Robotaxis are self-driving, complex supercomputers on wheels that require high-performance compute and a unique end-to-end process to develop, roll out, and continually improve. NVIDIA DRIVE provides full-stack AI compute solutions for robotaxi development, enabling fully autonomous vehicles that process massive amounts of data and run redundant and diverse deep neural networks for safe and secure operation.

NVIDIA DRIVE Infrastructure

An Intelligent Infrastructure

Data center development is critical to deploying robotaxis at scale. The ability to operate in thousands of conditions around the world requires intensive deep neural network training using massive amounts of data. NVIDIA DRIVE Infrastructure’s unified, open, and high-performance compute, powered by GPU technology, is the only solution to develop, train, test, and validate self-driving DNNs at scale.

Around-the-Clock AI Compute

The high-performance compute required to develop robotaxis is just as necessary in the vehicle itself. NVIDIA DRIVE AGX AI compute platforms make it possible to run the redundant and diverse DNNs needed to replace the human driver, all at once. The DRIVE AGX family is built on a single scalable architecture, capable of delivering up to 2,000 trillion operations per second for safe, around-the-clock driverless operation.

NVIDIA DRIVE AGX AI compute platforms
NVIDIA Robotaxi

Continuous Improvement

By combining data center and in-vehicle solutions, AV companies can create a continuous, end-to-end development cycle. As DNNs learn new capabilities in the data center, the validated algorithms can be delivered to the car’s compute platform over the air for a vehicle that’s forever featuring the latest and greatest technology. This continuous development cycle provides riders with amazing new experiences and enables transformative new business models.

A Rich Robotaxi Ecosystem

Optimus Ride

And more

Find out how you can start developing safer, more efficient
autonomous transportation.