StickyLocalization: Robust End-To-End Relocalization on Points Clouds using Graph Neural Networks

Kai Fischer, Martin Simon, Stefan Milz, Patrick Mäder

Abstract:

Relocalization inside pre-built maps provides a big benefit
in the course of today’s autonomous driving tasks where the
map can be considered as an additional sensor for refining
the estimated current pose of the vehicle. Due to potentially
large drifts in the initial pose guess as well as maps con-
taining unfiltered dynamic and temporal static objects (e.g.
parking cars), traditional methods like ICP tend to fail and
show high computation times. We propose a novel and fast
relocalization method for accurate pose estimation inside
a pre-built map based on 3D point clouds. The method is
robust against inaccurate initialization caused by low perfor-
mance GPS systems and tolerates the presence of unfiltered
objects by specifically learning to extract significant features
from current scans and adjacent map sections. More specif-
ically, we introduce a novel distance-based matching loss
enabling us to simultaneously extract important information
from raw point clouds and aggregating inner- and inter-
cloud context by utilizing self- and cross-attention inside a
Graph Neural Network. We evaluate StickyLocalization’s
(SL) performance through an extensive series of experiments
using two benchmark datasets in terms of Relocalization
on NuScenes and Loop Closing using KITTI’s Odometry
dataset. We found that SL outperforms state-of-the art point
cloud registration and relocalization methods in terms of
transformation errors and runtime.