (ML) for correcting the ranging measurements and demonstrate that we are able to localize a node with respect to an aircraft seat with a measured likelihood of 97%.

Figures (12)

• Figure 1: Illustration of single sided TWR and ToF calculations
• Figure 2: Architecture of the NN and the size of the different layers. The size of the last layer depends on the type of output required.
• Figure 3: Measurement environment and tag positioning
• Figure 4: A321 cabin layout and anchor placements. The position of each seat was measured during our measurement campaign.
• Figure 5: Example of CIR data. The effects of multipath are clearly seen in the aircraft cabin compared to the indoor environment.