Autonomous Vehicle Safety

Autonomous Vehicle Safety

Developing with NVIDIA Halos enables vehicle safety across all levels of automation.

Overview

Autonomous Vehicle Safety, From the Cloud to the Car

NVIDIA Halos is a full-stack comprehensive safety system that unifies vehicle architecture, AI models, chips, software, tools, and services to ensure the safe development of autonomous vehicles (AVs) from cloud to car.

The system ensures safety across the full development lifecycle with design-time, deployment-time, and validation-time guardrails that collectively build safety and explainability into AI-based AV stacks. These guardrails are implemented using three powerful computers—NVIDIA DGX for AI training, NVIDIA Omniverse and Cosmos for simulation, and NVIDIA AGX for deployment.

NVIDIA Halos also complements existing industry-standard safety practices, while introducing unique elements for autonomous vehicles. This ensures regulatory compliance, and advances safe and reliable AV stacks, together with NVIDIA’s AI Systems Inspection Lab.

NVIDIA Launches Halos, a Full-Stack Comprehensive Safety System for Autonomous Vehicles

NVIDIA unifies vehicle architecture to AI models; chips, software, and tools to services for safely developing AVs from cloud to car.

NVIDIA Halos

In this video, we show how NVIDIA Halos is a full-stack comprehensive safety system that unifies development from vehicle architecture to AI to ensure safe autonomous vehicle deployment.

Highlights

Autonomous Vehicle Safety Leadership

NVIDIA Halos is the result of continuous investment in autonomous vehicle safety—from research to engineering to active engagement with international safety standards—validated by independent third-party assessments.

15,000+

Engineering years invested in vehicle safety to date

21 Billion+

Safety transistors safety assessed

7,000,000

Lines of safety-assessed code

2,000,000

Daily end-to-end integration tests for validation

22,000+

Platform safety monitors

20,000+

Hours of test data

1,000+

Patents filed

240+

Research papers published on AV safety

30+

Certificates and assessment reports issued

Technology

Engineered for Safety, Designed for Trust

As AV companies transition to AI-based, end-to-end architectures, NVIDIA Halos provides the critical safety foundation to ensure system-level reliability and iterative improvement for automated driving systems. This includes integration of third party-assessed hardware, software, and processes with a diverse algorithmic architecture and validation pipelines.

NVIDIA DGX

Design-time safety guardrails for built-in hardware/software safety and trustworthy development processes.

NVIDIA Omniverse With Cosmos

Validation-time guardrails for data generation, simulation, evaluation, and lifelong safety assurances.

NVIDIA DRIVE AGX

Deployment-time guardrails for run-time monitoring and real-time introspection.

Benefits

A Comprehensive System for Autonomous Vehicle Safety

NVIDIA Halos helps to ensure AI-driven AV systems are safe and secure. Partners can leverage NVIDIA’s investments in AI safety to accelerate development and enhance AV reliability. NVIDIA Halos is open to developers, enabling adoption or customization of safety elements, driving the shared mission to develop safe and reliable autonomous vehicle technology.

Design-time, deployment-time, and validation-time guardrails collectively build safety and explainability into several layers of technologies spanning platform safety, AI algorithmic safety, and ecosystem safety. 

At the top of the NVIDIA Halos elements sits the NVIDIA AI Systems Inspection Lab, which allows customers and ecosystem partners to verify the safe integration of their products with NVIDIA Halos elements. The lab is the first worldwide program to be accredited by ANAB for AI functional safety.

Use Cases

A Full-Stack Comprehensive Safety System

NVIDIA unifies vehicle architecture from AI models, chips, software, and tools to services for safely developing autonomous vehicles, from cloud to car. NVIDIA Halos integrates foundational models and a diverse algorithmic stack, combining classical and AI-based, end-to-end models to ensure system-level safety in the shift toward AI-driven AV architectures. 

Platform Safety

A robust foundation for autonomous driving systems, including:

  • A System-on-a-Chip (SoC) that’s designed for safety, with hundreds of built-in safety mechanisms.
  • NVIDIA DriveOS, a safety-certified ASIL-D operating system that extends from CPU, ISP, GPU, I/O, and memory.
  • A safety assessed base platform that delivers the foundational safe computer needed to enable safe systems, for all types of applications
  • NVIDIA DRIVE AGX Hyperion™, a diverse hardware platform that connects the SoC, OS, and sensors in a vehicle architecture that ensures a vehicle can safely execute contingency plans if needed.

Algorithmic Safety

Algorithmic AI safety spans:

  • A diverse AV stack that combines a modular stack and end-to-end AI models for algorithmic AI safety.
  • Training, simulation, and validation environments that use Omniverse and Cosmos platforms to build safe AVs.
  • A separate safety dataset that ensures AV performance is tested against diverse, unbiased data.

Ecosystem Safety

Building a safer AV ecosystem includes:

  • Continual improvements through a safety data flywheel, which continually learns from the road how to expand the set of operational design domains for safe deployment.
  • Seamless integration of physically based and diverse sensor simulation into existing workflows to safely train, test, and validate AVs with the NVIDIA Omniverse Blueprint for AV Simulation.
  • Open-source data, such as the NVIDIA Physical AI Dataset, to enable critical safety research throughout the industry.
  • Click here to see a growing list of partners using the NVIDIA Halos system.

AI Systems Inspection Lab

NVIDIA is the first company in the world to establish an ANSI National Accreditation Board (ANAB)-accredited AI Systems Inspection Lab, integrating functional safety, cybersecurity, AI, and regulations into a unified safety framework. The lab helps to ensure that partner system integrations meet rigorous safety and cybersecurity standards through impartial assessments.

By providing inspection reports and streamlining technical validations, the lab accelerates compliance with global safety standards for AV safety and cybersecurity. This empowers the automotive ecosystem to deploy safe, more reliable AI-driven technologies while advancing compliance with international standards.

Certification

Assessed by Experts

Independent third-party safety and cybersecurity assessments of NVIDIA Halos elements demonstrate NVIDIA’s ongoing commitment to AV safety.

ANSI National Accreditation Board

ANAB accredited NVIDIA AI Systems Inspection Lab as ISO/IEC 17020 Inspection Body. NVIDIA is the first company accredited by ANAB for an inspection plan that combines cybersecurity, AI, and functional safety.

TÜV SÜD

TÜV SÜD certified NVIDIA’s Automotive Product Lifecycle (PLC) software process and DriveOS 6.0 to ISO 26262 standard for Automotive Safety Integrity Level (ASIL) D. NVIDIA also received ISO/SAE 21434 Cybersecurity Process certification for its automotive system-on-a-chip, platform and software engineering processes.

TÜV Rheinland

TÜV Rheinland performed an independent United Nations Economic Commission for Europe safety assessment of NVIDIA DRIVE AV related to safety requirements for complex electronic systems.

Research

NVIDIA Research for Autonomous Vehicles

Our research and development have published 240+ research papers on autonomous vehicle safety.

Recent Advances and Trends on Automotive Safety

Catch up on recent automotive safety advances, focusing on Automated Driving Systems (ADS) and the interplay between functional safety, SOTIF, and cybersecurity.

NVIDIA Cosmos World Foundation Model Platform for Physical AI

Physical AI needs to be trained digitally first. This requires a digital twin of itself, the policy model, and a digital twin of the world—the world model. Cosmos helps developers build customized world models for physical AI setups.

Promptable Closed-Loop Traffic Simulation

Aside from simulating realistic traffic agent interactions in a closed loop, traffic models should also generate agent motions that satisfy a complex set of user-specified prompts.

Surprise Potential as a Measure of Interactivity in Driving Scenarios

Explore a novel metric that identifies interactive scenarios by measuring an AV's surprise potential on others.

Enhancing Autonomous Driving Safety with Collision Scenario Integration

HydraSafe is a framework that addresses the challenge of ensuring autonomous vehicle safety in hazardous scenarios by improving data availability and planner robustness.

System-Level Safety Monitoring and Replanning in Autonomous Vehicles

The safety-critical nature of autonomous vehicle (AV) operation necessitates the development of task-relevant algorithms that can reason about safety at the system level and not just at the component level.

For a list of additional AV Research papers, click here.

Partners

Partners Using NVIDIA Halos System

Leading robotaxi companies, OEMs, industry safety pioneers, mapping and simulation companies, and software and sensor providers worldwide are using the system to deliver autonomous vehicle safety at all levels of automation.

Cars

Trucks

Robotaxis

Suppliers

Simulation

Sensors

Software

Mapping

Resources

The Latest in NVIDIA Halos Resources

Next Steps

Redefining Safe Autonomy

Learn how cutting-edge AI, rigorous validation frameworks, and global standards are shaping autonomous vehicle safety.

Automotive News

Sign up for the latest news and updates from NVIDIA.

NVIDIA Automotive

NVIDIA’s automotive solutions give you the performance and scalability to design, visualize, develop, and simulate the future of driving.

Read the NVIDIA Autonomous Vehicles Safety Report