High-Performance
In-Vehicle Computing for Autonomous Vehicles
Overview
Driving Next-Generation AV Breakthroughs
The future of mobility is driven by AI, and NVIDIA’s in-vehicle compute solutions are central to this transformation. The NVIDIA DRIVE Hyperion™ platform features two NVIDIA DRIVE AGX Thor™ systems-on-a-chip on a single board; the safety-certified NVIDIA DriveOS™ operating system; and a fully qualified multimodal sensor suite that includes 14 high-definition cameras, nine radars, one lidar, and 12 ultrasonics. This delivers the compute performance and redundancy necessary to enable L4 autonomous driving.
At its core, NVIDIA DRIVE AGX™ delivers the AI computing power for safe, intelligent driving, while NVIDIA DRIVE AV provides the end-to-end autonomous driving software stack. Together with the NVIDIA DriveOS™ safety-certified operating system, the platform enables real-time processing, security, and system monitoring to meet functional safety requirements.
As part of NVIDIA’s three-computer solution for AVs, DRIVE AGX works alongside NVIDIA DGX™ for AI model training and NVIDIA Omniverse™ and Cosmos™ for simulation and validation. NVIDIA Halos serves as the foundation for end-to-end safety, combining hardware, software, tools, and models to protect the entire AV stack, from the cloud to the car.
Features
Unmatched AI Computing for Autonomous Vehicle Innovation
NVIDIA DRIVE AGX delivers a scalable, energy-efficient, future-proof AI computing platform, engineered to process the most complex, real-time workloads essential for safe autonomous driving.
End-to-End Safety and Security
Safety-certified operating system (DriveOS), and hardware design principles comply with stringent automotive safety standards providing a foundation of trust. NVIDIA Halos provides deployment-time guardrails for run-time monitoring and real-time introspection, ensuring continuous protection and security across the entire AV stack, from the cloud to the car.
Future-Proof AI-Defined Architecture
Runs the latest and most demanding AI models, ensuring your vehicle’s capabilities evolve throughout its entire lifecycle with support for continuous hardware and software upgrades.
Sensor Fusion
Integrates data from the complete suite of sensors—including cameras, radar, lidar, and ultrasonic—to create a robust, 360-degree real-time perception of the environment.
Optimized Energy Efficiency
Features a power-efficient, in-vehicle architecture that delivers maximum AI performance with minimal thermal and energy impact.
Hardware
A Powerful AI Computing Platform
Delivering scalable, high-performance hardware for highly automated and fully autonomous driving.
Software
Breakthroughs for Autonomous Vehicles
Enabling safe, scalable, and intelligent driving systems.
The Path to Level 4 Autonomy
The next wave of autonomous vehicles demands AI that can see, reason, and act safely in complex real-world environments. Alpamayo is an end-to-end platform that brings together open AI models, datasets, and high-fidelity simulation into a cohesive ecosystem for reasoning-based autonomy. From vision-language-action models to simulation blueprints, NVIDIA’s expanding portfolio accelerates learning, testing, and deployment—helping developers fast-track safe, level 4 autonomy by design.
NVIDIA Halos: A Full-Stack Comprehensive Safety System for Autonomous Vehicles
Over 15,000 engineering years invested in AV safety have led to the NVIDIA Halos system for chip-to-deployment AV safety. It combines hardware, software, tools, models, and proven design principles to safeguard end-to-end AV stacks.
NVIDIA Automotive NIMs
Accelerated Training and Inference for Autonomous Vehicle Development
Suite of optimized AI models now available for AV developers.
DRIVE Customers
A Shared Vision With Industry Leaders
Delivering industry-leading platforms for the world’s top automakers and mobility companies, built on NVIDIA DRIVE AGX.
Resources
Latest Automotive News
-
Blogs
-
Sessions
Next Steps