Car design is a complex and private process that can take years. The details of aerodynamics testing are typically kept secret, leading to slow advancements in fuel efficiency and electric vehicle range across the automotive industry. MIT engineers have developed the largest open-source dataset for car aerodynamics, called DrivAerNet++, which includes over 8,000 realistic car designs and detailed aerodynamics data. This dataset can be used to train AI models to quickly generate novel car designs that are optimized for better performance, ultimately leading to more fuel-efficient cars and electric vehicles with longer ranges in a fraction of the time it currently takes.
https://news.mit.edu/2024/design-future-car-with-8000-design-options-1205