Einride teams up with NVIDIA to scale Level 4 autonomous trucking

Einride has announced a strategic collaboration with NVIDIA aimed at accelerating the development and deployment of autonomous heavy-duty transport.

Under the agreement, the Swedish company will build the next generation of its Einride Driver autonomous driving system on NVIDIA Hyperion, adapting the platform to the specific requirements of heavy-duty freight applications.

NVIDIA Hyperion combines computing, sensors and software architecture designed to support Level 4 autonomous driving, where vehicles can perform the complete driving task without human intervention within defined operating conditions and areas.

The two companies will work together to extend the platform to heavy-duty applications, integrating it with the NVIDIA Halos safety system.

Einride remains in control of the autonomous driving system

The collaboration does not mean NVIDIA will take over development of Einride Driver. Einride will continue to design and operate its autonomous driving system end-to-end, including software development, safety validation, regulatory approval and deployment with customers.

NVIDIA will provide the underlying computing platform and AI development tools required to support the system.

“We have the customers, the operational experience and the technology. Building the next generation of the Einride Driver on the NVIDIA Hyperion platform will enable us to scale autonomous deployment across a freight network that’s already serving customers today,” said Henrik Green, Chief Technology Officer at Einride.

Einride currently operates hundreds of electric trucks for customers across the United States, Europe and the Middle East, including autonomous vehicles already deployed in contracted operations. The company expects its overall fleet to grow to between 1,500 and 2,000 vehicles by 2028, based on customer demand currently captured on its platform. Einride estimates that around 80% of that demand could be suitable for automation in the medium term.

NVIDIA Cosmos and Blackwell for training and validation

Another element of the partnership concerns the data used to develop and validate autonomous driving models.

Einride will use NVIDIA Cosmos to identify particularly complex situations in footage collected by vehicle cameras and complement real-world information with photorealistic synthetic scenarios. The aim is to broaden the range of situations available for training and testing the autonomous driving system.

The company also plans to use NVIDIA Blackwell infrastructure through an NVIDIA-certified cloud provider to train, test and refine its autonomous driving models at scale.

The NVIDIA collaboration comes as Einride continues to expand the ecosystem around its autonomous driving technology. In Europe, the company is also working with DAF Trucks on the integration of Einride Driver into the Dutch manufacturer’s electric vehicle platform, with the project targeting Level 4 applications.