RuDaCoP: The Dataset for Smartphone-based Intellectual Pedestrian Navigation

TL;DR

This paper introduces RuDaCoP, a comprehensive dataset of inertial sensor data from smartphones and foot-mounted units, designed to advance pedestrian navigation algorithms through diverse trajectories and high-accuracy ground truth.

Contribution

The paper provides a large, diverse dataset for smartphone-based pedestrian navigation, including synchronized inertial measurements and precise ground truth, facilitating both learning-based and classical navigation algorithm development.

Findings

Dataset includes 1200+ inertial measurement sets.

Data collected over trajectories up to 10 minutes long.

Ground truth accuracy achieved with foot-mounted sensors.

Abstract

This paper presents the large and diverse dataset for development of smartphone-based pedestrian navigation algorithms. This dataset consists of about 1200 sets of inertial measurements from sensors of several smartphones. The measurements are collected while walking through different trajectories up to 10 minutes long. The data are accompanied by the high accuracy ground truth collected with two foot-mounted inertial measurement units and post-processed by the presented algorithms. The dataset suits both for training of intellectual pedestrian navigation algorithms based on learning techniques and for development of pedestrian navigation algorithms based on classical approaches. The dataset is accessible at http://gartseev.ru/projects/ipin2019.