Non-Parametric Modeling of Spatio-Temporal Human Activity Based on Mobile Robot Observations

TL;DR

This paper introduces a non-parametric, Gaussian process-based model for mapping human activity over time and space using mobile robots, effectively handling long-term data and movement-induced data variability.

Contribution

It presents a novel variational Gaussian process model that incorporates periodic and spatial dependencies for long-term human activity mapping by robots.

Findings

Outperforms existing methods in predictive accuracy.

Handles large multi-week datasets efficiently.

Improves robot path planning based on activity maps.

Abstract

This work presents a non-parametric spatio-temporal model for mapping human activity by mobile autonomous robots in a long-term context. Based on Variational Gaussian Process Regression, the model incorporates prior information of spatial and temporal-periodic dependencies to create a continuous representation of human occurrences. The inhomogeneous data distribution resulting from movements of the robot is included in the model via a heteroscedastic likelihood function and can be accounted for as predictive uncertainty. Using a sparse formulation, data sets over multiple weeks and several hundred square meters can be used for model creation. The experimental evaluation, based on multi-week data sets, demonstrates that the proposed approach outperforms the state of the art both in terms of predictive quality and subsequent path planning.