Lane marking aided vehicle localization

Zui Tao (1) , Philippe Bonnifait (1) , Vincent Fremont (1) , Javier Ibañez-Guzman (2)

1 Heudiasyc - Heuristique et Diagnostic des Systèmes Complexes [Compiègne]
2 Technocentre Renault [Guyancourt]

A localization system that exploits L1-GPS estimates, vehicle data, and features from a video camera as well as lane markings embedded in digital navigation maps is presented. A sensitivity analysis of the detected lane markings is proposed in order to quantify both the lateral and longitudinal errors caused by 2D-world hypothesis violation. From this, a camera observation model for vehicle localization is proposed. The paper presents also a method to build a map of the lane markings in a first stage. The solver is based on dynamical Kalman filtering with a two-stage map-matching process which is described in details. This is a software-based solution using existing automotive components. Experimental results in urban conditions demonstrate an significant increase in the positioning quality.

Mots clés: Localization; Mobile mapping; camera observation model

Domaines: Robotique [cs.RO]

Zui Tao, Philippe Bonnifait, Vincent Fremont, Javier Ibañez-Guzman. Lane marking aided vehicle localization. IEEE 16th International Conference on Intelligent Transportation Systems (ITSC 2013), Oct 2013, Hague, Netherlands. pp.1509-1515. ⟨hal-00880631⟩