Abstract
Locating the vehicle in its road is a critical part of any autonomous vehicle system and has been subject to different research topics. In most works presented in the literature, ego-localization is split into three parts: Road level-localization consisting in the road on which the vehicle travels, Lane level localization which is the lane on which the vehicle travels, and Ego lane level localization being the lateral position of the vehicle in the ego-lane. For each part, several researches have been conducted. However, the relationship between the different parts has not been taken into consideration. Through this work, an end-to-end ego-localization framework is introduced with two main novelties. The first one is the proposition of a complete solution that tackles every part of the ego-localization. The second one lies in the information-driven approach used. Indeed, we use prior about the road structure from a digital map in order to reduce the space complexity for the recognition process. Besides, several fusion framework techniques based on Bayesian Network and Hidden Markov Model are elaborated leading to an ego-localization method that is, to a large extent, robust to erroneous sensor data. The robustness of the proposed method is proven on different datasets in varying scenarios.
Highlights
O VER the past decades, the automotive industry has been growing strongly
The lack of accuracy provided by a classic GPS that can be caused by poor satellite signals, high degree dilution of precision, or multi-path in urban scenes, is first compensated with proprioceptive sensors, such as Inertial Measurement Unit (IMU)
In an attempt to provide a more robust and more accurate localization, the trend for manufacturers and researchers is to equip the ego-vehicle with multiple sensors such as Velodyne lidars, multiples cameras, inertial measurement unit (IMU) and high defined digital map that contains the precise location of high features such as the lane marking or landmarks [32]
Summary
O VER the past decades, the automotive industry has been growing strongly. The demand for the driver and pedestrians security coupled with the technological advances are the main factors behind this exponential growth. The main mission of these systems is to ensure that driver safety is constantly guaranteed For this purpose, multiple applications have been deployed, such as lane departure warning, lane keeping assist, pedestrian detection, collision avoidance, or lane change assist system. Multiple applications have been deployed, such as lane departure warning, lane keeping assist, pedestrian detection, collision avoidance, or lane change assist system To achieve this mission, the faultless knowledge of the localization of the ego-vehicle with regards to the surrounding environment is necessary. For some applications like lane-keeping, knowing the road on which the vehicle is traveling is not sufficient These systems must be informed about the position of the host lane in the road to provide the adequate maneuver instruction and maintain the vehicle safety. In this work, an end-to-end solution for egolocalization from Road level localization to Ego-lane level localization is presented
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
