NVIDIA Details European Robotaxi and Level 4 Programs on Hyperion

NVIDIA (NVDA ) announced on October 21, 2026, at GTC Berlin that European automakers and mobility providers, including Bolt with Lucid, Mercedes-Benz (MBG.DE ), Volkswagen Commercial Vehicles and Einride, are showcasing selected autonomous-mobility use cases on the NVIDIA Hyperion computing platform, demonstrating potential applications for level 3 and level 4 vehicles and future robotaxi fleets. Volvo Cars is adopting Hyperion and the NVIDIA Alpamayo Stack software for automated driving, and NVIDIA also introduced new safety and development technologies for autonomous-vehicle programs.

NVIDIA described autonomous transportation as a multitrillion-dollar opportunity, with robotaxis leading the move to commercial level 4 deployment. “Robotaxis are the first mass-market application of robotics and physical AI, reinventing how people and goods move,” said Jensen Huang, founder and CEO of NVIDIA.

European Partner Programs on Hyperion

Bolt selected the NVIDIA Alpamayo Stack for its European robotaxi program, beginning with future Lucid vehicles built on Hyperion. Bolt and NVIDIA will adapt the software for European roads and integrate it into vehicles from multiple manufacturers, combining NVIDIA’s driving and safety technologies with Bolt’s fleet-management systems, operations and local market expertise. Bolt plans to begin gathering real-world driving data to support development and validation of the autonomous-driving technology, subject to regulatory approval, in Madrid in 2027. Germany is a priority for future deployment within a planned European rollout of at least 25,000 level 4-capable future Lucid vehicles built on Hyperion.

The robotaxi program builds on a collaboration Bolt first detailed in a March 16, 2026, announcement from Tallinn, Estonia, in which it said it would build an autonomous-vehicle platform on NVIDIA DRIVE Hyperion with dual NVIDIA DRIVE AGX Thor processors, a multi-sensor architecture combining lidar, camera and radar, and the safety-certified NVIDIA DriveOS. In that statement, Bolt said it would use NVIDIA Cosmos, Omniverse NuRec and Alpamayo across training, simulation and in-vehicle deployment, and that all processing of Bolt fleet data would use privacy-preserving mechanisms to comply with GDPR and EU cybersecurity standards. Bolt states that it operates in more than 50 countries and more than 850 cities, serving over 200 million customers. “Real-world data is the most valuable asset in the race for safe autonomy,” Jevgeni Kabanov, Bolt’s president and head of autonomous driving, said in the earlier announcement.

At GTC Berlin, Volkswagen Commercial Vehicles is presenting its autonomous ID. Buzz AD vehicle platform with Hyperion to support multiple autonomous-driving systems, with the platform providing a common computing and sensor architecture designed to simplify integration and validation for robotaxi and commercial transport services. Volvo Cars is combining its vehicle safety systems and engineering expertise with Hyperion, Halos OS and Alpamayo Stack, with the goal of enabling future Volvo cars to safely navigate complex real-world environments from door to door. Mercedes-Benz is extending its partnership with NVIDIA on Hyperion and Alpamayo Stack to support development of the automaker’s L3 and L4 capabilities. According to NVIDIA, MB.DRIVE ASSIST PRO, developed in partnership with NVIDIA, will soon get approval for urban point-to-point driver assistance in Germany.

Beyond passenger vehicles and robotaxis, Einride is building its next-generation Einride Driver on Hyperion for autonomous freight trucks, using Halos, Alpamayo and NVIDIA Cosmos open world models to develop and validate its driving system. TIER IV and the Technical University of Munich plan to integrate Hyperion to develop and validate systems for autonomous public transportation in Germany. Technology and manufacturing partners Aptiv, Valeo and Schaeffler are building Hyperion-based computing platforms that vehicle manufacturers can integrate for L4 autonomous vehicles and robotaxis.

Safety Framework and New Development Tools

NVIDIA introduced Halos SAFE, the Safety Assurance Framework for Evaluation, within its Halos safety system, combining simulation and physical testing to generate measurable, traceable autonomous-vehicle safety evidence. Halos SAFE connects simulation, software- and hardware-in-the-loop evaluation, on-road testing and fleet monitoring through defined scenarios, tests and measurable performance criteria. dSPACE, IVEX and TÜV Rheinland are collaborating on the evaluation workflows, and the wider Halos SAFE ecosystem includes JLR, Mercedes-Benz, Volvo Cars, 51Sim, aiMotive, AVL, Deepen AI, Foretellix and Synopsys.

NVIDIA also announced new models, tools and blueprints for autonomous-vehicle development. Alpamayo 2 Edge is a 2-billion-parameter reasoning model built on the NVIDIA Nemotron-based foundation of Cosmos 3 Edge, optimized for the NVIDIA DRIVE AGX Thor platform and designed to run at 10Hz for in-vehicle scene understanding and motion planning. AlpaJudge is a human-calibrated evaluation and reward model that scores driving explanations to assess reasoning quality, filter weak annotations and reduce manual review of training data. Foundation4D labels multicamera video without lidar input, supporting perception-model training and Omniverse NuRec scene reconstruction, while new Cosmos 3 Nano model variants expand synthetic data generation and closed-loop simulation across diverse driving scenarios. A Cosmos Data Factory blueprint turns driving video and vehicle signals into curated, searchable, labeled data, and Alpamayo Agentic Factory is an open blueprint NVIDIA expects to become available in early 2027. New NVIDIA NIM microservices deliver Alpamayo 1.5 and NuRec Harmonizer as optimized inference containers.

Uber and NVIDIA are developing a data factory powered by Cosmos to curate and process data for autonomous-vehicle development, part of a broader partnership spanning AI development infrastructure, Hyperion-based vehicles and Uber’s global ride-hailing network. Porsche is leading development of a data flywheel workflow across Volkswagen Group brands through Voxel51, using NVIDIA Cosmos Data Factory and Omniverse NuRec on Microsoft Azure to turn fleet data into datasets and simulations for evaluating autonomous-driving models. NVIDIA stated the workflow is expected to reduce repeated physical test drives by up to 90% and shorten development cycle duration by up to 85%.