abstract
- As opposed to flat or planar extrusion additive manufacturing, the benefits of multi-plane and curved fused deposition of material are conclusive; however, several issues need to be considered and solved when a robotic manipulator is used for the deposition of material. The path and motion planning for printing using robotics need considerations to guarantee adequate results. This work presents the projection of a printing trajectory on a tessellated surface and a Reinforcement Learning strategy that optimizes the angular displacement of the joints. The validation of the strategy is presented under simulated conditions inserting different obstacles for a projected zigzag printing pattern on a curved surface. Results show that this approach can choose the optimal inverse kinematic solution to optimize the movement of the main joints of a robot with six degrees of freedom while avoiding different obstacles. The strategy was tested on an actual printing of a re-entrant pattern on a curved surface using an extruder attached to a collaborative robot UR3.