NVIDIA DRIVE® Infrastructure encompasses the complete data center hardware, software, and workflows needed to develop autonomous driving technology—from raw data collection through validation. It provides the end-to-end building blocks required for neural network development, training and validation, and testing in simulation.
High-performance, energy-efficient AI computing infrastructure is required to develop autonomous vehicles. The key to success is optimizing the data load for training and operating these vehicles without compromising safety. The more information that cars can gather and process, the faster and better AI can learn and make decisions.
NVIDIA DGX SuperPOD™ delivers a turnkey AI data center solution for organizations that want to focus on insights instead of infrastructure. It includes best-of-breed computing, software tools, expertise, and continuous innovation delivered seamlessly.
NVIDIA LaunchPad gives enterprises immediate, short-term access to NVIDIA AI running on private accelerated compute infrastructure to power critical AI initiatives. Speed the development and deployment of modern, data-driven applications and quickly test and prototype your entire AI workflow on the same complete stack you can purchase and deploy.
It’s impossible for an autonomous vehicle to encounter every possible traffic situation while testing on public roads. In NVIDIA DRIVE Sim™, virtual vehicle fleets can drive millions of miles in a broad range of scenarios—from routine driving to rare or even dangerous situations—with greater efficiency, cost-effectiveness, and safety than in the real world. The high-fidelity platform can also generate synthetic physically based sensor and ground truth data to tailor scenarios to any development need.
NVIDIA OVX Server is designed to run DRIVE Sim with the complex sensor architectures necessary for autonomous driving. OVX combines high-performance compute and GPU-accelerated graphics with high-speed storage access, low-latency networking, and precision timing to provide the performance required for scalable software-in-the-loop (SIL) AV simulation.
NVIDIA DRIVE Constellation™ pairs an OVX Server with an additional server containing the in-vehicle compute for hardware-in-the-loop (HIL) simulation. The entire system is designed to run in the data center at scale. It runs NVIDIA DRIVE Sim in real time and tests the software on the same hardware used in the vehicle to support bit- and timing-accurate AV validation.
Gain insights from NVIDIA's AV training and testing efforts on NVIDIA DGX SuperPOD, including AI infrastructure at scale, overcoming data management challenges, and ML Ops.
Breakthroughs by NVIDIA Research demonstrate the power of Omniverse digital twin to reconstruct real world scenarios in simulation.
Learn about the technology that enables DRIVE Replicator to produce physically accurate synthetic sensor data and ground truth for training AV perception algorithms at scale.
See the latest developments and capabilities in DRIVE Sim software. Demonstrations will highlight innovative development techniques using simulation.
This post covers the validation of camera models in DRIVE Sim, assessing the performance of each element, from rendering of the world scene to protocol simulation.
With DRIVE Sim, AV developers can improve productivity, efficiency, and test coverage, advancing time-to-market while minimizing real-world driving. If you’re interested in joining the DRIVE Sim early access release program, please apply to become a member.
Find out how you can start developing AI-powered autonomous vehicles.
This form is for automotive inquires only. For other inquiries, please click here.