Dataset Preparation - Prerequisites
This section describes the necessary setup steps before starting data preparation.
INFO
When executing terminal commands in this document, refer to the indicators below to run them on the correct PC or Docker container
USER PC: Your PC with the camera connected, used for dataset collection with Physical AI Tools🐋 OPEN MANIPULATOR: Open Manipulator Docker container🐋 PHYSICAL AI TOOLS: Physical AI Tools Docker container
Launch the Camera Node
Navigate to open_manipulator/docker directory and enter the Docker container:
USER PC
cd open_manipulator/docker./container.sh enterUSER PC 🐋 OPEN MANIPULATOR
Then, launch the wrist USB camera node:
ros2 launch open_manipulator_bringup camera_usb_cam.launch.pyAlternatively, you can customize the camera topic namespace and video device (serial). By default, name=camera1 and video_device=/dev/video0.
ros2 launch open_manipulator_bringup camera_usb_cam.launch.py name:=camera1 video_device:=/dev/video0Launch the Physical AI Server
Navigate to physical_ai_tools/docker directory and enter the Docker Container:
USER PC
cd physical_ai_tools/docker./container.sh enterLaunch Physical AI Server with the following command:
USER PC 🐋 PHYSICAL AI TOOLS
ros2 launch physical_ai_server physical_ai_server_bringup.launch.pyOr, use shortcut command:
ai_serverLaunch the ROS 2 Teleoperation Node
Navigate to open_manipulator/docker directory and enter the Docker container:
USER PC
cd open_manipulator/docker./container.sh enterThen, launch the ROS 2 teleoperation node with the following command:
WARNING
Executing the code will cause OMX to move immediately. Please stay clear and be cautious.
USER PC 🐋 OPEN MANIPULATOR
ros2 launch open_manipulator_bringup omx_ai.launch.py