End-to-End Probabilistic Ego-Vehicle Localization Framework
| Autor: | Dieumet Denis, Johann Laconte, Abderrahim Kasmi, Romuald Aufrère, Roland Chapuis |
|---|---|
| Přispěvatelé: | Institut Pascal (IP), SIGMA Clermont (SIGMA Clermont)-Université Clermont Auvergne [2017-2020] (UCA [2017-2020])-Centre National de la Recherche Scientifique (CNRS), SherpaEngineering, R&DDepartment, Nanterre |
| Rok vydání: | 2021 |
| Předmět: |
Autonomous vehicle
Control and Optimization road prior Computer science Feature extraction fusion framework 02 engineering and technology computer.software_genre localization [SPI.AUTO]Engineering Sciences [physics]/Automatic [SPI]Engineering Sciences [physics] End-to-end principle Artificial Intelligence Robustness (computer science) 11. Sustainability 0502 economics and business 0202 electrical engineering electronic engineering information engineering Hidden Markov model 050210 logistics & transportation business.industry 05 social sciences Probabilistic logic Process (computing) Bayesian network lane marking map matching Automotive Engineering Global Positioning System 020201 artificial intelligence & image processing Data mining business computer |
| Zdroj: | IEEE Transactions on Intelligent Vehicles IEEE Transactions on Intelligent Vehicles, Institute of Electrical and Electronics Engineers, 2020, pp.1-1. ⟨10.1109/TIV.2020.3017256⟩ IEEE Transactions on Intelligent Vehicles, 2020, pp.1-1. ⟨10.1109/TIV.2020.3017256⟩ |
| ISSN: | 2379-8904 2379-8858 |
| DOI: | 10.1109/tiv.2020.3017256 |
| Popis: | International audience; 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|