Nvidia and European mobility platform Bolt have announced that they are collaborating on an AI foundation that will enable the scaling of autonomous vehicles in Europe.
Bolt‘s ride-hailing, car-sharing, micromobility and delivery operations generate real-world driving data across some of the most complex urban environments in the world. That operational footprint provides a practical foundation for building autonomous vehicle systems that work reliably across a range of European countries where transportation infrastructure and regulations can differ considerably.
This partnership will combine Bolt’s extensive ride-hailing and carsharing fleet data with Nvidia Omniverse libraries, Nvidia Cosmos world foundation models, Nvidia Alpamayo AV foundation models and Nvidia AI infrastructure. The resulting AV platform will be deployed on the Nvidia Drive Hyperion computer and sensor architecture to deliver a robotaxi service that meets Europe’s highest safety and performance standards.
“Real-world data is the most valuable asset in the race for safe autonomy,” said Jevgeni Kabanov, president and head of autonomous driving at Bolt. “By marrying Bolt’s operational scale with the Nvidia Hyperion Platform, Alpamayo foundation models, AI infrastructure, and open models and libraries, we are creating a European-led AV offering that ensures our continent remains at the forefront of mobility innovation while maintaining full control over our data and technology.”
Technology for the EU
Bolt’s strategy uses its extensive fleet data to build a learning engine grounded in real-world driving. Bolt will curate and search this data with Nvidia Cosmos, reconstruct high-fidelity scenes from driving logs with Nvidia Omniverse NuRec, and use Cosmos again to generate and augment data at scale. Alpamayo will be used to accelerate policy learning and behavioral adaptation across diverse European traffic norms, helping ensure the resulting AI models reflect the complexity and diversity of European city streets.
All processing of Bolt Fleet data will use privacy-preserving mechanisms to ensure strict compliance with GDPR and EU cybersecurity standards.
Next-generation Nvidia autonomous platform
Bolt will integrate the Nvidia Drive Hyperion platform, designed for robotaxi-ready deployments. The system will leverage dual Nvidia Drive AGX Thor processors and a multi-sensor architecture combining lidar, camera and radar for robust perception and redundancy. Running the safety-certified Nvidia DriveOS, this system provides the high-performance compute required for real-time processing and Level 4-ready autonomous capabilities.
The platform is designed to work seamlessly with Alpamayo foundation models, Cosmos and Omniverse NuRec across training, simulation and in-vehicle deployment.
The initiative will provide open source access to critical tooling, interfaces, evaluation frameworks, benchmarks and reference implementations.
“Autonomous vehicles require a full-stack approach that unifies AI models, high-performance compute, and a robust sensor architecture,” said Philippe Van Den Berge , EMEA vice president of automotive at Nvidia.
“By combining Bolt’s real-world operational data with the Nvidia Drive Hyperion platform, AI infrastructure, and open models and libraries across Omniverse, Cosmos and Alpamayo, we’re enabling a scalable foundation for safe, high-performance autonomous mobility services designed for the complexity and diversity of European roads.”
Related news, Researchers find driverless cars and digital twins need more than 5G