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.

Tutorial for DNN Object Detection with Isaac Sim

https://media.githubusercontent.com/media/NVIDIA-ISAAC-ROS/.github/main/resources/isaac_ros_docs/concepts/object_detection/detectnet/isaac_sim_detectnet_output.png/

Overview

This tutorial walks you through a pipeline for object(people) detection using DetectNet consuming images from Isaac Sim.

Tutorial Walkthrough

  1. Complete the quickstart here.

  2. Launch the Docker container using the run_dev.sh script:

    cd ${ISAAC_ROS_WS}/src/isaac_ros_common && \
      ./scripts/run_dev.sh
    
  3. Run the setup script to download the PeopleNet Model from NVIDIA GPU Cloud(NGC) and convert it to a .etlt file

    cd /workspaces/isaac_ros-dev/src/isaac_ros_object_detection/isaac_ros_detectnet && \
      ./scripts/setup_model.sh --height 720 --width 1280 --config-file resources/isaac_sim_config.pbtxt
    
  4. Launch the pre-composed pipeline launch file:

    cd /workspaces/isaac_ros-dev && \
      ros2 launch isaac_ros_detectnet isaac_ros_detectnet_isaac_sim.launch.py
    
  5. Install and launch Isaac Sim following the steps in the Isaac ROS Isaac Sim Setup Guide

  6. Press Play to start publishing data from the Isaac Sim.

    https://media.githubusercontent.com/media/NVIDIA-ISAAC-ROS/.github/main/resources/isaac_ros_docs/getting_started/isaac_sim_sample_scene.png/
  7. You should see the image from Isaac Sim with the rectangles overlaid over detected people in the frame.