News Summary:<\/p>\n
\n\tNVIDIA Jetson AGX Thor developer kit and production modules, robotics computers designed for physical AI and robotics, are now generally available.
\n\tOver 2 million developers are using NVIDIA\u2019s robotics stack, with Agility Robotics, Amazon Robotics, Boston Dynamics, Caterpillar, Figure, Hexagon, Medtronic and Meta among early Jetson Thor adopters.
\n\tJetson Thor, powered by NVIDIA Blackwell, offers 7.5x more AI compute and 3.5x greater energy efficiency compared with its predecessor, Jetson Orin, unlocking real-time reasoning inference, critical for highly performant physical AI applications.
\n\tJetson Thor solves one of the most significant challenges in robotics: enabling robots to have real-time, intelligent interactions with people and the physical world.
<\/p>\n
NVIDIA today announced the general availability of the NVIDIA Jetson AGX Thor\u2122<\/a> developer kit and production modules, powerful new robotics computers designed to power millions of robots across industries including manufacturing, logistics, transportation, healthcare, agriculture and retail.<\/p>\n Early adopters include industry leaders Agility Robotics<\/a>, Amazon Robotics, Boston Dynamics, Caterpillar, Figure, Hexagon, Medtronic and Meta, while 1X, John Deere, OpenAI and Physical Intelligence are evaluating Jetson Thor to advance their physical AI capabilities.<\/p>\n \u201cWe\u2019ve built Jetson Thor for the millions of developers working on robotic systems that interact with and increasingly shape the physical world,\u201d said Jensen Huang, founder and CEO of NVIDIA. \u201cWith unmatched performance and energy efficiency, and the ability to run multiple generative AI models at the edge, Jetson Thor is the ultimate supercomputer to drive the age of physical AI and general robotics.\u201d<\/p>\n The Ultimate Platform for Next-Generation Robotics Compared with its predecessor, the NVIDIA Jetson Orin<\/a>\u2122, Jetson Thor delivers up to 7.5x higher AI compute and 3.5x greater energy efficiency to run any generative AI<\/a> model \u2014 from vision language action models like NVIDIA Isaac\u2122 GR00T N1.5<\/a> to popular large language and vision language models.<\/p>\n The new system-on-module solves one of the most significant challenges in robotics: running multi-AI workflows to enable robots to have real-time, intelligent interactions with people and the physical world. Jetson Thor unlocks real-time inference, critical for highly performant physical AI applications spanning humanoid robotics<\/a>, agriculture and surgical assistance.<\/p>\n Global Robotics Leaders Build on Jetson Thor<\/p>\n Jetson Thor is powered by the full-stack NVIDIA Jetson\u2122 software platform<\/a>, built for physical AI and humanoid robotics, which supports any popular AI framework and generative AI model. It is also fully compatible with NVIDIA\u2019s software stack from cloud to edge, including NVIDIA Isaac<\/a> for robotics simulation and development, Isaac GR00T<\/a> humanoid robot foundation models, NVIDIA Metropolis<\/a> for vision AI and NVIDIA Holoscan<\/a> for real-time sensor processing.<\/p>\n
\nPowered by an NVIDIA Blackwell GPU and featuring 128GB of memory, Jetson Thor delivers up to 2,070 FP4 teraflops of AI compute to effortlessly run the latest AI models \u2014 all within a 130-watt power envelope.<\/p>\n