THÖR-MAGNI DATASET

Tracking Human Motion at Örebro University

THÖR-MAGNI is a public dataset of human motion trajectories, recorded in a controlled indoor experiment.

About

We present THÖR-MAGNI: a dataset of motion trajectories aligned with eye tracking data with diverse and accurate social human motion data in a shared indoor environment. We provide five distinct scenarios, that enable users to study various human activities and human motion in the presence of navigating robots and during interactions with them.

Overview

  • THÖR-MAGNI follows the same data collection protocol as in THÖR
  • Multiple recordings over several days, including 5 different scenarios: over 3.5 more trajectories than its predecessor THÖR
  • High variety and meaningful human activities, social interactions between individuals and a mobile robot, in different layouts with static obstacles
  • Map of static obstacles, goal coordinates, grouping information, and human activities
  • Accurate data for 3D position and 3D head orientation, recorded with a motion capture system at 100 Hz
  • Eye gaze data at 50 Hz with the gaze-overlaid first-person video at 25 Hz aligned with the other sensor modalities
  • 3D LiDAR scans and RGB video captured by sensors onboard a mobile robot

Updates

  • 23.01.2024 The THÖR-MAGNI dataset is published online

Setup

Data

Overview

THÖR-MAGNI dataset is a novel data collection of accurate human and robot navigation and interaction in diverse indoor contexts, building on the previous THÖR dataset protocol. We provide position and head orientation motion capture data, eye gaze tracking, 3D LiDAR scans and RGB data onboard a mobile robot. In total, THÖR-MAGNI captures 3.5 hours of motion of 40 participants on 5 recording days. This data collection is designed around systematic variation of factors in the environment to allow building cue-conditioned models of human motion and verifying hypotheses on factor impact.



Tools

Additionally, we provide a set of data visualization tools, including a dashboard, and introduce a specialized Python package thor-magni-tools. This package is designed to facilitate the filtering and preprocessing of raw trajectory data, enhancing the accessibility and usability of the THÖR-MAGNI dataset.

Downloads

You can find all the data files of our dataset and how to download them in our repository: THÖR-MAGNI data repository

License

Cite

Please use this citation when referencing THÖR-MAGNI:


@article{schreiter2022magni,
  title={The magni human motion dataset: Accurate, complex, multi-modal, natural, semantically-rich and contextualized},
  author={Schreiter, Tim and de Almeida, Tiago Rodrigues and Zhu, Yufei and Maestro, Eduardo Gutierrez and Morillo-Mendez, Lucas and Rudenko, Andrey and Kucner, Tomasz P and Mozos, Oscar Martinez and Magnusson, Martin and Palmieri, Luigi and others},
  journal={arXiv preprint arXiv:2208.14925},
  year={2022}
}
                                

Find out more in the IEEE RO-MAN 2022 Workshop Proceedings publication: https://arxiv.org/abs/2208.14925

Authors

Please contact us with any feedback, questions, or comments by email.

Tim Schreiter


tim.schreiter@oru.se

AASS Research Centre
School of Science and Technology
Örebro University
70182 Örebro, Sweden

https://www.oru.se/english/employee/tim_schreiter/

Tiago Almeida


tiago.almeida@oru.se

AASS Research Centre
School of Science and Technology
Örebro University
70182 Örebro, Sweden

https://www.oru.se/english/employee/tiago_almeida/

Yufei Zhu


yufei.zhu@oru.se

AASS Research Centre
School of Science and Technology
Örebro University
70182 Örebro, Sweden

https://www.oru.se/english/employee/yufei_zhu/

Eduardo
Gutierrez Maestro


eduardo.gutierrez-maestro@oru.se

AASS Research Centre
School of Science and Technology
Örebro University
70182 Örebro, Sweden

https://www.oru.se/english/employee/eduardo_gutierrez-maestro/

Lucas
Morillo-Mendez


lucas.morillo@oru.se

AASS Research Centre
School of Science and Technology
Örebro University
70182 Örebro, Sweden

https://www.oru.se/english/employee/lucas_morillo/

Andrey Rudenko


andrey.rudenko@de.bosch.com

Bosch Corporate Research
71272 Renningen, Germany

https://rudenkoandrey.github.io

Tomasz Piotr Kucner


tomasz.kucner@aalto.fi

Department of Electrical Engineering and Automation Aalto University
Espoo, Finnland

https://people.aalto.fi/tomasz.kucner/

Martin Magnusson


martin.magnusson@oru.se

AASS Research Centre
School of Science and Technology
Örebro University
70182 Örebro, Sweden

https://www.oru.se/personal/martin_magnusson/

Luigi Palmieri


luigi.palmieri@de.bosch.com

Bosch Corporate Research
71272 Renningen, Germany

Achim J. Lilienthal


achim.lilienthal@oru.se

AASS Research Centre
School of Science and Technology
Örebro University
70182 Örebro, Sweden

https://www.professoren.tum.de/lilienthal-achim

Funding

Darko

This work was partially supported by Darko Project, an international research project on dynamic agile production robots that learn and optimise knowledge and operations.


WASP

This work was partially supported by the Wallenberg AI, Autonomous Systems and Software Program (WASP) funded by the Knut and Alice Wallenberg Foundation.