Data for The MagPIE2 Dataset: Magnetic Field-Based Mapping, Localization, and SLAM
Dataset Description |
If you use this dataset, please cite both the dataset and the associated data paper (bibtex is below). @ARTICLE{11386847,
We present a dataset for the evaluation of magnetic field-based robotic and pedestrian localization, mapping, and SLAM methods. This dataset contains magnetometer and inertial measurement unit data collected from inside three buildings both a pedestrian and a ground robot. Data were collected at different heights simultaneously, both with and without changes in the placement of objects that may affect magnetometer measurements. In total, approximately 689 square meters of floor space was covered by this dataset.
Note that while the dataset is meant to be permanently stored, this forum is not meant to guarantee perennial support and its existence will be dependent on the policies of GitHub. How is the dataset organized? The data is divided into the following parts at a high level and more detailed information can be found in the Readme: 1. The walking portion of the dataset: CSL_WLK.zip, DCL_WLK.zip, Talbot_WLK.zip, and WLK_Misc.zip.
How is data recorded and stored? Data is generally collected in the form of ROS bag files. Each ROS bag has Intel Realsense camera images, magnetometer readings, IMU readings, timestamps, and more as applicable for each file in the dataset. Each bag file has an associated metadata file written as a YAML file. This contains general information about each bag file including the start and stop time, who collected the bag file (during the pedestrian portion of the dataset), and the approximate location where data was collected. In several cases, additional comma separated (csv) files of the dataset where included either as a convenient supplement to ROS bag files (e.g., csv files of magnetometer calibration data) or because they serve as human readable quick start results. How does one set up and run files on the dataset? The files are stored in ROS bags and are, therefore, meant to be run using the Robot Operating System. Information regarding how to use the Robot Operating System as well as installation instructions are available at: https://ros.org/ |
Subject |
Technology and Engineering |
Keywords |
Localization; mapping; SLAM; dataset; benchmark; magnetometer; magnetic field |
License |
CC BY |
Corresponding Creator |
David Hanley |
Downloaded |
45 times |
| Version | DOI | Comment | Publication Date |
|---|---|---|---|
| 1 | 10.13012/B2IDB-0228701_V1 | 2026-02-11 |
Contact the Research Data Service for help interpreting this log.
| Dataset | update: {"all_globus"=>[nil, true]} | 2026-02-12T13:31:04Z |
| Dataset | update: {"all_medusa"=>[nil, true]} | 2026-02-12T06:15:08Z |
| RelatedMaterial | create: {"material_type"=>"Article", "availability"=>nil, "link"=>"https://doi.org/10.1109/TIM.2026.3662919", "uri"=>"10.1109/TIM.2026.3662919", "uri_type"=>"DOI", "citation"=>"D. Hanley, J. Lee, S. Y. Choi and T. Bretl, \"The MagPIE2 Dataset for Mapping, Localization, and Simultaneous Localization and Mapping Using Magnetic Fields,\" in IEEE Transactions on Instrumentation and Measurement, doi: https://doi.org/10.1109/TIM.2026.3662919", "dataset_id"=>2724, "selected_type"=>"Article", "datacite_list"=>"IsSupplementTo", "note"=>nil, "feature"=>nil} | 2026-02-11T15:16:23Z |
| Dataset | update: {"description"=>["If you use this dataset, please cite both the dataset and the associated data paper (bibtex is below).\r\n\r\n@article{doi:tbd,\r\nauthor = {David Hanley and Jongwon Lee and Su Yeon Choi and Timothy Bretl},\r\ntitle ={The MagPIE2 Dataset: Magnetic Field-Based Mapping, Localization, and SLAM},\r\njournal = {TBD},\r\nvolume = {TBD},\r\nnumber = {TBD},\r\npages = {TBD},\r\nyear = {TBD},\r\ndoi = {TBD},\r\nURL = {TBD}\r\n}\r\n\r\nWe present a dataset for the evaluation of magnetic field-based robotic and pedestrian localization, mapping, and SLAM methods. This dataset contains magnetometer and inertial measurement unit data collected from inside three buildings both a pedestrian and a ground robot. Data were collected at different heights simultaneously, both with and without changes in the placement of objects that may affect magnetometer measurements. In total, approximately 689 square meters of floor space was covered by this dataset.\r\n\t\r\nThis dataset is archivally stored. We provide a GitHub site which is meant to serve as a forum to post issues with the dataset, share code using the dataset, and to resolve problems: <a href=\"https://github.com/hanley6/MagPIE2Forum\">https://github.com/hanley6/MagPIE2Forum</a>\r\n\r\nNote that while the dataset is meant to be permanently stored, this forum is not meant to guarantee perennial support and its existence will be dependent on the policies of GitHub.\r\n\r\n<b>How is the dataset organized?</b> The data is divided into the following parts at a high level and more detailed information can be found in the Readme:\r\n\r\n1. The walking portion of the dataset: CSL_WLK.zip, DCL_WLK.zip, Talbot_WLK.zip, and WLK_Misc.zip.\r\n2. The robot portion of the dataset: Robot_Dataset.zip.\r\n3. Motor interference tests: Motor_Interference_Test.zip.\r\n4. Ground truth evaluation: Ground_Truth_Evaluation.zip.\r\n5. Quick start results: Quick_Start_Results.zip. \r\n\r\n<b>How is data recorded and stored?</b> Data is generally collected in the form of ROS bag files. Each ROS bag has Intel Realsense camera images, magnetometer readings, IMU readings, timestamps, and more as applicable for each file in the dataset. Each bag file has an associated metadata file written as a YAML file. This contains general information about each bag file including the start and stop time, who collected the bag file (during the pedestrian portion of the dataset), and the approximate location where data was collected. In several cases, additional comma separated (csv) files of the dataset where included either as a convenient supplement to ROS bag files (e.g., csv files of magnetometer calibration data) or because they serve as human readable quick start results.\r\n\r\n<b>How does one set up and run files on the dataset?</b> The files are stored in ROS bags and are, therefore, meant to be run using the Robot Operating System. Information regarding how to use the Robot Operating System as well as installation instructions are available at: <a href=\"https://ros.org/\">https://ros.org/</a>", "If you use this dataset, please cite both the dataset and the associated data paper (bibtex is below).\r\n\r\n@ARTICLE{11386847,\r\n author={Hanley, David and Lee, Jongwon and Choi, Su Yeon and Bretl, Timothy},\r\n journal={IEEE Transactions on Instrumentation and Measurement}, \r\n title={The MagPIE2 Dataset for Mapping, Localization, and Simultaneous Localization and Mapping Using Magnetic Fields}, \r\n year={2026},\r\n volume={},\r\n number={},\r\n pages={1-1},\r\n keywords={Magnetometers;Magnetic field measurement;Magnetic fields;Pedestrians;Location awareness;Buildings;Simultaneous localization and mapping;Measurement errors;Hardware;Calibration;Localization;mapping;SLAM;dataset;benchmark;magnetometer;magnetic field},\r\n doi={10.1109/TIM.2026.3662919}}\r\n\r\nWe present a dataset for the evaluation of magnetic field-based robotic and pedestrian localization, mapping, and SLAM methods. This dataset contains magnetometer and inertial measurement unit data collected from inside three buildings both a pedestrian and a ground robot. Data were collected at different heights simultaneously, both with and without changes in the placement of objects that may affect magnetometer measurements. In total, approximately 689 square meters of floor space was covered by this dataset.\r\n\t\r\nThis dataset is archivally stored. We provide a GitHub site which is meant to serve as a forum to post issues with the dataset, share code using the dataset, and to resolve problems: <a href=\"https://github.com/hanley6/MagPIE2Forum\">https://github.com/hanley6/MagPIE2Forum</a>\r\n\r\nNote that while the dataset is meant to be permanently stored, this forum is not meant to guarantee perennial support and its existence will be dependent on the policies of GitHub.\r\n\r\n<b>How is the dataset organized?</b> The data is divided into the following parts at a high level and more detailed information can be found in the Readme:\r\n\r\n1. The walking portion of the dataset: CSL_WLK.zip, DCL_WLK.zip, Talbot_WLK.zip, and WLK_Misc.zip.\r\n2. The robot portion of the dataset: Robot_Dataset.zip.\r\n3. Motor interference tests: Motor_Interference_Test.zip.\r\n4. Ground truth evaluation: Ground_Truth_Evaluation.zip.\r\n5. Quick start results: Quick_Start_Results.zip. \r\n\r\n<b>How is data recorded and stored?</b> Data is generally collected in the form of ROS bag files. Each ROS bag has Intel Realsense camera images, magnetometer readings, IMU readings, timestamps, and more as applicable for each file in the dataset. Each bag file has an associated metadata file written as a YAML file. This contains general information about each bag file including the start and stop time, who collected the bag file (during the pedestrian portion of the dataset), and the approximate location where data was collected. In several cases, additional comma separated (csv) files of the dataset where included either as a convenient supplement to ROS bag files (e.g., csv files of magnetometer calibration data) or because they serve as human readable quick start results.\r\n\r\n<b>How does one set up and run files on the dataset?</b> The files are stored in ROS bags and are, therefore, meant to be run using the Robot Operating System. Information regarding how to use the Robot Operating System as well as installation instructions are available at: <a href=\"https://ros.org/\">https://ros.org/</a>"]} | 2026-02-11T15:16:23Z |