Skip to content

MIT: open-source dataset turbocharges AI-driven EV design

MIT states its open-source library of 8,000 car designs can train AI models to produce the next generation of electric vehicles. By Will Girling

SUVs have enjoyed a surge in popularity around the world in recent years. They constituted 48% of global car sales in 2023 and 55% of new electric vehicle (EV) registrations, according to the International Energy Agency. The reasons include a growing cultural preference for larger vehicles and an expansive footprint that allows for more batteries.

Increasingly, however, there is a risk of SUV market saturation. Some commentators highlight that differentiation is becoming paramount for brand success, and diverse vehicle shapes—enabled by advances in electric powertrain technology—could be about to make a comeback. But when even a single design can take years and millions of dollars to develop, the old tools used by engineers might not be enough.

Subscribe to Automotive World to continue reading

Sign up now and gain unlimited access to our news, analysis, data, and research

Subscribe

Already a member?

https://www.automotiveworld.com/articles/mit-open-source-dataset-turbocharges-ai-driven-ev-design/

Welcome back , to continue browsing the site, please click here