Joint work between Visual attention and Grasping groups

From Wiki for iCub and Friends
Jump to: navigation, search

How to measure the location of the target

At some point we need to estimate the location of the target for grasping. For this we need some help from the visual attention group.

  • We are going to calibrate the cameras of the robot with the help of Jonas
  • Alexis and Baris are going to test the artoolkit program in the repository to see what kind of information we can get from visual markers (artoolkit need some visual calibration too)
  • From calibrated images we can measure the distance of the object from its size (ball detector from Matteo? or the artoolkit markers)
  • If the estimated position of the target is not precise enough we might need to try a visual servoing approach