In the past few years, we have covered a bunch of robots that can draw beautiful pictures. This video from USC Viterbi School of Engineering shows a spray painting robot that can paint a mural like a pro. A mobile manipulator system was used for this task.
As the makers explain, this robot accurately sprays paint on large surfaces by creating a plan based on the given spraying task:
we demonstrate the use of self-supervised batch learning to reduce the number of experiments needed to create a model of the spray tool. We report a mobile base placement planner that determines the minimum base locations required to carry out the spraying task. Lastly, we have developed a image-based perception pipeline that enables the robot to characterize spraying error.
[HT]
