Section: New Results

LIDAR-Based perception For Vehicle Localization in an HD Map

Participants : Farouk Ghallabi, Fawzi Nashashibi.

Self-vehicle localization is one of the fundamental tasks for autonomous driving. Most of current techniques for global positioning are based on the use of GNSS (Global Navigation Satellite Systems). However, these solutions do not provide a localization accuracy that is better than 2-3 m in open sky environments. Alternatively, the use of maps has been widely investigated for localization since maps can be pre-built very accurately. State of the art approaches often use dense maps or feature maps for localization. This year, we tackled to problems:

• In [14] we proposed a road sign perception system for vehicle localization within a third party map. This is challenging since third party maps are usually provided with sparse geometric features, which makes the localization task more difficult in comparison to dense maps. Experiments have been conducted on a Highway-like test track using GNSS/INS with RTK corrections as ground truth (GT).

• In [15] High Reflective Landmarks (HRL) - such as lane markings, road signs and guard rail reflectors (GRR) - are detected from a 3D point cloud. A particle filtering algorithm estimates the position of the vehicle by matching observed HRLs with HD map attributes. Experiments have been conducted on a highway-like test track using GNSS/INS with RTK corrections as a ground truth (GT). Error evaluations are given as cross-track (CT) and along-track (AT) errors defined in the curvilinear coordinates related to the map. The obtained accuracies of the localization system is 18 cm for the cross-track error and 32 cm for the along-track error.