6. ROS2 Navigation

6.1. Learning Objectives

In this ROS2 sample, we are demonstrating Omniverse Isaac Sim integrated with ROS2 Nav2.

6.2. Getting Started


  • This ROS2 Navigation sample is only supported on ROS2 Foxy Fitzroy or later. See the ROS2 website for requirements and installation instructions: https://docs.ros.org/en/foxy/Releases/Release-Foxy-Fitzroy.html

  • The Nav2 project is required to run this sample. To install Nav2 refer to the Nav2 installation page.

  • Enabled the omni.isaac.ros2_bridge extension from the extension manager menu Window->Extensions.

  • This tutorial requires carter_navigation, carter_description, and isaac_ros_navigation_goal ROS2 packages which are provided as part of your Omniverse Isaac Sim download. These ROS2 packages are located under the directory <foxy_ws>/src/navigation/. They contain the required launch file, navigation parameters, and robot model. Complete ROS & ROS 2 Installation, make sure the ROS2 workspace environment is setup correctly.

6.4. Running Nav2

  1. Go to Isaac Examples -> ROS -> Navigation to load the warehouse scenario.

  2. Click on Play to begin simulation.

  3. In a new terminal, run the ROS2 launch file to begin Nav2.

    ros2 launch carter_navigation carter_navigation.launch.py

    RViz2 will open and begin loading the occupancy map. If a map does not appear, repeat the previous step.

  4. Load the URDF model into the RViz2 window by clicking on RobotModel -> Description File and navigate to the location of the Carter URDF model which can be found at the urdf directory in the sample carter_description ROS2 package (carter_description/urdf/carter.urdf).

  5. Since the position of the robot is defined in the parameter file carter_navigation_params.yaml, the robot should already be properly localized. If required, the 2D Pose Estimate button can be used to re-set the position of the robot.

  6. Click on the Navigation2 Goal button and then click and drag at the desired location point in the map. Nav2 will now generate a trajectory and the robot will start moving towards its destination!

6.5. Run ROS2 Navigation with RTX Lidar

Open the scene located at Isaac/Samples/ROS2/Scenario/rtx_lidar_carter_warehouse_navigation.usd

This scene contains the Carter robot with the RTX Lidar. Press play and follow from step 3 onwards above.

Refer to Publish RTX Lidar Point Cloud for using RTX Lidar with ROS2

6.6. Sending Goals Programmatically

The isaac_ros_navigation_goal ROS2 package can be used to set goal poses for the robot using a python node. It is able to randomly generate and send goal poses to Nav2. It is also able to send user-defined goal poses if needed.

  1. Make any changes to the parameters defined in the launch file found under isaac_ros_navigation_goal/launch as required. Make sure to re-build and source the package/workspace after modifying its contents.

    The parameters are described below:

    • goal_generator_type: Type of the goal generator. Use RandomGoalGenerator to randomly generate goals or use GoalReader for sending user-defined goals in a specific order.

    • map_yaml_path: The path to the occupancy map parameters yaml file. Example file is present at isaac_ros_navigation_goal/assets/carter_warehouse_navigation.yaml. The map image is being used to identify the obstacles in the vicinity of a generated pose. Required if goal generator type is set as RandomGoalGenerator.

    • iteration_count: Number of times goal is to be set.

    • action_server_name: Name of the action server.

    • obstacle_search_distance_in_meters: Distance in meters in which there should not be any obstacle of a generated pose.

    • goal_text_file_path: The path to the text file which contains user-defined static goals. Each line in the file has a single goal pose in the following format: pose.x pose.y orientation.x orientation.y orientation.z orientation.w. Sample file is present at: isaac_ros_navigation_goal/assets/goals.txt. Required if goal generator type is set as GoalReader.

    • initial_pose: If initial_pose is set, it will be published to /initialpose topic and goal poses will be sent to action server after that. Format is [pose.x, pose.y, pose.z, orientation.x, orientation.y, orientation.z, orientation.w].

  2. To run the launch file, use the following command:

    ros2 launch isaac_ros_navigation_goal isaac_ros_navigation_goal.launch.py


The package will stop processing (setting goals) once any of the below conditions are met:

  1. Number of goals published till now >= iteration_count.

  2. If GoalReader is being used then if all the goals from file are published, or if condition (1) is true.

  3. A goal is rejected by the action server.

  4. In case of RandomGoalGenerator, if a goal was not generated even after running the maximum number of iterations, which is rare but could happen in very dense maps.

To learn more about programmatically sending navigation goals to multiple robots simultaneously see Sending Goals Programmatically for Multiple Robots.

6.7. Summary

In this tutorial, we covered

  1. Occupancy map

  2. Running Isaac Sim with Nav2.

  3. Running the Isaac ROS2 Navigation Goal package to send nav goals programmatically.

6.7.1. Next Steps

Continue on to the next tutorial in our ROS2 Tutorials series, Multiple Robot ROS2 Navigation to move multiple navigating robots with ROS2.

6.7.2. Further Learning