wiki:ConveyorDetection

Version 3 (modified by vmatare, 3 months ago) (diff)

--

This page documents the Carologistics' conveyor detection system. As of 2019, it is comprised of the conveyor_plane and conveyor_pose plugins.

Recording Models

  • set record_model: true
  • observe record_path
  • start fawkes

conveyor_pose will now keep atomically overwriting record_path with the current trimmed scene.

  • move the gripper to (0,0,0) in the conveyor_calib frame
  • open up rviz and enable the following displays:
    • TF gripper_fingers_record
    • TF conveyor_cam
    • PointCloud2 /fawkes_pcls/trimmed
    • PointCloud2 /fawkes_pcls/model
  • Move the robot/MPS to position the gripper_fingers_record frame where you want the origin of the model to be. The model that is being written is displayed twice, once at its "real" location (topic /fawkes_pcls/trimmed), and once with its origin transformed into the camera frame (topic /fawkes_pcls/model).
  • Adjust the trim box to crop out anything you don't want in the model.
  • Make a few copies of the recorded model, pick out a nice looking one an possibly remove artifacts and noisy areas using CloudCompare.