Siemens Technology (Principal Investigator), The Boeing Company, and Southwest Research Institute (SwRI).
The ARM Institute’s strategic collaboration with the JROBOT Working Group resulted in the identification, funding, and execution of several robotics for manufacturing programs addressing pervasive Department of Defense (DoD) sustainment needs. The ARM Institute-funded Autonomous Coating with Realtime Control and Inspection Project was a result of this collaboration and the project team recently performed the program’s final out-brief meeting and demonstration. The project successfully demonstrated the feasibility of a (1) low fidelity paint model to quickly and autonomously determine the critical robotic coating parameters to yield the desired thickness and (2) real-time visual inspection made possible by machine learning trained using purely simulated data.
Coating operations play a critical role in preventing the loss of DoD assets to damage, which is estimated to cost $20 billion annually. Coating operations also have significant commercial applications in the airline, shipping, construction, and manufacturing industries. An automated solution could have great impact for both the DoD and the ARM Membership as a whole.
The application of coatings on vehicles, ships, aircraft and facilities is currently a time and labor-intensive operation. In addition, these operations are hazardous for workers (carcinogenic, flammable coating materials, elevated platforms).
The coating quality and consistency also varies significantly from one operator to another. Insufficient coating leads to part damage (corrosion in metals and erosion in composites) while excess coating results in material wastage and increased weight, which is particularly important in aviation.
Similarly, the inspection of coated surfaces is also largely manual task that requires experts to assess the paint quality by looking at the surface. Inspecting larger structures also has high infrastructure costs due to the use of elevators and cranes, which often do not adapt to differences in the shapes of the structures.
The Autonomous Coating with Realtime Control and Inspection Project focused on developing the technologies to build an autonomous painting and inspection system that could provide any worker with high quality painting capabilities through a an autonomous painting and inspection system that is able to not only adapt to the physical requirements of painting large structures but also paint effectively to minimize the problems of insufficient/excess paint and minimize human involvement in such operations.
The developed technology is an enabler to use large robotic systems with flexibility across different paint operations, and to different manufacturing operations. There are three key principles of the project.
- The project centers on taking automation to the part. This means that the robotic motions are derived from the observed (i.e. scanned) geometry of the part, which itself is unknown. All paint robots in manufacturing lines have fixed motions that are repetitive and cannot adjust to the part if the geometry changes. The scan-n-plan technology from ROS-Industrial is adopted here. The same approach is usable for operations like sanding, polishing, deburring, paint stripping, cold spray coating, and others.
- The project also accounts for physics properties of the process and its relation to environmental and robotic variables. Painting operations are complex and expensive to perform. Having a model that captures the paint deposition is useful to validate paint operations before they are physically performed.
- The project also uses a simulated defect generation pipeline for training inspection models. Collecting data for real world defects is an expensive and time consuming operation. A simulation based defect generation using image processing techniques allow for creating inexpensive synthetic data that is used to train deep neural network models.
During the execution of the projects funded in collaboration with the JROBOT Summit, project team members worked closely with DoD personnel to ensure that the projects were on track to generate impact for the DoD. This collaboration between industry, government, and academia is key to the success and impact of ARM Institute-funded projects.
The technology developed by the program team successfully applied a coating at the appropriate paint thickness on a test coupon using a low fidelity model that could autonomously generate robot input parameters based on the desired thickness results. This demonstrates that the practice of developing a simplified and executable model to optimize a coating applications is feasible.
Based on the results, we can conclude that further refinement and development of this technology can potentially produce considerable cost savings, improved quality, and better safety.
Secondly, using only simulated data, the team used machine learning methods to train and develop a computationally efficient defect inspection model. The demonstration showed that approximately 70% of the defects were identified. The demonstration of this technology demonstrates the feasibility of this approach which can be improved and applied to other inspection techniques.
Impact for the Department of Defense (DoD):
The automation of painting and the application of advanced coatings remains a high priority for the DoD. The Autonomous Coating with Realtime Inspection project addresses some of the key robotic capabilities and technologies that are critical needs towards achieving autonomous mobile multi-agent robotic spray systems that are capable of painting large, complex and eventually complete aircraft.
The ARM Institute, in collaboration with the project team, was able to highlight and demonstrate that advanced coating systems have the potential to be safer, higher quality, and optimized for the environment conditions and design parameters.
There is considerable interest in continuing to pursue developing robotic spray solutions by the ARM Institute, the ARM Membership, and key partners within the DoD. Many of the long term benefits are significant, and ARM Institute funded programs like this have identified some of the challenges and demonstrated the potential for considerable improvements.
The ARM Institute, in partnership with the DoD, will continue to work with Siemens Corporate Technology to leverage the results of this program to advance robotic coating capabilities within the sustainment community.
The ARM Institute’s Role
“We would like to thank the ARM Institute for introducing the robotic sustainment program and giving us the chance to work on robotic challenges faced by the DoD. Throughout the project acquisition and execution phase, there was a continuous interaction between the ARM Institute, the DoD, and the project partners in shaping the project towards success. Thanks to the effective project management and tools provided by the ARM Institute, it was possible to co-develop software and hardware technologies among the project partners and manage project deliverables effectively. Beyond the existing scope, the continuous dialogue maintained by the ARM Institute helps in identifying future problems, strategies, and technology transitions together with the DoD and the large ARM community.” – Yash Shahapurkar, Siemens
About the ARM Institute
The ARM (Advanced Robotics for Manufacturing) Institute is a Manufacturing Innovation Institute (MII) funded by the Office of the Secretary of Defense under Agreement Number W911NF-17-3-0004, and part of the Manufacturing USA® network. The ARM Institute leverages a unique, robust, and diverse ecosystem of consortium members and partners across industry, academia, and government to make robotics, autonomy, and artificial intelligence more accessible to U.S. manufacturers large and small, train and empower the manufacturing workforce, strengthen our economy and global competitiveness, and elevate national security and resilience. Based in Pittsburgh, PA since 2017, the ARM Institute is leading the way to a future where people & robots work together to respond to our nation’s greatest challenges and to produce the world’s most desired products. For more information, visit www.arminstitute.org and follow the ARM Institute on LinkedIn and Twitter.