Abstract: In this attempt, a new approach to automate and improve a robotic painting task process
is described. A direct self-learning programming method is usually adopted, i.e. the operator guides the robot
manually through a complete spraying cycle. However, in order to avoid this time-consuming procedure,
CAD-based or “acquire-compare-recognize” methods have been developed.
This paper presents a general technique that avoids the need for manual programming or CAD drawings
and allows to obtain an optimal trajectory by using the graph theory and operative research techniques.
After image acquisition, a software module called partitioner splits the object into a set of primitives, then
the proposed algorithm is run on the graph in order to generate the optimal path. Then, an optimal trajectory
is planned by imposing parameters as velocity, acceleration, rotation of the wrist, opening/closing
spray gun for every point of the path. The algorithm has been implemented in Matlab™ and Visual Studi -
o.Net™ environments, and extensively tested, both in a simulation environment and on a real painting robot.