Visible to Intel only — GUID: GUID-6B1A5AAB-A9F8-4BC0-8B21-373F38281E08
UPS 6000 and UP Xtreme i11 Robot Kits
Create Your Own Robot Kit
Perception
Navigation
Simulation
Benchmarking and Profiling
EI for AMR Container on a Virtual Machine
Fibocom’s FM350 5G Module Integration
Change Existing and Add New Docker* Images to the EI for AMR SDK
Troubleshooting for Robot Tutorials
Spatial Partitioning and Search Operations with Octrees
Constructing a Convex Hull Polygon for a 3D Point Cloud
Detecting Specific Models and Their Parameters in 3D Point Clouds
Plane Model Segmentation
Surface Reconstruction with Intel® oneAPI Base Toolkit's Moving Least Squares (MLS)
Intel® oneAPI Base Toolkit's Iterative Closest Point (ICP)
KdTree Search Using Intel® oneAPI Base Toolkit's KdTree FLANN
Downsampling 3D Point Clouds with a Voxelized Grid
Filtering Point Clouds with a Passthrough Filter
PCL Optimizations Outside of Docker* Images
Optimized PCL Known Limitation
Optimized PCL Troubleshooting
Visible to Intel only — GUID: GUID-6B1A5AAB-A9F8-4BC0-8B21-373F38281E08
Step 3: Robot Base Node ROS 2 Node
Introduction to Robotic Base Node
The Edge Insights for Autonomous Mobile Robots pipeline assumes that the robot base ROS 2 node:
Publishes odom and base_link
odom is used by the Navigation 2 package and others to get information from sensors, especially the wheel encoders. See this Navigation 2 tutorial on odometry for more information.
base_link represents the center of the robot to which all other links are connected.
Creates the transform between odom and base_link
Is subscribed to cmd_vel which is used by the Navigation 2 package to give instructions to the robot like spin in place or move forward
In Edge Insights for Autonomous Mobile Robots, there are two examples:
cd <edge_insights_for_amr_path>/Edge_Insights_for_Autonomous_Mobile_Robots_*/AMR_containers ls 01_docker_sdk_env/artifacts/01_amr/amr_generic/param/pengo_nav.param.yaml ls 01_docker_sdk_env/artifacts/01_amr/amr_generic/param/aaeon_node_params.yaml # These are configuration files that the robot base nodes of Pengo and UP Xtreme i11 robotic kits. ls 01_docker_sdk_env/docker_compose/05_tutorials/aaeon_wandering__aaeon_realsense_collab_slam_fm_nav2.tutorial.yml ls 01_docker_sdk_env/docker_compose/05_tutorials/pengo_wandering__kobuki_realsense_collab_slam_fm_nav2.tutorial.yml # These are yaml files that start the full pipeline that makes these robots wander and area and map it. # In them you can find how each nodes are started.
One is for AAEON’s UP Xtreme i11 Robotic Kit, and the other is for Cogniteam’s Pengo robot.
Robotic Base Node Deep Dive
NOTE:
The following commands only work only if they are run on Cogniteam’s Pengo robot or AAEON’s UP Xtreme i11 Robotic Kit.
Using the Cogniteam’s Pengo robot and AAEON’s UP Xtreme i11 Robotic Kit as references and starting their node like this:
cd <edge_insights_for_amr_path>/Edge_Insights_for_Autonomous_Mobile_Robots_*/AMR_containers source ./01_docker_sdk_env/docker_compose/common/docker_compose.source export CONTAINER_BASE_PATH=`pwd` export ROS_DOMAIN_ID=27 # for Cogniteam's Pengo robot docker-compose -f 01_docker_sdk_env/docker_compose/05_tutorials/pengo_wandering__kobuki_realsense_collab_slam_fm_nav2.tutorial.yml up kobuki # or for UP Xtreme i11 Robotic Kit docker-compose -f 01_docker_sdk_env/docker_compose/05_tutorials/aaeon_wandering__aaeon_realsense_collab_slam_fm_nav2.tutorial.yml up aaeon-amr-interface
In a different terminal, attach to the opened Docker* image:
docker exec -it amr-aaeon-amr-interface bash # or docker exec -it amr-kobuki bash source ros_entrypoint.sh export ROS_DOMAIN_ID=27
You can check the following:
ROS 2 topics
ros2 topic list # The result for UP Xtreme i11 Robotic Kit is similar to: # /amr/cmd_vel # /amr/imu/raw # /amr/initial_pose # /amr/odometry # /parameter_events # /rosout # /sensors/battery_state # /tf # The result for the Pengo robot contains multiple topics but the crucial to this pipeline are: # /cmd_vel # /joint_states # /rosout # /odom # /parameter_events # /tf
odom and base_link frames
ros2 run tf2_tools view_frames.py cp frames.pdf /home/<user> # Open the pdf through file explorer, it should look similar to:
Did you find the information on this page useful?
Feedback Message
Characters remaining: