Tutorial for Visual SLAM Using a HAWK Camera


This tutorial walks you through setting up Isaac ROS Visual SLAM with a Hawk camera.

Tutorial Walkthrough - VSLAM Execution

  1. Complete the Hawk setup tutorial.

  2. Complete the VSLAM quickstart here.

  3. [Terminal 1] Inside the container, install the dependencies:

    sudo apt-get install -y \
       ros-humble-isaac-ros-correlated-timestamp-driver \
       ros-humble-isaac-ros-hawk \
       ros-humble-isaac-ros-image-proc \
  4. [Terminal 1] Run the launch file inside the container and wait for 5 seconds:

    ros2 launch isaac_ros_visual_slam isaac_ros_visual_slam_hawk.launch.py
  5. [Terminal 2] In a second terminal check that the VSLAM node is publishing the odometry messages.

    Attach another terminal to the running container for issuing other ROS 2 commands.

    cd ${ISAAC_ROS_WS}/src/isaac_ros_common

    Verify that you are getting the output from the visual_slam node at the same rate as the input.

    ros2 topic hz /visual_slam/tracking/odometry --window 20

Typically, if you are running visual_slam on Jetson, it is recommended that you NOT evaluate with live visualization.