Build a Radxa X4 ROS2 Car Robot Using Intel Robotics SDK

Before we start, I am open to collaborating with hardware manufacturers to promote your products by creating engaging tutorials for multiple online platforms. Please feel free to email me at mikrik@mxlfrbt.com

I invite you to use a Radxa X4 to build a ROS2 powered robot featuring Robotics SDK and Realsense 3D Vision camera technology.

In this tutorial you will learn more about Robotics SDK software using Radxa X4 board as host part of the system.

Briefly About Robotics SDK

A development Robotics SDK software aimed to boost development of the AMR(Autonomous Mobile Robots) robots in logistics, last-mile delivery and industrial automatisation service fields. I say Robotics SDK product is a Robotics OS for robot OEMs manufacturers. This robust solution upgrades mobile robots with the most cutting-edge, industrial-grade functionality available at Intel.

Robotics SDK equips AMR robots with essential autonomy skills for precise localization and navigation, complemented by an advanced set of ITS Path Planned Navigation Plugins. It works using Intel-proprietary algorithms and products like ADBSCAN, CollabSLAM. These products facilitate seamless and autonomous operation.

Prerequisites

• Firstly, if you don't have any ROS robot then follow Part 1 of the MIKRIK Robotics tutorial here. Build a tele-operated car robot, running ROS1 Raspberry node. After you made it, continue following steps described here.
• If you have any ROS robot, you can add VSLAM functionality to it by following steps below. You can setup ROS1-ROS2 bridge with your robot, or run all communications using ROS2 if your robot runs ROS2. If you have /cmd_vel topic provided by your robot, you can communicate between a robot and Robotics SDK host software with minimal changes. Read more here
• Currently CAD files are not available for a free download, and you can only purchase plastic chassis on Tindie, or replace chassis with any other bought on the internet.

Cost-cut Ideas

• Buy a second-hand Realsense camera on Ebay ~100$. It can be D415, D430, D435 or D435i, and so on.

Part 1 Power your Radxa X4 Platform

Step 1.2 Wiring update

To power Radxa X4 board you can use a powerbank with Type-C cable.

Mikrik Radxa X4 Robot Video

Now I will share steps to make Visual SLAM based on Realsense D435i camera work in three modes: mapping, localization, and localization with navigation. Of course, you can use any other Realsense camera, just replace camera name in config file, like GMSL Realsense camera.

Part 2 Setup Robotics SDK on your Radxa X4 host computer

Step 2.1 Install Ubuntu 22.04 for Intel IoT

Download a Ubuntu 22.04 Desktop version Intel IoT for Radxa X4 Intel Atom X7000E Series CPU here

If you already have installed 22.04 LTS Ubuntu Desktop, you may try to replace kernel with kernel for Intel IoT. It worked for me. Steps are described here.

Note: When I installed the necessary Ubuntu Dekstop version I lost my built-in WiFi module connectivity, didn't investigate it further, and installed an external Wi-Fi dongle that worked straight from the box. If you met with the same problem, let me know, maybe necessary to build a drivers for a built-in WiFi module that are not included in the Intel IoT kernel.

Step 2.2 Install Intel Robotics SDK

Follow official documentation page Getting Started Guide

During the installation steps choose genXe in the prompt terminal window.

When you will reach the step to install actually Robotics SDK, using command below, check if it works:

sudo apt install ros-humble-robotics-sdk

In my case, I got an error, and was not able to install Robotics SDK it using default apt method

For me it worked only using aptitude command with a few tricks.

sudo aptitude install ros-humble-robotics-sdk

When it will print you a first solution, type "n".

Second solution, and again type "n".

Third solution, and again type "n".

The last time type "n".

And on the fifth solution solution suggestion, type "Y".

Type "Y" here too.

Step 2.3 Update camera namespace

Remove unnecessary namespace 'camera'.

Open configuration file

sudo vi /opt/ros/humble/share/realsense2_camera/launch/rs_launch.py

Delete default value 'camera' of the camera_namespace. That means line below change from

{'name': 'camera_namespace',  'default': 'camera', 'description': 'namespace for camera'}

to

{'name': 'camera_namespace',  'default': '', 'description': 'namespace for camera'}

Part 3 Mapping Mode using Robotics SDK

Before launch Mapping and Localization you need to change files in the default Robotics SDK installation folder.

Step 3.1 Clone The Github Repository With Launch Files

Clone the repo mikrik_robotics_sdk

cd ~
git clone https://github.com/mxlfrbt/mikrik_robotics_sdk.git

Step 3.2 Mapping Mode Setup

Collab Visual SLAM mapping is done using two ROS2 nodes: univloc_tracker and univloc_server, each of them has a separate launch file. Please, read more about Collab SLAM on the Robotics SDK page here.

Make a copy of the Univloc Tracker Launch file

sudo cp /opt/ros/humble/share/univloc_tracker/launch/tracker.launch.py /opt/ros/humble/share/univloc_tracker/launch/tracker_mikrik.launch.py

Open newly created file using sudo:

sudo vi /opt/ros/humble/share/univloc_tracker/launch/tracker_mikrik.launch.py

In L21 replace string

configFilePath = os.path.join(get_package_share_directory('univloc_tracker'),'config','tracker.yaml')

with the string that leads to the new config file in a folder cloned from my Github repo

configFilePath = '/home/<your-username-here>/mikrik_robotics_sdk/tracker_configs/mikrik_robot_tracker.yaml'

Tracker file is ready. Make sure that path <your-username-here> to the config file mikrik_tracker.yaml is the correct one.

Now you have to edit Univloc Server launch file.

Make a copy of the file Univloc Server launch file

sudo cp /opt/ros/humble/share/univloc_server/launch/server.launch.py /opt/ros/humble/share/univloc_server/launch/server_mikrik.launch.py

Open server file again using sudo

sudo vi /opt/ros/humble/share/univloc_server/launch/server_mikrik.launch.py

Replace in a newly created file L104 from

rviz_config = os.path.join(get_package_share_directory('univloc_server'), 'config', 'rviz2_server.rviz')

to

rviz_config = '/home/<your-username-here>/mikrik_robotics_sdk/rviz_configs/mikrik_server_localization_nav2.rviz'

Make sure that inside the bridge launch script is the correct path to the sourced files. Open file, and replace sample file names with your system specific file names, path, and Ethernet IP address.

vi ~/mikrik_robotics_sdk/scripts/mikrik_bridge_launch.sh

Make script executable

cd ~/mikrik_robotics_sdk/scripts/
sudo chmod u+x realsense_collabslam_mapping.sh

Step 3.3 Mapping Mode Launch Commands

SSH and launch ROS1 node on Raspberry PI firstly.

ssh <username>@<raspberry-ip-address>

Then enter ros folder

cd ~/mikrik/ros

Change to root

sudo su

Source variables and launch all ROS1 nodes

source devel/setup.bash
roslaunch mikrik_description bringup.launch

Now SSH from your host computer to Radxa

ssh <username>@<radxa-ip-address>

Then launch VNC on Radxa

vncserver -localhost no -geometry 1920x1080 -depth 16 :42

Then open Terminal, and launch bridge and mapping commands below.

Launch the ROS1-ROS2 bridge on Radxa

cd ~/mikrik_robotics_sdk/scripts/
./mikrik_bridge_launch.sh

In a second terminal tab finally launch Mapping Mode on your x86 Radxa board

cd ~/mikrik_robotics_sdk/scripts/
./realsense_collabslam_mapping.sh

After launching the script, the RViz window will open. Enable the "Map" checkbox to display the 2D map in RViz. By default, this option is disabled.

Now you can drive robot around and build map.

Mapping Process

Part 4 Robotics SDK Localization Mode

Localization uses the same tracker file, but a different configuration file. I created a copy of the tracker file with a mark "loc" meaning "localization". It will contain a path to the different tracker config file, to make it work in localization mode.

Step 4.1 Localization Mode Setup

Create a copy of the tracker file again

sudo cp /opt/ros/humble/share/univloc_tracker/launch/tracker_mikrik.launch.py /opt/ros/humble/share/univloc_tracker/launch/tracker_mikrik_loc.launch.py

Open tracker_mikrik_loc.launch.py file using sudo

sudo vi /opt/ros/humble/share/univloc_tracker/launch/tracker_mikrik_loc.launch.py

In L21 replace string

configFilePath = '/home/<your-username-here>/mikrik_robotics_sdk/tracker_configs/mikrik_robot_tracker.yaml'

to the string that leads to the new config file

configFilePath = '/home/<your-username-here>/mikrik_robotics_sdk/tracker_configs/mikrik_robot_tracker_localization.yaml'

Make script executable

cd ~/mikrik_robotics_sdk/scripts/
sudo chmod u+x realsense_collabslam_localization.sh

Step 4.2 Localization Mode Launch Commands

Notes: Make sure script contains correct path to all files. Assuming that ROS1-ROS2 bridge is already running.

Launch Localization Mode

cd ~/mikrik_robotics_sdk/scripts/
./realsense_collabslam_localization.sh

After you launched localization mode, very important to check that your rviz opened correctly. Map created during the Mapping Step must be loaded, and visible in rviz, you must see moving TF-tree of the robot.

Make sure that rviz title name on the top of window shows the path to the config file mikrik_server_localization_nav2.rviz.

If it is not, then double check that path to the rviz config file is a correct in file

/opt/ros/humble/share/univloc_server/launch/server_mikrik.launch.py

You no need to close rviz window, proceed with navigation node setup.

Localization Process

Part 5 Navigation Mode

Now you can get navigating on the map.

Step 5.1 Navigation Setup

Create a copy of the default nav2 launch file:

sudo cp /opt/ros/humble/share/nav2_bringup/launch/navigation_launch.py /opt/ros/humble/share/nav2_bringup/launch/mikrik_cslam_nav2_launch.py

Add two remappings.

Open with sudo launch file

sudo vi /opt/ros/humble/share/nav2_bringup/launch/mikrik_cslam_nav2_launch.py

Add two remapping into section in L57 Instead of

remappings = [('/tf', 'tf'),
              ('/tf_static', 'tf_static')]

Add remappings

remappings = [('/tf', 'tf'),
              ('/tf_static', 'tf_static'),
              ('/cmd_vel', '/mobile_mikrik/cmd_vel'),
              ('/map', '/univloc_server/map')]

Save file.

Change inside navigation script realsense_collabslam_navigation.sh path to the nav2 configuration file relevant to your file system

cd ~/mikrik_robotics_sdk/scripts/
vi realsense_collabslam_navigation.sh

Change in line L4 path to the config file

params_file:=<your-username-here>/mikrik_robotics_sdk/nav2_configs/mikrik_robot_nav2.param.yaml

Now you can launch Navigation node!

Step 5.2 Navigation Mode Launch

Make sure that ROS1-ROS2 Bridge, and Localization node are running!

Make script executable

cd ~/mikrik_robotics_sdk/scripts/
sudo chmod u+x realsense_collabslam_navigation.sh

Launch it by running

cd ~/mikrik_robotics_sdk/scripts/
./realsense_collabslam_navigation.sh

If everything is correct, you will see that localization rviz window got updated with a costmap on it.

Navigation Process

Tips

You might also install realsense-viewer to check your camera performance and to update its firmware. Follow official Realsense guide to install GUI interface app for your camera.

Troubleshooting

• If you don't see TF tree and map, make sure that ROS1-ROS2 bridge running on Radxa X4.
• If brdige is runnning, make sure that you launched ROS1 nodes on Raspberry side.

Slack Support Channel

Met an issue? Please join my Slack channel or leave comments below the post.

Todo list

• Radxa X4 GPIO support. Switch from Raspberry Pi ROS1 GPIO readings fully to the Radxa X4 GPIO. It will require to rework existing Mikrik ROS1 source code for Raspberry Pi4.

Custom E-Learning Courses For Your Company

I'm writing a custom E-Learning courses for your company, for more details, please, contact me https://www.tmlr.pl