{"id":130625,"date":"2026-07-24T10:39:20","date_gmt":"2026-07-24T10:39:20","guid":{"rendered":"https:\/\/www.seeedstudio.com\/blog\/?p=130625"},"modified":"2026-07-24T10:58:06","modified_gmt":"2026-07-24T10:58:06","slug":"introducing-recomputer-j601-carrier-board-a-compact-physical-ai-platform-for-nvidia-jetson-agx-thor","status":"publish","type":"post","link":"https:\/\/www.seeedstudio.com\/blog\/2026\/07\/24\/introducing-recomputer-j601-carrier-board-a-compact-physical-ai-platform-for-nvidia-jetson-agx-thor\/","title":{"rendered":"Introducing reComputer J601 Carrier Board: A Compact Physical AI Platform for NVIDIA\u00ae Jetson AGX Thor\u2122"},"content":{"rendered":"\n
\"\"<\/figure>\n\n\n\n

Built for embodied AI development and production, reComputer J601 Carrier Board is a compact edge AI platform designed for NVIDIA Jetson AGX Thor, combining up to 2070 TFLOPS AI computing performance with robotics-focused connectivity for humanoid robots, robotic arms, and Physical AI applications.<\/strong><\/p>\n\n\n\n

\n\n\n\n

Bringing NVIDIA Jetson AGX Thor AI Computing Power to Physical AI Robotics<\/h2>\n\n\n\n

Robotics is entering a new era driven by Physical AI.<\/p>\n\n\n\n

Unlike traditional robots that execute predefined commands, next-generation intelligent robots need to perceive their surroundings, understand complex environments, process multimodal information, and make real-time decisions. This evolution requires powerful edge AI computing platforms capable of running advanced models directly on robotic systems.<\/p>\n\n\n\n

NVIDIA Jetson AGX Thor is designed for robotics, humanoid robots, and Physical AI workloads, delivering the computing performance required for real-time AI inference at the edge. Built on NVIDIA\u2019s advanced architecture, Jetson AGX Thor delivers up to 2070 TFLOPS of AI computing performance<\/strong>, enabling demanding workloads including vision AI, large language models (LLMs), vision-language-action (VLA) models, and multimodal AI applications.<\/p>\n\n\n\n

\"\"<\/figure>\n\n\n\n

However, bringing this level of AI intelligence into real-world robots requires more than computing power alone. Developers need a compact and flexible hardware platform that can connect high-performance AI computing with cameras, sensors, controllers, and robotic systems.<\/p>\n\n\n\n

That is where reComputer J601 Carrier Board<\/a><\/strong> comes in.<\/p>\n\n\n\n

reComputer J601: The Compact AI Computing Platform for Humanoid and Embodied AI Robots<\/h2>\n\n\n\n

The reComputer J601 Carrier Board is a compact edge AI carrier board designed specifically for the NVIDIA Jetson AGX Thor module, providing the connectivity and expansion capabilities required for robotics and Physical AI development.<\/p>\n\n\n\n

By combining Thor\u2019s advanced AI computing capability with robotics-focused connectivity and expansion, J601 provides the foundation for building intelligent machines that can perceive, reason, and interact with the physical world.<\/p>\n\n\n\n

With a compact 168mm \u00d7 153mm footprint<\/strong>, J601 is designed for space-constrained robotic platforms, making it especially suitable for humanoid robot development, robotic prototypes, and embedded AI applications.<\/p>\n\n\n\n

Together with Jetson AGX Thor\u2122, J601 provides the computing foundation for humanoid robots and embodied AI systems, supporting advanced AI workloads including:<\/p>\n\n\n\n

    \n
  • Vision AI Models for Robotics Perception \u2014 enabling robots to perceive and understand their surroundings through tasks such as object detection, tracking, and localization. Developers can deploy vision AI models such as YOLO for real-time object detection and LocateAnything for vision-language object localization, enabling robots to perceive and understand their surroundings.<\/li>\n\n\n\n
  • Large Language Models (LLMs) \u2014 enabling robots to understand natural language instructions, perform reasoning, and support intelligent task planning.<\/li>\n\n\n\n
  • Vision-Language-Action (VLA) Models \u2014 combining visual perception, language understanding, and robot control to enable intelligent manipulation and autonomous behaviors, such as NVIDIA\u00ae Isaac\u2122 GR00T for humanoid robot learning, imitation learning, and autonomous manipulation.<\/li>\n\n\n\n
  • Multimodal AI Models \u2014 combining vision, language, and sensor information to support advanced scene understanding and embodied AI applications.<\/li>\n\n\n\n
  • Robotics Frameworks \u2014 supporting development ecosystems including NVIDIA Isaac, ROS 1\/2, PyTorch, and Hugging Face.<\/li>\n<\/ul>\n\n\n\n
    \"\"<\/figure>\n\n\n\n

    Designed for Real-World Robotics Integration<\/h2>\n\n\n\n

    Developing intelligent robots requires more than AI inference performance. A robotics computing platform must seamlessly connect multiple sensors, communication systems, and control components.<\/p>\n\n\n\n

    reComputer J601 is designed around these real-world requirements.<\/p>\n\n\n\n

    Rich Robotics Connectivity for AI-Powered Robot Systems<\/h3>\n\n\n\n

    Modern robots rely on high-speed communication between computing modules, cameras, sensors, and controllers.<\/p>\n\n\n\n

    J601 integrates:<\/p>\n\n\n\n

      \n
    • 4\u00d7 10Gb <\/strong>Ethernet<\/strong>RJ45<\/strong> ports<\/strong><\/li>\n\n\n\n
    • 4\u00d7 <\/strong>USB<\/strong> 3.2 Type-A ports<\/strong><\/li>\n\n\n\n
    • HDMI 2.1<\/li>\n\n\n\n
    • CAN \/ CAN-FD interfaces<\/li>\n\n\n\n
    • RS-485 and RS-232\/422\/485 support<\/li>\n<\/ul>\n\n\n\n

      These interfaces enable developers to build scalable robotic architectures for research, prototyping, and production deployment.<\/p>\n\n\n\n

      \n
      \"\"<\/figure>\n\n\n\n
      \"\"<\/figure>\n<\/figure>\n\n\n\n

      Advanced Vision AI With Multi-Camera Support<\/h2>\n\n\n\n

      Perception is fundamental to embodied AI.<\/p>\n\n\n\n

      To help robots understand their environment, reComputer J601 supports up to 8\u00d7 GMSL2 cameras<\/strong> through integrated MAX96712 deserialization, enabling high-bandwidth multi-camera perception systems.<\/p>\n\n\n\n

      Combined with Jetson AGX Thor\u2019s AI computing capability, J601 supports advanced vision AI applications such as:<\/p>\n\n\n\n

        \n
      • BEV (Bird\u2019s Eye View)<\/li>\n\n\n\n
      • Occupancy Grid<\/li>\n\n\n\n
      • SLAM<\/li>\n\n\n\n
      • Object detection<\/li>\n\n\n\n
      • Autonomous navigation<\/li>\n<\/ul>\n\n\n\n

        This allows developers to build robots with stronger environmental awareness and real-time decision-making capabilities.<\/p>\n\n\n\n

        \n