Japanese automotive giant Toyota has started to research AI-based car design using the generative artificial intelligence technique developed by the Toyota Research Institute (TRI).
The company said that designers can leverage publicly available text-to-image generative AI tools as an early step in their creative process.
Using TRI’s new technique, designers can add initial design sketches and engineering constraints into this process, cutting down the iterations needed to reconcile design and engineering considerations.
“Generative AI tools are often used as inspiration for designers, but cannot handle the complex engineering and safety considerations that go into actual car design,” Avinash Balachandran, director of TRI’s Human Interactive Driving (HID) Division, whose team worked on the technology, said in a statement.
“This technique combines Toyota’s traditional engineering strengths with the state-of-the-art capabilities of modern generative AI,” he added.
In an example given by the company, a designer can request, via text prompt, a suite of designs based on an initial prototype sketch with specific stylistic properties like “sleek,” “SUV-like,” and “modern” while also optimising a quantitative performance metric.
The team concentrated on aerodynamic drag in their research paper. The method can also be used to optimise any other performance metrics or constraints derived from a design image.
Meanwhile, Toyota is planning an EV (electric vehicle) powered by a solid-state battery that would have a range of nearly 1,200 km (750 miles) and a charge time of only 10 minutes.
Elon Musk-run Tesla Superchargers give about 200 miles of charge in 15 minutes.
20230623-145802
