INTRODUCING NVIDIA DRIVE AGX ORIN™ This highly advanced, software-defined platform for autonomous machines delivers 200 TOPS—nearly 7X the performance of NVIDIA Xavier. It's powered by the new Orin system-on-a-chip and designed to handle the large number of applications and DNNs that run simultaneously in autonomous vehicles and robots. LEARN MORE
DRIVE AP2X DRIVE AP2X provides an industry-leading driver-assistance experience, handling challenges both inside and outside the vehicle. It’s the world’s first commercially available Level 2+ automated driving system, integrating the high-performance NVIDIA Xavier™ SoC and DRIVE Software. This lets manufacturers bring sophisticated driver assistance features, as well as intelligent cockpit and visualization capabilities, to passenger cars and commercial trucks. Learn More
Hardware NVIDIA DRIVE AGX is a scalable, open autonomous vehicle computing platform that serves as the brain for autonomous vehicles. The only hardware platform of its kind, NVIDIA DRIVE AGX delivers high-performance, energy-efficient computing for functionally safe AI-powered self-driving. Learn More
Software To augment and, eventually, replace the human driver, NVIDIA DRIVE software enables key self-driving functionalities such as sensor fusion and perception. The open, full-stack solution features libraries, toolkits, frameworks, source packages, and compilers for vehicle manufacturers and suppliers to develop applications for autonomous driving and user experience. Learn More
Simulation Photorealistic simulation is a safe, scalable solution for testing and validating a self-driving platform before it hits the road. NVIDIA DRIVE Constellation™ is a data center solution that integrates powerful GPUs and DRIVE AGX Pegasus™. Advanced visualization software running on GPUs simulate cameras, radar, and lidar as inputs to DRIVE AGX Pegasus, which processes the data as if it were actually driving on the road. This scalable system is capable of generating billions of miles of diverse autonomous vehicle testing scenarios to validate hardware- and software-in-the-loop prior to deployment. Learn More
