Morocco Visual Inertial Navigation Data Set - MADMAX

The Institute of Robotics and Mechatronics was part of the PERASPERA Space Robotics Technologies Cluster in the operational grants OG3 and OG6. In that context, the research group participated in the 2018 November/December field test in the Moroccan desert close to the city of Erfoud.

Apart from the participation in PERASPERA, many other datasets for testing of autonomous navigation algorithms were recorded by our research group at several very distinctive sites in an Mars-analogue-environment. There, we used our compact human‐portable DLR Sensor Unit for Planetary Exploration Rovers (SUPER) to record the Morocco‐Acquired data set of Mars‐Analog eXploration (MADMAX).

MADMAX contains:

36 different navigation experiments, captured at eight Mars analog sites of widely varying environmental conditions. Its longest trajectory covers 1.5 km and the combined trajectory length is 9.2 km. The data set contains time‐stamped recordings from monochrome stereo cameras, a color camera, omnidirectional cameras in stereo configuration, and from an inertial measurement unit.
the ground truth in position and orientation together with the associated uncertainties, obtained by a real‐time kinematic‐based algorithm that fuses the global navigation satellite system data of two body antennas.
the navigation performance of two state‐of‐the‐art navigation algorithms, ORB‐SLAM2 and VINS‐mono with our data. This provides a navigation baseline (benchmark), which can be used as a performance reference of accuracy and robustness for other navigation algorithms.

The data can be accessed under: https://datasets.arches-projekt.de/morocco2018/.

The Sensor Unit for Planetary Exploration Rovers (SUPER) in the Morocco Desert: it can be either carried by a human operator (foreground) or be mounted on a roboter - here on the SherpaTT rover of the DFKI Robotics Innovation Center (background)

Publication

Lukas Meyer, Michal Smíšek, Alejandro Fontan Villacampa, Laura Oliva Maza, Daniel Medina, Martin J. Schuster, Florian Steidle, Mallikarjuna Vayugundla, Marcus G. Müller, Bernhard Rebele, Armin Wedler, and Rudolph Triebel, "The MADMAX data set for visual‐inertial rover navigation on Mars", Journal of Field Robotics (JFR), 1– 21, March 2021, doi: 10.1002/rob.22016, [elib]