KORTHOS / ECOSYSTEM / PRODUCT

ZED Box

About

About ZED Box

ZED Box is a rugged embedded computer built around NVIDIA Jetson modules for processing stereo-camera and AI workloads close to the robot. It provides high-speed camera, networking and expansion interfaces inside an industrial enclosure and can run depth estimation, positional tracking, mapping and neural-network inference from connected ZED cameras.

Stereolabs supplies several compute configurations configured for different performance and power budgets. The system runs the ZED SDK and can host ROS, perception and application software for mobile robots, autonomous machines and multi-camera installations. ZED Box is commercially available with mounting, cable and camera options.

Supply

Supply / Components

  • ZED Box Orin

    Ublox Zed F9p GNSS Option For Zed Box - Positioning & navigation - u-blox - ZED Box Orin is sold with an optional u-blox ZED-F9P RTK GNSS module - source: stereolabs.com

    Source
  • ZED Box Orin

    Nvidia Jetson Orin Compute For Zed Box - Compute & Control - NVIDIA - Stereolabs ZED Box Orin configurations use NVIDIA Jetson Orin compute modules - source: stereolabs.com

    Source
  • ZED Box Orin

    Intel Ax210 Wifi Module For Zed Box - connectivity - Intel - ZED Box Orin is sold with an optional Intel AX210 Wi-Fi module - source: stereolabs.com

    Source

Timeline

  • Stereolabs launches ZED Box Mini Super for edge AI vision

    2025-03-19 - Product Launch - Stereolabs announced the ZED Box Mini Super as a compact embedded AI computer for vision workloads at the edge. The launch tied the product to robotics and smart infrastructure use cases and highlighted its NVIDIA Orin-based processing stack. The release expanded the company's hardware line beyond stereo cameras into deployable edge compute for perception systems.

    Source

Context

Market context

Edge AI computing unit designed to run Stereolabs perception stack locally.

  • Target environment: Robotics, automation and edge-AI systems that need sensing, depth perception, vision processing or local compute.
  • Workflow context: Depth sensing, visual perception, edge processing, object detection, tracking and robot awareness.
  • Customer context: Robot builders, machine-vision teams, automation engineers and edge-AI developers.
  • Deployment model: Commercial or available product positioned for customer use, integration or developer adoption.
  • Commercial maturity: Publicly presented as commercial or available, with maturity depending on deployment scale and support coverage.
  • Adoption constraints: Adoption depends on accuracy, latency, environmental robustness, SDK quality, compute budget and integration with the robot stack.
  • Market position: ZED Box sits in the perception and compute layer that helps robots understand or process the physical world.
  • Adjacent products: ZED cameras, Ouster lidar, Cognex VisionPro, NVIDIA Jetson

Comparable Systems