Lane Level Positioning Method for Unmanned Driving Based on Inertial System and Vector Map Information Fusion Applicable to GNSS Denied Environments

Abstract

With the development of vehicle sensors, unmanned driving has become a research hotspot. Positioning is also considered to be one of the most challenging directions in this field. Aiming at the poor positioning accuracy of vehicles under GNSS denied environments, a lane-level positioning method based on inertial system and vector map information fusion is proposed. A dead reckoning model based on optical fiber IMU and odometer is established, and its positioning error is regarded as a priori information. Furthermore, a map matching model based on HMM is built up. Three validation experiments are carried out and experimental results show that the positioning error can be reduced to less than 30 cm when driving for about 7 min, which proves the effectiveness of the proposed method. Our work may provide a reference for the further improvement of positioning for unmanned driving under GNSS denied environments.

A Comparative Experimental Performance Assessment of RTK+OSNMA-Based Positioning for Road Vehicle Applications

“…Totals 72.62% of the OSNMA strict solutions, 86.75% of the OSNMA loose solutions, and 86.86% of the OSNMA off solutions had an accuracy of better than 2 cm. These results show that under open sky conditions a vehicle can safely be guided within a traffic-lane, and this is also in agreement with [27][28][29].…”

Relative Localization within a Quadcopter Unmanned Aerial Vehicle Swarm Based on Airborne Monocular Vision

“…UAV swarms, as multi-intelligence systems, should also have the ability to achieve relative localization without relying on external facilities or information. Similar functions have already been implemented in the rapidly developing field of advanced driving assistance system (ADAS) research [16,17]. Based on the information provided by vision, laser, and other sensors, it has been possible to achieve accurate relative positioning of objects within a certain range while the vehicle is in motion.…”