From Project Funding to a Solved Problem & New Start-Up
In this project highlight, learn how an ARM Institute Technology Project Team both solved a key industry problem and laid the foundation for a new robotics start-up.
Project Team
Carnegie Mellon University (Principal Investigator), Siemens Energy, and Yaskawa
Background
This AI and robotics project sought to automate the internal polishing process on a Siemens Energy combustion turbine transition duct piece, which today is largely completed manually in uncomfortable environments for human operators. Today’s industry standard manual process also risks human errors and often takes more than 8-hours for a skilled worker to polish the complex geometry workpiece.
The development of an automatic robotic polishing system through this project significantly enhanced both the efficiency and quality of the polishing process. The project was recently demonstrated at the ARM Institute’s Pittsburgh headquarters to great success.
Technical Approach
The challenges of robotic automatic grinding lie in how to precisely calibrate the robotic system, how to accurately localize the workpiece, how to plan robot trajectories in real time in confined environments, and how to develop compliant and robust control strategies tailored specifically for polishing tasks.
This project team developed a robotic solution to efficiently remove weld beads through a combination of weld washing, grinding, and polishing techniques. While some manufacturers have introduced robotic solutions for polishing smaller workpieces as a final manufacturing step, these methods are limited in scope and lack adaptability. Typically, in existing approaches, the grinding machine remains stationary, while a robot arm manipulates the workpiece for polishing. However, this restricts its applicability to small-scale pieces and requires manual reconfiguration of the robot trajectory for varying workpiece geometries.
The polishing system catalyzed by this project is composed of five components: laser calibration, tool calibration, surface measurement, path generation, and compliance control for polishing. This design allows autonomous measurement, calibration, planning and execution of unknown workpieces, significantly improving adaptability and efficiency in robotic grinding applications while addressing the challenges of precision, real-time planning and compliance in complex surface finishes.
Impact & New Start-Up
The planning algorithms generated from this project exhibit the highest success rate in comparison to all baseline methods, while maintaining high efficiency. These components collectively enabled the team to achieve precise and efficient weld bead removal. Both quantitative and qualitative evaluations reveal that this method effectively removes weld materials, achieving height tolerances at sub-millimeter precision.
Additionally, Carnegie Mellon University team members from this project leveraged the outputs and technology catalyzed through this funding as a foundation to start a new business: Instinct Robotics. Contact Weiye Zhao at [email protected] to learn more about Instinct Robotics.
Learn More & Access Further Outputs from this Project
ARM Institute Members have access to the outputs, including consortium developed intellectual property (CDIP), presentations, demo recordings, reports, and more, from this project and others through the ARM Member Community.
ARM Members can log into the Member Community here or email [email protected] for assistance.
Not an ARM Member? The ARM Institute catalyzes collaboration across our 450+ member organizations spanning industry, government, and academia to spur robotics, AI, and workforce solutions to strengthen U.S. manufacturing. We do this through funded projects, such as the on outlined above, networking, knowledge-sharing, and more.
Learn more about membership here.
ABOUT THE ARM INSTITUTE
The Advanced Robotics for Manufacturing (ARM) Institute is a Manufacturing Innovation Institute (MII) funded by the Office of the Secretary of Defense under Agreement Number W911NF-17-3-0004 and is part of the Manufacturing USA® network. The ARM Institute leverages a unique, robust, and diverse ecosystem of 400+ 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, with a satellite office in St. Petersburg, FL, 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 X (formerly Twitter).
Join our mailing list