image for details: Soundcore by Anker Q30 Hybrid
Active Noise Cancelling Headphones featuring
Multiple Modes, Hi-Res Sound, Custom EQ via App,
50 Hours of Playtime, Comfortable Fit,
Bluetooth Connectivity and Multipoint Connection.
Volvo Cars is utilising AI-generated lifelike virtual worlds to enhance the development of its safety software, particularly driver-assistance systems (ADAS), to create even safer vehicles.
The company can now synthesise incident data collected by the advanced sensors in its new cars, which include features like emergency braking, sharp steering, and manual intervention. This capability enables Volvo to analyse, reconstruct, and explore various incidents innovatively to better understand how to prevent them.
This advancement is made possible by an advanced computational technique, Gaussian splatting, which can generate many realistic, high-fidelity 3D scenes and subjects based on real-world visuals. The virtual environment can be modified by adding or removing road users and altering traffic behaviour or obstacles to create different outcomes.
This technique allows Volvo to expose its safety software to a wide range of traffic situations at a speed and scale previously unattainable. They can now develop software that performs effectively in complex, rare, yet potentially dangerous “edge cases,” reducing the time required to test these scenarios from months to days.
“We already have millions of data points from scenarios that have never occurred, which we use to develop our software,” says Alwin Bakkenes, Head of Global Software Engineering at Volvo Cars. “Thanks to Gaussian splatting, we can select a rare edge case and expand it into thousands of new scenario variations to train and validate our models. This has the potential to unlock a scale we’ve never experienced before and could even help us anticipate edge cases before they happen in the real world.”
