Sign in Subscribe
Artificial intelligence

Nvidia Launches Powerful New "Brain" for Robots: Jetson Thor

Strategic Insights

— 1 min read

Nvidia has announced the launch of the Jetson Thor module, a powerful new "brain" for robots that aims to make humanoid machines as quick-thinking and sure-footed as experienced workers. This new $3,499 developer kit promises to deliver unmatched performance and scalability, enabling roboticists to process high-speed sensor data and perform visual reasoning at the edge. The Jetson Thor module is designed to power the next generation of AI-powered humanoid robots and can be installed in production-ready robots made by Amazon or Meta.

Key Takeaways:

  • The Jetson Thor module delivers 7.5x more AI compute, 3.1x more CPU performance, and 2x more memory than its predecessor, the NVIDIA Jetson Orin.
  • The new "brain" for robots promises to enable roboticists to process high-speed sensor data and perform visual reasoning at the edge, opening new possibilities for multimodal AI applications such as humanoid robotics.
  • The Jetson Thor chip is powered by the company's top-end Blackwell chips and comes with 128 GB of memory, making it ideal for running large AI models.
  • The new developer kit will start shipping next month, and the company's stock has rose slightly on the news.
  • The Jetson Thor family includes a developer kit and production modules, which support all popular generative AI frameworks and AI reasoning models with unmatched real-time performance.
  • Thousands of software companies can now elevate their traditional vision AI and robotics applications with multi-AI agent workflows running on Jetson Thor, with leading adopters including Openzeka, Rebotnix, Solomon, and Vaidio.
  • More than 2 million developers use NVIDIA technologies to accelerate robotics workflows.

Statistics:

  • The Jetson Thor module delivers 7.5x more AI compute than its predecessor, the NVIDIA Jetson Orin.
  • Jetson Thor promises "unmatched performance and scalability" to deliver a massive amount of power needed to run generative AI models.
  • The Jetson Thor chip comes with 128 GB of memory, making it ideal for running large AI models.
  • The Jetson ecosystem supports a variety of application requirements, high-speed industrial automation protocols, and sensor interfaces, accelerating time to market for enterprise developers.
  • More than 2 million developers use NVIDIA technologies to accelerate robotics workflows.

Sources:

  • Nvidia blog post
  • Statement from Peggy Johnson, CEO of Agility Robotics
  • Times Content article

Read more