Edge Insights for Autonomous Mobile Robots (EI for AMR) Developer Guide
Run the ADBSCAN Algorithm
This tutorial tells you how to run the ADBSCAN algorithm from EI for AMR using 2D Slamtec* RPLIDAR and Intel® RealSense™ camera input.
It outputs to the obstacle_array topic of type nav2_dynamic_msgs/ObstacleArray.
Prerequisites: You know how to connect and configure a Slamtec* RPLIDAR sensor. For details, see: Launch Cartographer with 2D LIDAR.
Run the ADBSCAN Algorithm with Slamtec* RPLIDAR Input
Go to the AMR_containers folder:
cd <edge_insights_for_amr_path>/Edge_Insights_for_Autonomous_Mobile_Robots_*/AMR_containers
Prepare the 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 # Unzip the ros2 bags if they were not unzipped before unzip 01_docker_sdk_env/docker_compose/06_bags.zip -d 01_docker_sdk_env/docker_compose/
Depending on the Slamtec* RPLIDAR availability, you have two possibilities:
Slamtec* RPLIDAR connected
Start a pre-configured yml file that starts the LIDAR Node and then the ADBSCAN application:
CHOOSE_USER=eiforamr docker-compose -f 01_docker_sdk_env/docker_compose/05_tutorials/adbscan_LIDAR.tutorial.yml up
No Slamtec* RPLIDAR connected
Start a pre-configured yml file that plays a ROS 2 bag containing LIDAR data and then the ADBSCAN application:
CHOOSE_USER=eiforamr docker-compose -f 01_docker_sdk_env/docker_compose/05_tutorials/adbscan_2D.tutorial.yml up
Expected output: ADBSCAN prints logs of its interpretation of the LIDAR data coming from the ROS 2 bag.
Run the ADBSCAN Algorithm with Intel® RealSense™ Camera Input
Go to the AMR_containers folder:
cd <edge_insights_for_amr_path>/Edge_Insights_for_Autonomous_Mobile_Robots_<version>/AMR_containers
Prepare the 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 # Unzip the ros2 bags if they were not unzipped before unzip 01_docker_sdk_env/docker_compose/06_bags.zip -d 01_docker_sdk_env/docker_compose/
Depending on the Intel® RealSense™ camera availability, you have two possibilities:
Intel® RealSense™ camera connected
Start a pre-configured yml file that starts the Intel® RealSense™ node and then the ADBSCAN application:
CHOOSE_USER=eiforamr docker-compose -f 01_docker_sdk_env/docker_compose/05_tutorials/adbscan_RealSense.tutorial.yml up
No Intel® RealSense™ camera connected
Start a pre-configured yml file that plays a ROS 2 bag containing Intel® RealSense™ data and then the ADBSCAN application:
CHOOSE_USER=eiforamr docker-compose -f 01_docker_sdk_env/docker_compose/05_tutorials/adbscan_RS.tutorial.yml up
Expected result: rviz2 starts, and you see how ADBSCAN interprets Intel® RealSense™ data coming from the ros2 bag:
Troubleshooting
For general robot issues, go to: Troubleshooting for Robot Tutorials.