NVIDIA Unveils Full-Stack Autonomous Vehicle Software Platform for Safe, Intelligent Transportation Innovations

NVIDIA launches a comprehensive autonomous vehicle (AV) software platform, NVIDIA DRIVE, for automakers, truck manufacturers, and robotaxi companies. The full-stack software platform is now in production and offers a robust foundation for AI-powered mobility, unlocking a multitrillion-dollar global opportunity in autonomous and highly automated vehicles. It provides a unified, safety-certified AV software architecture for real-time sensor fusion and continuous improvement through over-the-air updates. NVIDIA's three-computer solution spans the entire AV development pipeline, including training AI models, simulation and synthetic data generation, and processing real-time sensor data for safe, highly automated, and autonomous driving capabilities.

NVIDIA has announced the launch of its comprehensive autonomous vehicle (AV) software platform, NVIDIA DRIVE, designed to accelerate large-scale deployment of safe, intelligent transportation innovations. The full-stack NVIDIA DRIVE AV software platform, now in full production, offers a robust foundation for AI-powered mobility, unlocking a multitrillion-dollar global opportunity in autonomous and highly automated vehicles [1].

The platform provides a unified, safety-certified AV software architecture that supports real-time sensor fusion and continuous improvement through over-the-air updates. This modular and flexible approach empowers customers to scale based on their specific needs, whether they adopt the entire stack or a subset. It supports advanced driver-assistance features such as surround perception, automated lane changes, parking, and active safety for level 2++ and level 3 vehicles, with a seamless path to higher levels of automation as technologies and regulations evolve [1].

NVIDIA's three-computer solution spans the entire AV development pipeline. It includes NVIDIA DGX systems and GPUs for training AI models and developing AV software, the NVIDIA Omniverse and NVIDIA Cosmos platforms for simulation and synthetic data generation, and the automotive-grade NVIDIA DRIVE AGX in-vehicle computer for processing real-time sensor data for safe, highly automated, and autonomous driving capabilities [1].

The platform embraces generative AI and an end-to-end model approach, using deep learning and foundation models trained on large datasets of human driving behavior to process sensor data and directly control vehicle actions. This eliminates the need for predefined rules or traditional modular pipelines, allowing vehicles to learn from vast amounts of real and synthetic driving behavior data to safely navigate complex environments [1].

NVIDIA DRIVE AV software unifies perception, prediction, planning, and control functions, enhancing safety and efficiency in autonomous vehicle development. The NVIDIA Omniverse Blueprint for AV simulation further enhances the development pipeline, enabling physically accurate sensor simulation for AV training, testing, and validation. By combining the blueprint with NVIDIA's three-computer solution, developers can convert thousands of human-driven miles into billions of virtually driven miles, amplifying data quality and enabling efficient, scalable, and continuously improving AV systems [1].

NVIDIA Halos, a comprehensive end-to-end safety system, integrates hardware, software, AI models, and tools to ensure safe AV development and deployment from cloud to car. The NVIDIA DriveOS safety-certified ASIL B/D operating system provides a robust foundation for safe vehicle operation and meets stringent automotive safety standards [1].

The platform's launch marks a significant milestone in the automotive industry, transforming vehicle cockpits, vehicle design, engineering, and manufacturing. NVIDIA has worked with the European auto industry for over a dozen years to drive automotive innovation, partnering with leading manufacturers, suppliers, and mobility startups [1].

References:
[1] https://blogs.nvidia.com/blog/drive-full-stack-av-software-europe/
[2] https://blogs.nvidia.com/blog/autonomous-vehicle-ecosystem-ai-models-developer-tools/

View Source