As autonomous vehicle systems rapidly grow in complexity, equipped with reasoning vision language action models, generative AI and advanced sensor technologies, developers need tools that are powerful, efficient and built to meet automotive-grade safety requirements.
The NVIDIA DRIVE AGX Thor developer kit — now available for preorder today, with delivery in September — provides developers and researchers worldwide an advanced platform to accelerate the design, testing and deployment of AVs and intelligent mobility solutions.
The developer kit is built on the NVIDIA Blackwell architecture, next-generation Arm Neoverse V3AE CPUs and the NVIDIA DriveOS 7 software stack. It’s purpose-built for reasoning vision language action models and ideal for automotive development, with sufficient I/O to support surround cameras, radars and lidars, as well as common vehicle interfaces including GbE/10GbE and PCI-Express. DRIVE AGX Thor also meets the automotive industry’s stringent functional safety (ISO 26262) and cybersecurity requirements (ISO 21434).
The Growing DRIVE AGX Thor Ecosystem
The world’s leading automotive companies are building on NVIDIA DRIVE AGX Thor, including BYD, GAC, IM Motors, Li Auto, Volvo Cars, Xiaomi and Zeekr. Autonomous trucking companies building on NVIDIA DRIVE AGX Thor include Aurora, Gatik, PlusAI and Waabi.
NVIDIA AV partners DeepRoute.ai, Nuro, WeRide and ZYT are using DRIVE AGX Thor for their AV software platforms. DRIVE AGX Thor production systems are available from Tier 1 suppliers Continental Automotive, Desay SV, Lenovo, Magna and Quanta.
DRIVE AGX Thor is supported by a growing number of sensor and embedded technology pioneers, including AdaCore, Lauterbach, OMNIVISION, QNX and Vector.
AV Safety From Cloud to Car
Designed for automotive-grade safety and security, DRIVE AGX Thor and DriveOS are key elements of NVIDIA Halos, a comprehensive safety system that brings together NVIDIA’s automotive hardware and software safety technologies with cutting-edge AI research in AV safety.
Halos offers a holistic approach to automotive safety:
- At the technology level, it spans platform, algorithmic and ecosystem safety.
- At the development level, it includes design-, deployment- and validation-time guardrails.
- At the computational level, it spans AI training to deployment, using three powerful computers — NVIDIA DGX for AI training, NVIDIA Omniverse and NVIDIA Cosmos running on NVIDIA OVX for simulation, and NVIDIA DRIVE AGX for deployment.
Get Started
Watch the NVIDIA DRIVE AGX Thor unboxing video and join the NVIDIA DRIVE AGX SDK Developer Program.
Plus, learn more about NVIDIA Jetson AGX Thor developer kit and NVIDIA Jetson T5000 modules — available today — empowering robotics developers everywhere to build the future of physical AI.
See notice regarding software product information.
