Freetures: Localization in Signed Distance Function Maps
This work addresses localization for robotics, offering a novel method that improves performance over existing techniques, though it is incremental in its application to SDF maps.
The paper tackles the problem of robotic localization in previously mapped environments by proposing a system that extracts features directly from Signed Distance Function (SDF) maps, which allows utilization of both surface and free-space information. It demonstrates an average improvement of ~12% on an RGB-D dataset and ~18% on a LiDAR-based dataset over state-of-the-art handcrafted surface-only descriptors.
Localization of a robotic system within a previously mapped environment is important for reducing estimation drift and for reusing previously built maps. Existing techniques for geometry-based localization have focused on the description of local surface geometry, usually using pointclouds as the underlying representation. We propose a system for geometry-based localization that extracts features directly from an implicit surface representation: the Signed Distance Function (SDF). The SDF varies continuously through space, which allows the proposed system to extract and utilize features describing both surfaces and free-space. Through evaluations on public datasets, we demonstrate the flexibility of this approach, and show an increase in localization performance over state-of-the-art handcrafted surfaces-only descriptors. We achieve an average improvement of ~12% on an RGB-D dataset and ~18% on a LiDAR-based dataset. Finally, we demonstrate our system for localizing a LiDAR-equipped MAV within a previously built map of a search and rescue training ground.