Towards a Data-Centric Architecture in the Automotive Industry
| Autor: | Daniel Alvarez-Coello, Adnan Bekan, Jorge Marx Gómez, Daniel Wilms |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
business.industry
Computer science Automotive industry 020206 networking & telecommunications Context (language use) 02 engineering and technology Data science Database-centric architecture Data modeling Variety (cybernetics) Software Conceptual design Analytics 0202 electrical engineering electronic engineering information engineering General Earth and Planetary Sciences Factory (object-oriented programming) 020201 artificial intelligence & image processing Data architecture business General Environmental Science |
| DOI: | 10.13140/rg.2.2.13954.09924 |
| Popis: | Vehicle software architectures have been evolving over the last twenty years to support data-driven functionalities. Several enterprises from different domains are currently focusing on improving their data architectures by re-defining the underlying data models to enable core support for analytics and artificial intelligence. Moreover, a common desire to add clear data provenance and explicit context impulses the field of semantics and knowledge graphs. Nevertheless, in the automotive industry, the scenario of connected vehicles implies extra complexity. Vehicle data has an enormous variety, making it essential to develop and adopt standards. This paper presents aspects of ongoing research at the BMW Research Department regarding a conceptual design for vehicle software architectures in the automotive industry. We discuss the principles of a modern data architecture with particular emphasis on the data-centric mindset. We also explore the current challenges and possible working points as the foundation to move from siloed data towards a so-called AI factory. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|