Organization of ML-based product development as per ISO 26262

Machine learning (ML) applications generate a continuous stream of success stories from various domains. ML enables many novel applications, also in a safety-related context. With the advent of Autonomous Driving, ML gets used in automotive domain. In such a context, ML-based systems are safety-related. In the automotive industry, the applicable functional safety standard is ISO 26262, which it does not cover specific aspects of ML. In a safety-related ML project, all ISO 26262 work products are typically necessary and have to be delivered. However, specific aspects of ML (like data set requirements, special analyses for ML) must be addressed within some work products. In this paper, we propose how the organization of a ML project could be done according to ISO 26262 phases, sub-phases and work-products.