Attention
As of June 30, 2025, the Isaac ROS Buildfarm for Isaac ROS 2.1 on Ubuntu 20.04 Focal is no longer supported.
Due to an isolated infrastructure event, all ROS 2 Humble Debian packages that were previously built for Ubuntu 20.04 are no longer available in the Isaac Apt Repository. All artifacts for Isaac ROS 3.0 and later are built and maintained with a more robust pipeline.
Users are encouraged to migrate to the latest version of Isaac ROS. The source code for Isaac ROS 2.1
continues to be available on the release-2.1
branches of the Isaac ROS
GitHub repositories.
The original documentation for Isaac ROS 2.1 is preserved below.
Repositories and Packages
Use this index to find the Isaac ROS packages you need and examples on how to use them.
Repository |
Package(s) |
Description |
---|---|---|
CUDA-accelerated AprilTag detection and pose estimation. |
||
ROS 2 packages based on NVIDIA |
||
ROS 2 package which adds on top of |
||
– |
Common utilities, packages, scripts, Dockerfiles, and testing infrastructure for Isaac ROS packages. |
|
Hardware accelerated data compression |
||
DNN-based depth segmentation and obstacle field ranging using Bi3D |
||
Hardware-accelerated DNN model inference ROS 2 packages using NVIDIA Triton/TensorRT for both Jetson and x86_64 with CUDA-capable GPU |
||
Deep learned stereo disparity estimation |
||
DNN-based freespace segmentation for navigation |
||
Hardware-accelerated ROS 2 packages for camera image processing. |
||
Hardware-accelerated, deep learned semantic image segmentation |
||
ROS 2 package for map localization |
||
Receives tasks and actions from the fleet management service and update progress, state, and errors |
||
NVIDIA Isaac Transport for ROS package for hardware-acceleration friendly movement of messages |
||
Use Isaac ROS packages in your ROS 1 Noetic with NITROS-enabled performance. |
||
Optimized Isaac ROS packages for Isaac Nova Orin. |
||
Hardware-accelerated 3D scene reconstruction and Nav2 local costmap provider using nvblox |
||
Deep learning model support for object detection including DetectNet |
||
Deep learned, hardware-accelerated 3D object pose estimation |
||
Visual odometry package based on hardware-accelerated NVIDIA cuVSLAM library with world class quality and performance. |