Velocity-Based Channel Charting with Spatial Distribution Map Matching

TL;DR

This article proposes a novel channel charting framework that does not require references and dramatically reduces life-cycle management, and achieves the localization accuracy of FP but without reference information.

Abstract

Fingerprint-based localization improves the positioning performance in challenging, non-line-of-sight (NLoS) dominated indoor environments. However, fingerprinting models require an expensive life-cycle management including recording and labeling of radio signals for the initial training and regularly at environmental changes. Alternatively, channel-charting avoids this labeling effort as it implicitly associates relative coordinates to the recorded radio signals. Then, with reference real-world coordinates (positions) we can use such charts for positioning tasks. However, current channel-charting approaches lag behind fingerprinting in their positioning accuracy and still require reference samples for localization, regular data recording and labeling to keep the models up to date. Hence, we propose a novel framework that does not require reference positions. We only require information from velocity information, e.g., from pedestrian dead reckoning or odometry to model the channel charts, and topological map information, e.g., a building floor plan, to transform the channel charts into real coordinates. We evaluate our approach on two different real-world datasets using 5G and distributed single-input/multiple-output system (SIMO) radio systems. Our experiments show that even with noisy velocity estimates and coarse map information, we achieve similar position accuracies

Figures (14)

• Figure 1: Trajectory of the agent (gray) with consecutive CSI measurements (red dots). The distances $d_{n,n+1}, \ldots, d_{n,n+3}$ are calculated within a window (green) for the positions $p_n, \ldots, p_{n+3}$.
• Figure 2: The two stages of the positioning pipeline. Stage 1 generates a channel chart based on CSI and velocity information. After the channel chart is generated, it only reflects the radio geometry up to isometries. To exploit the channel chart for localization, stage 2 learns a linear transformation to the real world coordinates by provided topological map information.
• Figure 3: Schematic top view (left) of the environment (right) of the 5G dataset. The red rectangles indicate reflective walls, the green dots are the base stations, blue indicates small shelves and purple the large shelves. The recording area, indicated in blue, has a size of $20\,\mathrm{m} \times 10\,\mathrm{m}$.
• Figure 4: Schematic top view of the environment of the SIMO dataset dataDichasusIndustrial. The orange rectangle indicates a small container room. The recording area, indicated in blue, has a size of $11\,\mathrm{m} \times 13\,\mathrm{m}$.
• Figure 5: The topological map of the 5G dataset (left) and the SIMO dataset (right) represented as discrete coordinates (blue). The trajectories of the training datasets are shown in orange.