×
Sweden’s Volvo creates AI virtual world to accelerate its zero-accident mission
Written by
Published on
Join our daily newsletter for breaking news, product launches and deals, research breakdowns, and other industry-leading AI coverage
Join Now

Volvo is leveraging an AI-generated virtual world to accelerate its zero-accident mission, a bold safety initiative aimed at preventing traffic fatalities. By creating high-fidelity digital environments that can be easily manipulated, the Swedish automaker is dramatically shortening the development cycle for its advanced driver assistance systems (ADAS). This technological breakthrough represents a significant advancement in how carmakers can test safety features by simulating countless dangerous scenarios without real-world risk.

The big picture: Volvo has partnered with Zenseact and the Wallenberg AI research program to create an AI-driven testing environment that transforms real-world driving data into adaptable virtual scenarios.

  • Using Gaussian splatting, an advanced rendering technique, engineers can visualize and manipulate realistic three-dimensional driving environments in days rather than months.
  • The technology allows Volvo to test its vehicle systems against rare but dangerous scenarios that would be impractical or impossible to recreate in physical testing.

Why this matters: The technology could dramatically accelerate Volvo’s progress toward its zero-accident goal as the World Health Organization estimates 1.19 million annual traffic-related deaths globally.

  • By multiplying limited real-world data into thousands of scenario variations, Volvo can train its AI systems on a much broader range of potential hazards.

How it works: Volvo collects real-world incident data through sensors on its connected vehicles, capturing emergency braking events, sharp steering maneuvers, and driver interventions when ADAS systems are operating.

  • Engineers can then reconstruct these incidents virtually and manipulate variables—adding or removing roads, changing traffic behaviors, or inserting different obstacles—to test how safety systems respond.
  • The technology can generate extreme hazards to explore vehicle behavior in complex but infrequent accident scenarios.

What they’re saying: “Data holds the key to improving automotive safety. Thanks to Gaussian splatting, we can now quickly multiply the millions of datapoints we have, turning real-world sensor sequences into thousands of variations of edge cases,” Alwin Bakkenes, head of global software engineering at Volvo Cars, told Newsweek.

  • Bakkenes described the technology as “the mileage multiplier that we’ve been looking for to accelerate how quickly we reach our ambition for a zero-collision future.”

Behind the technology: The virtual testing environment is powered by a newly expanded partnership with NVIDIA, utilizing their DGX systems to process and contextualize massive amounts of driving data.

  • Volvo and Zenseact have jointly established one of the largest data centers in the Nordic region to support this AI development work.
  • The company’s new software-defined vehicles, including the EX90 electric SUV and forthcoming ES90 sedan, are designed to receive over-the-air updates, allowing safety systems to continuously improve.

The complete approach: Volvo is combining its virtual environment testing with traditional real-world software training, development, and validation methods to create a comprehensive safety development ecosystem.

Volvo using AI, your SUV's data to create a virtual world to test safety

Recent News

North Korea unveils AI-equipped suicide drones amid deepening Russia ties

North Korea's AI-equipped suicide drones reflect growing technological cooperation with Russia, potentially destabilizing security in an already tense Korean peninsula.

Rookie mistake: Police recruit fired for using ChatGPT on academy essay finds second chance

A promising police career was derailed then revived after an officer's use of AI revealed gaps in how law enforcement is adapting to new technology.

Auburn University launches AI-focused cybersecurity center to counter emerging threats

Auburn's new center brings together experts from multiple disciplines to develop defensive strategies against the rising tide of AI-powered cyber threats affecting 78 percent of security officers surveyed.