LAVA: A Methodology for Leveraging Aggregated Vehicle Analytics

Driver Assist Technologies are complex systems for which it can be difficult to objectively estimate customer experience in a repeatable and quantitative manner. We must assess the designed feature operation at a massive scale to better understand the eventual customer impact and cost of a variety of engineering decisions. We will present the Leveraging Aggregated Vehicle Analytics (LAVA) methodology for improved understanding of the impact of these dynamic and subjective problems by utilizing connected vehicle (CV) data. Several examples of the LAVA methodology will be discussed and examined in detail. Using the LAVA methodology, minimal and anonymized data collected from CVs can be used to answer many engineering decision questions with high confidence in a controlled and scientific manner.