ai-vision-ros2
Install latest/stable of ai-vision-ros2
Ubuntu 16.04 or later?
Make sure snap support is enabled in your Desktop store.
Install using the command line
sudo snap install ai-vision-ros2Don't have snapd? Get set up for snaps.
Details for ai-vision-ros2
Package name
- ai-vision-ros2
License
- unset
Last updated
- 25 August 2026 - latest/stable
- 8 September 2026 - nvidia/edge
Report a Snap Store violation
Report ai-vision-ros2 for a Snap Store violation
Snap Store Violation Report submitted successfully
Thank you for your report. Information you provided will help us investigate further.
Error submitting report
There was an error while sending your report. Please try again later.
Share this snap
Generate an embeddable card to be shared on external websites.
SO-101 Depth Anything V2 (Small) depth visualisation (ROS 2 Jazzy)
CPU monocular depth visualisation for the SO-101 arm. Subscribes to a ROS 2 image topic, runs Depth Anything V2 (Small) with ONNX Runtime, and republishes both a colorised relative-depth image (for viewing) and a raw normalised depth map (32FC1, for downstream consumers such as so101_safety).
This is the "ai-vision-ros2" snap's DEPTH variant, published on the
latest/stable channel. The model weights are bundled directly in this snap
(fetched from Hugging Face at build time) -- no content interface, no
separate model snap, no manual snap connect step required.
The SAME snap name also has a completely different PERSON-DETECTION variant (YOLOv8n, so101_yolo_demo) published on latest/edge -- swap between them live with:
snap refresh ai-vision-ros2 --channel=edge # -> person detection
snap refresh ai-vision-ros2 --channel=stable # -> back to depth
Runs as an always-on daemon (like usb-cam). Configure it with snap set
instead of launch arguments, e.g.:
snap set ai-vision-ros2 input-image-topic=/my/camera/image_raw
snap set ai-vision-ros2 output-image-topic=/camera/depth/visualization
snap set ai-vision-ros2 output-depth-topic=/perception/depth
snap set ai-vision-ros2 min-period-s=0.1
Other options: model-input-size, publish-width, publish-height, intra-op-threads, namespace, node-name, ros-domain-id, rmw-implementation.
Check status with snap services ai-vision-ros2 / snap logs ai-vision-ros2.
| Revision | Channel | Version | Build | Commit |
|---|
The build and commit information is derived from build infrastructure records.
Install ai-vision-ros2 on your Linux distribution
Choose your Linux distribution to get detailed installation instructions. If yours is not shown, get more details on the installing snapd documentation.
