Static Reconstruction with RealSense

This tutorial demonstrates how to perform depth-camera based reconstruction using a RealSense camera, Isaac ROS Visual SLAM and Isaac ROS Nvblox.


This tutorial requires a compatible RealSense camera from the list of available cameras.

RealSense Camera Firmware

This example is tested and compatible with RealSense camera firmware version


The latest RealSense firmware (version 5.14 at the time of publishing) might have issues. Our recommendation is to install exactly version

Host System Setup

The ROS 2 message delivery might be unreliable under high load without some small modifications to the QoS profile (especially on weaker machines). Before running this example, run one of the following:

To set the parameter temporarily, until reboot:

sudo sysctl -w net.core.rmem_max=8388608 net.core.rmem_default=8388608

To set the parameter permanently, run:

echo -e "net.core.rmem_max=8388608\nnet.core.rmem_default=8388608\n" | sudo tee /etc/sysctl.d/60-cyclonedds.conf

See DDS tuning for more information.

Installing the Dependencies

  1. Complete steps 1 and 2 described in the Nvblox Quickstart Guide to set up your development environment and clone the required repositories.

  2. Stop Git tracking the COLCON_IGNORE file in the realsense_splitter package and remove it.

    cd ${ISAAC_ROS_WS}/src/isaac_ros_nvblox/nvblox_examples/realsense_splitter && \
      git update-index --assume-unchanged COLCON_IGNORE && \

Note: The COLCON_IGNORE file was added to remove the dependency to realsense-ros for users that don’t want to run the RealSense examples.

  1. Complete the Isaac ROS RealSense Setup to set up librealsense outside of the isaac_ros_common Docker, clone realsense_ros, and to configure the container for use with RealSense.

  2. Launch the Docker container using the script:

    cd ${ISAAC_ROS_WS}/src/isaac_ros_common && \
  3. Inside the container, install package-specific dependencies using rosdep:

    cd /workspaces/isaac_ros-dev/ && \
      rosdep install -i -r --from-paths src --rosdistro humble -y --skip-keys "libopencv-dev libopencv-contrib-dev libopencv-imgproc-dev python-opencv python3-opencv nvblox"
    sudo apt-get install -y ros-humble-isaac-ros-stereo-image-proc ros-humble-isaac-ros-visual-slam
  4. Build and source the workspace:

    cd /workspaces/isaac_ros-dev && \
      colcon build --symlink-install && \
      source install/setup.bash

Example with RealSense Live Data

  1. Complete the sections above.

  2. Connect the RealSense device to your machine using a USB 3 cable/port.

  3. Run the ROS Docker container using the script:

    cd ${ISAAC_ROS_WS}/src/isaac_ros_common && \
  4. Source the workspace:

    source /workspaces/isaac_ros-dev/install/setup.bash
  5. Verify that the RealSense camera is connected by running realsense-viewer:

  6. If successful, run the launch file to spin up the example:

    ros2 launch nvblox_examples_bringup


If you want to restrict odometry to a 2D plane (for example, to run a robot in a flat environment), you can use the flatten_odometry_to_2d argument.

Example with RealSense Recorded Data

If you want to run the example on recorded data refer to the RealSense Data Recording for Nvblox.


See RealSense Issues.