ROOAD: RELLIS Off-road Odometry Analysis Dataset
share
The development and implementation of visual-inertial odometry (VIO) has focused on structured environments, but interest in localization in off-road environments is growing. In this paper, we present the ROOAD which provides high-quality, time-synchronized off-road monocular visual-inertial data sequences to further the development of related research. We exhibit the 2-30x worse performance of two established VIO implementations, OpenVINS and VINS-Fusion, when stable, and the former is less prone to estimation divergences on our data sequences. The accuracy and repeatability of Kalibr's IMU-camera extrinsics calibration tool is measured to be +/-1 degrees for orientation and +/-1mm at best (left-right) and +/-10mm (depth) at worse for position estimation in the camera frame. This novel dataset provides a new set of scenarios for researchers to design and test their localization algorithms on, as well as critical insights in the current performance of VIO off-road. ROOAD Dataset: github.com/unmannedlab/ROOAD
READ FULL TEXT
