Visible to Intel only — GUID: GUID-FB3F0EFA-7363-4D70-AF64-B449FDCC5072
Run a ROS 2 Sample Application in the Docker* Container
Run an Intel® RealSense™ ROS 2 Sample Application in Docker* Container
Run a GStreamer* Video Pipeline using GStreamer* Plugins in Docker* Container
Run a GStreamer* Audio Pipeline using GStreamer* Plugins in Docker* Container
Run a GStreamer* Video Pipeline using libv4l2 in Docker* Container
Run a GStreamer* Video Pipeline using the Intel® RealSense™ Plugin in the Docker* Container
Optional (Only for Sony* IMX390 Setups): Run a GStreamer* Video Pipeline using Sony’s IMX390 MIPI Sensor in Docker* Container
Run OpenVINO™ Sample Applications in Docker* Container
Run ROS 2 OpenVINO™ Toolkit Sample Applications in Docker* Container
Run Intel® oneAPI Base Toolkit Sample Applications in Docker* Container
Run Profiling Application in Docker* Container with VTune™ Profiler
Run OpenVINO™ Benchmarking Tool
Run the ADBSCAN Algorithm
Launch Wandering Application with Gazebo* Simulation
Launch Wandering Application on AAEON* Robot Kit
Launch Cartographer with 2D LIDAR
Run FastMapping Algorithm
Run ROS 2 Navigation Sample Applications Using the ITS Path Planner Plugin in a Docker* Container
ITS Path Planner Plugin Customization
Run the Edge Insights for Autonomous Mobile Robots Container in KVM Guest
Run a Collaborative SLAM System
Run the Sample Application
Troubleshooting
Build New and Custom Docker* Images from the Edge Insights for Autonomous Mobile Robots SDK
Troubleshooting for Robot Tutorials
Visible to Intel only — GUID: GUID-FB3F0EFA-7363-4D70-AF64-B449FDCC5072
Run a Collaborative SLAM System
This tutorial tells you how to run a collaborative SLAM system using two ROS 2 bags that simulate two robots exploring the same area.
The ROS 2 tool rviz2 is used to visualize the two robots, the server, and how the server merges the two local maps of the robots into one common map.
The output includes the estimated pose of the camera and visualization of the internal map.
All input and output are in standard ROS 2 formats.
Prerequisites:
The main input is a camera, either monocular, or stereo, or RGB-D.
IMU and odometry data are supported as auxiliary inputs.
Run the Sample Application
Go to the AMR_containers folder:
cd <edge_insights_for_amr_path>/Edge_Insights_for_Autonomous_Mobile_Robots_<version>/AMR_containers
Prepare environment setup:
source 01_docker_sdk_env/docker_compose/05_tutorials/config/docker_compose.source export CONTAINER_BASE_PATH=`pwd` export ROS_DOMAIN_ID=17 # If the bags were not extracted before do it now unzip 01_docker_sdk_env/docker_compose/06_bags.zip -d 01_docker_sdk_env/docker_compose/
Run the collaborative SLAM algorithm using two bags simulating two robots going through the same area:
CHOOSE_USER=eiforamr docker-compose -f 01_docker_sdk_env/docker_compose/05_tutorials/cslam.demo.yml up
On the server rviz2, both trackers are seen.
In the above figure:
Red indicates the path robot 1 is taking right now.
Blue indicates the path robot 2 took.
Green dots represent points that are known to the server.
Troubleshooting
Odometry feature use_odom:=true does not work with these bags.
The ros2 bags used in this example do not have the necessary topics recorded for the odometry feature of collaborative slam.
If the use_odom:=true parameter is set, the collab-slam will report errors.
The bags fail to play.
The collab_slam docker is started with the local user and needs access to the ros2 bags folder.
Make sure that your local user has read and write access to this path: <path to edge_insights_for_amr>//Edge_Insights_for_Autonomous_Mobile_Robots_*/AMR_containers/01_docker_sdk_env/docker_compose/06_bags
The best method is if your user is the owner of the folder. If the package was installed with sudo, please chown the folder to your local user.
For general robot issues, go to: Troubleshooting for Robot Tutorials.