ROS 2 Roboreg

ROS 2 integration for roboreg.

Table of Contents

• Installation
• Nodes
  • Monocular Depth
  • Autoreg
  • Static TF Broadcaster

Installation

• Install roboreg version 0.4.5:

Note

When using differentiable rendering, CUDA Toolkit is required at runtime, refer CUDA Toolkit Install Instructions.

pip3 install roboreg==0.4.5

• Build this roboreg ROS 2 integration

mkdir -p lbr-stack/src && cd lbr-stack
git clone https://github.com/lbr-stack/ros2_roboreg.git -b rolling src/ros2_roboreg
rosdep install --from-paths src -r -i -y
colcon build --symlink-install

Nodes

• Monocular Depth
• Autoreg
• Static TF Broadcaster

Monocular Depth

This node performs eye-to-hand calibration from RGB images and corresponding depth images. This does e.g. apply to

• RealSense cameras (monocular + depth)
• ZED cameras (monocular or stereo + depth)

To run, simply do

ros2 launch roboreg_nodes reg.launch.py mode:=monocular_depth

Sample configurations are provided in monocular_depth.yaml. Please note that compressed image / depth topics are also supported.

Subscribed Topics

• /camera/image_rect_color
• /camera/image_rect_color/camera_info
• /camera/depth_registered
• /camera/depth_registered/camera_info
• /joint_states
• /robot_description

Published Topics

• /camera/image_rect_color/render

Services

• collect_data
• clear_data
• register/hydra_icp
• export/data
• export/transform
• import/transform
• broadcast_transform

Autoreg

Utility node for executing trajectory via ros2_control and collecting samples via roboreg_nodes.

ros2 run roboreg_nodes autoreg --help

Static TF Broadcaster

Utility node for publishing static transform as acquired through roboreg_nodes.

ros2 run roboreg_nodes broadcaster --help

Acknowledgements

Organizations and Grants

We would further like to acknowledge following supporters:

Logo	Notes
	This work was supported by core and project funding from the Wellcome/EPSRC [WT203148/Z/16/Z; NS/A000049/1; WT101957; NS/A000027/1].
	This project has received funding from the European Union's Horizon 2020 research and innovation programme under grant agreement No 101016985 (FAROS project).
	Built at RViMLab.
	Built at CAI4CAI.
	Built at King's College London.