Case Study
Thursday, September 29
11:30 AM - 12:00 PM
Live in Berlin
Less Details
Machine learning is a set of tools that enables computers to learn a task by using data and not by being explicitly programmed or defined through human-understandable rules [ISO 4804:2020]. In automotive industry, data driven Machine Learning (ML) approaches are actively used for developing Automated Driving (AD) systems. When ML modules executing safety tasks (e.g., environmental perception, situation interpretation, trajectory planning, etc.) enter public road test or series production cars, establishing justified confidence in ML forms a core part of the safety case for these systems [Frtunikj et al. 2019].
Aligned with system safety principles in AD, ML must undergo safety assurance, safety argument and assessment for safety relevant applications. The presentation proposes recommendations on safety assurance of ML. As one part of system safety engineering, safety assurance of ML needs to focus on:
Groupe Renault has been making cars since 1898. Today it is an international multi-brand group, selling close to 3.76 million vehicles in 127 countries in 2017, with 36 manufacturing sites, 12,700 points of sales and employing more than 120,000 people. To meet the major technological challenges of the future and continue its strategy of profitable growth, the Group is harnessing its international growth and the complementary fit of its five brands, Renault, Dacia and Renault Samsung Motors, Alpine and LADA, together with electric vehicles and the unique Alliance with Nissan and Mitsubishi. With a new team in Formula 1 and a strong commitment to Formula E, Renault sees motorsport as a vector of innovation and brand awareness.