Filtering distributed information to build a plausible scene for autonomous and connected vehicles
| Autor: | Hanna Klaudel, Guillaume Hutzler, Abderrahmane Sali |
|---|---|
| Přispěvatelé: | Informatique, BioInformatique, Systèmes Complexes (IBISC), Université d'Évry-Val-d'Essonne (UEVE)-Université Paris-Saclay |
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
Value (ethics)
sensor fusion Computer science business.industry Autonomous vehicles Confidence 02 engineering and technology Machine learning computer.software_genre Sensor fusion Consistency (database systems) [INFO.INFO-PF]Computer Science [cs]/Performance [cs.PF] plausibility [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing Feature (computer vision) Order (exchange) 020204 information systems 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Relevance (information retrieval) Artificial intelligence Representation (mathematics) business computer |
| Zdroj: | 17th International Conference on Distributed Computing and Artificial Intelligence (DCAI 2020) 17th International Conference on Distributed Computing and Artificial Intelligence (DCAI 2020), Oct 2020, L'Aquila, Italy. pp.89--101, ⟨10.1007/978-3-030-53036-5_10⟩ Advances in Intelligent Systems and Computing ISBN: 9783030530358 DCAI |
| Popis: | International audience; To make their decisions, autonomous vehicles need to build a reliable representationof their environment. In the presence of sensors that are redundant, but not necessarilyequivalent, that may get unreliable, unavailable or faulty, or that may get attacked, it is offundamental importance to assess the plausibility of each information at hand. To this end,we propose a model that combines four criteria (relevance, trust, freshness and consistency)in order to assess the confidence in the value of a feature, and to select the values that aremost plausible.We show that it enables to handle various difficult situations (attacks, failures,etc.), by maintaining a coherent scene at any time despite possibly major defects. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|