{"id":1013879,"date":"2026-10-27T07:05:05","date_gmt":"2026-10-27T11:05:05","guid":{"rendered":"https:\/\/www.marketnewsdesk.com\/index.php\/stereolabs-launches-zed-box-2-series-for-physical-ai-and-vision-in-production-robots\/"},"modified":"2026-10-27T07:05:05","modified_gmt":"2026-10-27T11:05:05","slug":"stereolabs-launches-zed-box-2-series-for-physical-ai-and-vision-in-production-robots","status":"publish","type":"post","link":"https:\/\/www.marketnewsdesk.com\/index.php\/stereolabs-launches-zed-box-2-series-for-physical-ai-and-vision-in-production-robots\/","title":{"rendered":"Stereolabs Launches ZED Box 2 Series for Physical AI and Vision in Production Robots"},"content":{"rendered":"

<\/p>\n

Stereolabs Launches ZED Box 2 Series for Physical AI and Vision in Production Robots<\/b><\/p>\n

The high-performance edge AI series brings up to 2070 TFLOPS of compute, innovative cooling, and native support for up to 8 synchronized GMSL2 cameras for 360\u00b0 multi-view perception.<\/i><\/p>\n

PARIS–(BUSINESS WIRE<\/a>)–Stereolabs<\/a>, an Ouster, Inc.<\/a> company and leader in 3D AI vision, today introduced the ZED Box 2 Series, a new generation of industrial edge AI computers engineered for autonomous mobile robots (AMRs), robot vision, and spatial AI systems requiring high-throughput multi-camera perception and edge processing.<\/p>\n

This press release features multimedia. View the full release here: https:\/\/www.businesswire.com\/news\/home\/20261027977847\/en\/<\/a><\/p>\n

\"Stereolabs<\/p>\n

Stereolabs ZED Box 2 with 4 ZED X stereo cameras and 4 ZED X One S connected<\/p>\n<\/div>\n

\nZED Box 2 Max takes vision AI computing to the next level. Powered by NVIDIA\u00ae Jetson Thor\u2122 with up to 2,070 FP4 TFLOPS and 128 GB of memory, ZED Box 2 Max is built to run generative AI, vision-language-action (VLA) models and multi-sensor fusion directly on the robot, enabling advanced perception and real-time decision-making at the edge.<\/p>\n

\nRobots are moving from pilots to fleets, and each machine now carries multiple cameras and sensors. At that scale, the interface is a key aspect: GMSL2 has become the interface of choice for robot vision due to its low latency and reliability. Additionally, robotics teams want a complete system instead of separate components: AI compute, hardware synchronized sensors, and software that keeps working release after release.<\/p>\n

\n“Robot vision shouldn\u2019t take five suppliers,” said Edwin Azzam, CTO and co-founder of Stereolabs. \u201cWith ZED Box 2 Series, we provide robotics developers with the unified compute, cameras, lidar, and perception software that come from one team that tests them together and stands behind all of it. Plug in your cameras and you can have reliable 360\u00b0 perception in minutes, not weeks.”<\/p>\n

Up to 8x Cameras for Full Surround Perception<\/b><\/p>\n

\nDesigned for complex visual environments where a single stereo sensor is insufficient, the ZED Box 2 Series natively supports up to eight GMSL2 camera inputs via dual Quad Fakra-Z connectors. This enables integration of up to eight ZED X cameras for full 360-degree surround vision, multi-angle robotic cell manipulation, and multi-sensor fusion with high resolution digital lidar.<\/p>\n

\nTo ensure accurate temporal alignment across high-speed camera streams, the ZED Box 2 Series features hardware-level frame synchronization via a dedicated SYNC + IO interface, supporting internal synchronization and external trigger modes across multiple devices. Capabilities include:<\/p>\n