Abstract
This research proposes an accurate vehicular positioning system which can achieve lane-level performance in urban canyons. Multiple passive sensors, which include Global Navigation Satellite System (GNSS) receivers, onboard cameras and inertial sensors, are integrated in the proposed system. As the main source for the localization, the GNSS technique suffers from Non-Line-Of-Sight (NLOS) propagation and multipath effects in urban canyons. This paper proposes to employ a novel GNSS positioning technique in the integration. The employed GNSS technique reduces the multipath and NLOS effects by using the 3D building map. In addition, the inertial sensor can describe the vehicle motion, but has a drift problem as time increases. This paper develops vision-based lane detection, which is firstly used for controlling the drift of the inertial sensor. Moreover, the lane keeping and changing behaviors are extracted from the lane detection function, and further reduce the lateral positioning error in the proposed localization system. We evaluate the integrated localization system in the challenging city urban scenario. The experiments demonstrate the proposed method has sub-meter accuracy with respect to mean positioning error.
Highlights
Vehicle self-localization in urban environment is a challenging but significant topic for autonomous driving and driving assistance
Passive sensors such as Global Navigation Satellite System (GNSS) receivers and vision sensors collect signals, radiation, or light from the environment, while the active sensors have transmitters, which can send out light waves, electrons or signals
In order to mitigate the NLOS and multipath effects while reducing the Horizontal Dilution of Precision (HDOP) distortion, we proposed a candidate distribution based positioning method using a 3D building map (3D-GNSS) [19,20,21]. 3D-GNSS takes the advantage of 3D building map to rectify the pseudorange error caused by NLOS and multiple effects
Summary
Vehicle self-localization in urban environment is a challenging but significant topic for autonomous driving and driving assistance. In order to mitigate the NLOS and multipath effects while reducing the HDOP distortion, we proposed a candidate distribution based positioning method using a 3D building map (3D-GNSS) [19,20,21]. The stop line detection function was employed to reduce the longitudinal error in localization as well [47,48] All of these researches proposed to use the sensing technology to improve the positioning accuracy. Different with those related works, this paper focuses on the problem of vehicle self-localization in the most challenging environment, a city urban environment, and improves the positioning Speenrsofrosr2m01a5n, 1c5e, pfraogme–ptawgeo aspects: both GNSS positioning technology and sensor integration. We adopt the multiple satellite systems in 3D-GNSS, which includes GPS, and GLObal NAvigation Satellite System (GLONASS) and Quasi Zenith Satellite System (QZSS)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
