LAUSR

This paper presents planning algorithms for robotic cleaning of stains on nonplanar surfaces. Access to different portions of the stain may require frequent repositioning and reorienting of the object. Some portions with prominent stain may require multiple passes to remove the stain completely. Two robotic arms have been used in the experiments. The object is immobilized with one arm and the cleaning tool is manipulated with the other. The algorithm generates a sequence of reorientation and repositioning moves required to clean the part after analyzing the stain. The plan is generated by accounting for the kinematic constraints of the robot. Our algorithm uses a depth-first branch-and-bound search to generate setup plans. Cleaning trajectories are generated and optimal cleaning parameters are selected by the algorithm. We have validated our approach through numerical simulations and robotic cleaning experiments with two KUKA robots.Note to Practitioners—We encounter nonrepetitive cleaning tasks everyday in both industrial and household environments. Variations in stain pattern, geometry, and material of the object make it difficult to manually program robots for such tasks. In this paper, we present planning algorithms to automate the cleaning task using robots. The practical impact of our approach is evidenced by the actual robot results involving realistic examples like cleaning of hard paint stains on curved surfaces and rust on metal surfaces. Practitioners from industry can use the methods presented in this paper to develop automated robotic systems for nonrepetitive tasks like cleaning and polishing. Our approach caters to the primary requirements of these applications like multiple setups, multiple passes within each setup, and determination of optimal motion parameters like velocity, force, and oscillation frequency of the cleaning tool.