Home

Warning

The AI Accelerator requires ROS 2 Humble, so PolyScope X 10.12.1 is the latest compatible release. PolyScope X 10.13 and later use ROS 2 Jazzy and are not currently supported.

Universal Robots AI Accelerator kit with cobot, Orbbec camera, and embedded NVIDIA Jetson Orin AGX 64GB compute box

AI Accelerator hardware kit — UR cobot with Orbbec Gemini 335Lg camera and embedded NVIDIA Jetson Orin AGX 64GB compute box.

The AI Accelerator is a combined hardware and software platform that enables faster AI development on UR robots.

It creates a bridge between Universal Robots’ PolyScope X platform and NVIDIA’s Isaac ROS platform running on the embedded NVIDIA Jetson Orin AGX 64GB compute box.

PandaI is built as detect → pose → plan → move.

With plentiful examples and new API functionality for interacting with the NVIDIA system directly from the robot teach pendant, it is easier than ever to add enhanced perception and AI capabilities to your cobot solution.

Product overview: universal-robots.com/products/ai-accelerator

What’s in the box

Compute module

3D camera

Embedded NVIDIA Jetson Orin AGX 64GB compute box

Orbbec Gemini 335Lg camera

Embedded NVIDIA Jetson Orin AGX 64GB compute box

Orbbec Gemini 335Lg 3D vision camera

Host login: username lab, password easybot. Default IP on 2.x: 192.168.0.100 (see SDK).

Also included: camera bracket and flange extender, cabling and cable guidance, flyer and manual, and USB cable (GMSL available separately / soon).

Getting started

Follow these pages in order. Skip any step that does not apply to your setup.

  1. Hardware Manual — unpack and wire the AI Accelerator, robot, and camera.

  2. Update PolyScope X to 10.12.1 — install the latest compatible robot OS (USB .wic + Rufus). Skip if the controller is already on 10.12.1. Do not install 10.13 or later.

  3. Centercode — get downloads and check whether the compute module is on 1.x or 2.x.

  4. Upgrade from 1.x — only if the version check shows you are still on 1.x. If you are already on 2.x, skip this page.

  5. GMSL — optional: switch the Orbbec camera from USB to GMSL.

  6. SDK — install the three URCapX packages on the robot, install the SDK .deb on the compute module, and enter the Docker container.

  7. Jetson compute utilities — CPU/GPU load, temperature, power mode, and other host commands on the compute box.

  8. Orbbec Viewer — optional: install Orbbec’s camera GUI on the compute box to check RGB/depth before ROS.

  9. Tools — annotation, Console UI, and RViz.

  10. Examples — run the included demos.

  11. URScript API — program perception and planning from PolyScope X.

  12. Troubleshooting — common setup and runtime issues.

For a reference view of the software components and how they connect, see How PandaI uses NVIDIA Isaac, AI Accelerator Core, and Camera Creator.

Contents

Platform reference