Toyota is hoping to speed up vehicle design using its new artificial-intelligence technology employing text-to-image designs at an early stage.
The technique was developed by the Toyota Research Institute, which claims the tool has the potential to reduce the number of iterations needed to reconcile design and engineering challenges. It could also help the automaker design electrified vehicles more quickly and efficiently. For example, aerodynamics could be optimized by gaining an early insight into how to reduce the coefficient of drag generated by a new design, an especially important consideration for battery-electric vehicles.
TRI researchers have released two papers describing how the technique incorporates precise engineering constraints into the design process. In this way constraints such as drag and chassis dimensions like ride height and cabin size can now be incorporated in the generative AI process. The team combined optimization theory principles, used extensively for computer-aided engineering, with text-to-image-based generative AI. The resulting algorithm allows the designer to optimize engineering constraints while maintaining their text-based prompts to the generative AI process.
As an example, a designer can request, using a text prompt, a suite of designs based on an initial prototype sketch with specific stylistic properties, such as “sleek,” “SUV-like” and “modern” while also optimizing a quantitative performance metric. In the TRI research paper, the team focused on aerodynamic drag, but the approach also can be deployed in any other performance metrics or constraints inferred from a design image.
Avinash Balachandran, director of TRI’s human interactive driving division, whose team worked on the technology, explains: “Generative AI tools are often used as an inspiration for designers, but they cannot handle the complex engineering and safety considerations that go into actual car design. Our new technique combines Toyota’s traditional engineering strengths with the state-of-the-art capabilities of modern generative AI.”
