SBIR Phase II: AI-Driven Part Identification that Converts Standard Coordinate Measuring Machines into Autonomous Systems for Automated Part Measurements

The broader/commercial impact of this Small Business Innovation Research (SBIR) Phase II project lies in enabling autonomous part measurement on a Coordinate Measuring Machine (CMM), transforming how precision components are inspected in manufacturing. By automating part identification, program selection, and measurement execution, this innovation reduces manual intervention, minimizes errors, and significantly increases inspection throughput on the shop floor. This advancement has the potential to lower manufacturing costs, improve quality control, and address skilled labor shortages in industries such as aerospace, medical devices, and automotive manufacturing. The project will also enhance scientific and technological understanding of autonomous metrology by integrating advanced computer vision, machine learning, and robotics with established CMM workflows. By closing the loop between part production and inspection in a fully automated pipeline, the technology will enable real-time quality control and adaptive manufacturing, accelerating the adoption of advanced manufacturing practices. This project supports the competitiveness of U.S. manufacturers, enabling small and medium-sized enterprises to adopt a capability that was not previously available in the market. Overall, this innovation will contribute to building resilient, high-quality manufacturing ecosystems while advancing the field of intelligent, autonomous measurement systems. This Small Business Innovation Research (SBIR) Phase II project addresses the challenge of automating part measurement on Coordinate Measuring Machines (CMMs), a critical bottleneck in high-precision manufacturing. Currently, CMM inspection requires manual part identification, program selection, and positioning, resulting in delays, human errors, and inefficient use of metrology resources. The objective of this research is to develop and validate an autonomous measurement system that combines advanced computer vision, machine learning, and robotics with CMM operations to enable lights-out inspection. The proposed work will create algorithms for robust part recognition under varying lighting and positioning conditions, automate inspection routine selection and execution, and incorporate real-time feedback to detect errors or anomalies during measurement. The system is designed for seamless integration onto new CMMs and can also be retrofitted onto existing machines at customer sites, extending the utility of existing CMMs using low-cost vision systems. The project will include integration efforts at CMM manufacturer sites and pilot customer sites to ensure system robustness across diverse part geometries and shop floor environments. Anticipated technical results include a fully functional autonomous measurement workflow, significant reductions in inspection cycle times, and improved measurement reliability, advancing scalable, intelligent quality assurance in advanced manufacturing. 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.