SBIR Phase II: AI-DRIVEN PERSONALIZATION FOR SCALABLE CUSTOM-FIT FOOTWEAR

Award ID: 2335226

The broader impact/commercial potential of this Small Business Innovation Research (SBIR) Phase II project addresses the limitations of mass-produced footwear sizing by introducing size-inclusive bespoke custom-fit shoes. Poorly fitted footwear is an increasingly costly and painful problem with growing human, economic, and environmental implications. Incorrect footwear fit is a significant driver of foot pain and disorders, including toe deformities, corns, foot ulceration, and ankle pain. Additionally, e-commerce is on the rise, wherein up to 40% of shoes purchased online are returned with poor fit as the biggest driver. These reduce retail margins and increase footwears carbon footprint. Custom-fit shoes can solve the problem of poor fit; however, traditional custom-fit is a labor-intensive process. Advancements in artificial intelligence can modernize and scale custom-fit shoe manufacturing, potentially reducing price points and lead times. The proposed project aims to implement an automated solution for custom-fit footwear with three methods: (1) smartphone-based foot scanning and fit survey to obtain foot measurements and footwear construction preferences utilizing artificial intelligence, (2) automation of shoe last personalization, and (3) adaptive shoe componentry for custom-fit shoe construction. The project utilizes artificial intelligence and machine learning, 3D modeling, computer vision, and 3D manufacturing to: (i) develop and deploy a highly accurate virtual foot image-to-measurements machine learning model; (ii) expand a shoe last library to train and implement a machine learning model for foot measurement-to-shoe last prediction; (iii) manufacture custom-fit shoes by combining personalized last with a compatible adaptive sole; and (iv) establish a customer feedback system for iterative shoe modification by incorporating user qualitative responses and sole wear patterns. 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.

NSF Program Director: Alastair Monk