NVIDIA DRIVE Hyperion
Reference platform for safe, scalable, level 4-ready vehicles.
Overview
L4-Ready AV Platform
NVIDIA DRIVE Hyperion™ is a complete, production-ready autonomous driving development platform and reference architecture, combining a standardized sensor suite, high-performance NVIDIA DRIVE™ compute, and a robust software stack. This helps automakers, mobility providers, and AV startups develop, validate, and deploy next-generation driver-assist and autonomous driving capabilities. With DRIVE Hyperion, teams can focus on building differentiated AI while reducing integration risk, shortening development cycles, and improving safety.
Features
Built for the Future of Autonomy
DRIVE Hyperion brings together the essential capabilities required to build, validate, and deploy next-generation autonomous vehicles.
Specifications
DRIVE Hyperion
| DRIVE Hyperion 10 | DRIVE Hyperion 8 | |
| Compute Performance | Two NVIDIA DRIVE AGX Thor™ SoCs: up to 1,000 INT8 TOPS + 2,000 FP4 TFLOPS per SoC | Two NVIDIA DRIVE AGX Orin™ SoCs: combined up to ~508 INT8 TOPS depending on configuration |
| Sensor Suite | 14 cameras, 9 radars, 1 lidar, 12 ultrasonic sensors, 4 interior cameras, an exterior microphone array | 12 cameras, 9 radars, 1 lidar, 12 ultrasonic sensors, 3 interior cameras |
| Scalability | Level 2 ADAS through Level 4 autonomous driving | Level 2 ADAS through Level 3 autonomous driving |
| Safety Certification | ISO 26262 ASIL-D capable with NVIDIA Halos | ISO 26262 ASIL-D capable |
| Vehicle Integration | Production-ready for integration into any new vehicle architecture and platform | Production-ready for integration into any new vehicle architecture and platform |
| Cybersecurity | ISO 21434 capable with NVIDIA Halos | N/A |
End-to-End Infrastructure for Self-Driving Cars
DRIVE Hyperion is part of NVIDIA’s end-to-end AV platform that spans data center training, large-scale simulation, and in-vehicle compute. Data collected from DRIVE Hyperion-equipped vehicles can be used to train and refine AI models in the cloud, validate them in photorealistic simulation, and then deploy updated software back to the vehicle. This closed-loop, cloud-to-car workflow accelerates development and helps maintain a continuously improving autonomous driving system.
NVIDIA Alpamayo
Explore the family of open models, simulation, and datasets powering reasoning-based autonomous vehicles—designed to handle complex, real-world driving scenarios with transparent decision-making.
Industry Adopters
DRIVE Hyperion Ecosystem Partners
Contact Us
NVIDIA automotive solutions are available to automakers, tier 1 suppliers, startups, and research institutions working on the future of transportation.