SBIR Phase II: Smart Robotic Sanding Cells for Composite Parts in High-Mix Applications

This award is funded in whole or in part under the American Rescue Plan Act of 2021 (Public Law 117-2). The broader impacts of this Small Business Innovation Research (SBIR) Phase II project seek to improve the quality of life for manufacturing workers, help U.S. manufacturers remain cost-competitive in the global market, and improve the quality of the manufactured parts. The proposed robotic cells may reduce the need for workers to perform ergonomically challenging sanding tasks and reduce the risk of worker injuries on sanding lines. The developed technologies will enable the human operators to focus on high-level decision making and the creative aspects of the manufacturing tasks, while the robotic assistants perform the low-level tedious tasks. Moreover, this technology enables the human operator to guide the team operation. This ability will improve worker productivity. Currently, there are more than 3000 companies in the U.S. performing composite fabrication. Most of these companies face challenges due to a shortage of workers and high labor churn. These challenges lead to longer delivery times. This project may enable manufacturers to improve quality and lower costs. Moreover, the technology may enable manufacturers to reduce time to part delivery by reducing the reliance on human labor and easily scaling production capacity with the change in demand by adding or removing robotic cells. This Small Business Innovation Research (SBIR) Phase II project aims to develop a robotic sanding solution for high-mix applications by providing safety under uncertainty during robotic sanding and reducing cycle time by fast execution of safe and efficient trajectories by the robot. This award will make computational advances to enable robots to program themselves by automatically generating and safely executing trajectories based on the task description. The project will also enable the computational algorithms to account for the uncertainties present in the environment, making robots useful for sanding operations in high-mix applications. A robotic sanding cell for handling large parts in high-mix applications will be developed by selecting the appropriate sensors and tools. Algorithms will be developed for fast and safe workpiece localization in the robotic cell while the workpiece is secured with a cost-effective, general-purpose, low-cost fixture. Algorithms will be developed to determine the minimum number of setups needed for sanding large parts in the robotic cell and to generate robot trajectories to produce tool motion patterns that ensure efficient and safe sanding operation. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.