Planning algorithms for multi-setup multi-pass robotic cleaning with oscillatory moving tools

摘要

We present planning algorithms for cleaning stains on a curved object. Removing the stain may require multiple reorientations and repositions of the object and some portions of the stain may require multiple cleaning passes. The experimental setup involves two robot arms. The first arm immobilizes the object. The second arm moves the cleaning tool. The algorithm analyzes the stain and determines the sequence of positions and orientations needed to clean the part based on the kinematic constraints of the robot arm. Our algorithm uses a depth-first branch-and-bound search to generate setup plan solutions. We also compute the cleaning trajectories and select the cleaning parameters to maximize the cleaning performance. The algorithm generates multi-pass trajectories by replanning based on the observed cleaning performance. Numerical simulations and cleaning experiments with two Kuka <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup> robots are used to validate our approach.