Can a Building Work as a Reservoir: Footstep Localization with Embedded Accelerometer Networks

TL;DR

This paper presents a novel approach where building floors are used as physical reservoir computers to localize footsteps accurately using embedded accelerometers, without extensive calibration or training.

Contribution

It introduces a physical reservoir computing method for footstep localization, leveraging structural dynamics of floors for robust, calibration-free indoor sensing.

Findings

Achieved sub-meter accuracy along hallways with moderate sensor coverage.

Successfully predicted footstep locations across different participants without retraining.

Demonstrated building structures can serve as effective physical reservoir computers.

Abstract

Using floor vibrations to accurately predict occupants' footstep locations is essential for smart building operation and privacy-preserving indoor sensing. However, existing approaches are dominated by either physics-based models that rely on simplified wave propagation assumptions and careful calibration, or data-driven methods that require large labeled datasets and often lack robustness to subject and environmental variability. This work introduces a new approach by treating an instrumented building floor as a physical reservoir computer, whose intrinsic structural dynamics can perform nonlinear spatio-temporal computation and information extraction directly. Specifically, foot strike-induced floor vibrations recorded by a distributed accelerometer network are processed using a lightweight physical reservoir computing (PRC) pipeline consisting of short waveform extraction, root-mean-square (RMS) normalization, principal component analysis (PCA), and a weighted linear readout. Results of this study, involving 2 participants and 12 accelerometers, showed that RMS normalization and PCA projection successfully extracted occupant-invariant features from floor-vibration waveform data, enabling a single linear readout to predict foot-strike location across repeated traversals and participants. Sub-meter accuracy is achieved along the hallway direction with moderate sensing coverage, while cross-participant tests achieved meter-scale accuracy without subject-specific recalibration or retraining. These findings demonstrate that building-scale structures can function as capable physical reservoir computers for intelligent monitoring.