Volvo using advanced AI simulations and Gaussian Splatting to accelerate the development of driver safety systems

According to the car-maker, the team is taking real world incident data gathered by sensors on vehicles - such as emergency braking, sharp steering or manual intervention - and using an advanced computational technique known as Gaussian Splatting to rapidly create and probe a range of virtual scenarios.  

Volvo said that the technique, which can create a vast amount of realistic, high-fidelity 3D scenes and subjects from real-world visuals, enables the virtual environment to be manipulated by adding or removing road users and changing the behaviour of traffic or obstacles on the road and allows engineers to expose the safety software to all types of traffic situations, at a speed and scale not possible before.

The work has been partly helped by Volvo’s long-standing collaborative partnership with computing leader NVIDIA, which is helping the car maker explore and accelerate the application of AI technologies.  

Volvo said that the software is proving particularly useful for exploring rare, yet potentially dangerous “edge cases” - and can reduce the time it takes to expose the software to these extreme situations from months to days.

“We already have millions of data points of moments that never happened that we use to develop our software,” said Alwin Bakkenes, Head of Global Software Engineering at Volvo Cars. “Thanks to Gaussian splatting, we can select one of the rare edge cases and explode it into thousands of new variations of the scenario to train and validate our models against. This has the potential to unlock a scale that we’ve never had before and even to catch edge cases before they happen in the real world.”

This project is part of a PhD programme for leading Swedish universities to explore whether neural rendering techniques will be integrated into future safety initiatives. The study is sponsored by Wallenberg AI, Autonomous Systems and Software Program (WASP).  The virtual environments are developed in-house in collaboration with Zenseact, an AI and software company founded by Volvo Cars.

In a press statement Volvo explained that this latest innovation builds on a long history of making the best possible use of data to enhance safety.  Indeed, accident data gathered by Volvo’s Safety Research Team in the 1970s was key to the development of innovations, such as the Whiplash Injury Protection System and Side Impact Protection System.