End-to-End Probabilistic Ego-Vehicle Localization Framework

• Published in: IEEE transactions on intelligent vehicles Vol. 6; no. 1; pp. 146 - 158
• Main Authors: Kasmi, Abderrahim, Laconte, Johann, Aufrere, Romuald, Denis, Dieumet, Chapuis, Roland
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.03.2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE); Institute of Electrical and Electronics Engineers
• Subjects: Automatic; Autonomous vehicle; Autonomous vehicles; Bayesian analysis; Consumer goods; Digital mapping; Engineering Sciences; Feature extraction; fusion framework; Global Positioning System; Hidden Markov models; lane marking; Localization; Localization method; map matching; Markov chains; Receivers; road prior; Roads; Task analysis; localization; lane marking; map matching; Autonomous vehicle; road prior; fusion framework
• ISSN: 2379-8858; 2379-8904; 2379-8904
• DOI: 10.1109/TIV.2020.3017256

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.