A Multi-Platform Framework for Artificial Intelligence Engines in Automotive Systems

It is becoming increasingly evident that data science and artificial intelligence are key technologies in the future of automotive industry. Artificial Intelligence (AI) successes are significant, with some limitations in terms of algorithms portability and code industrialization for mass production and deployment. This is because there are many domains where several software development process standards need to be applied. The approach presented in this paper tries to overcome this issue by creating a unique platform with multiple artificial intelligence engines. By using state-of-the-art AI libraries, together with target-independent software, tackles the challenge of driving context recognition in embedded systems, and uses it as a validation method.