I-Corps: Artificial Intelligence (AI)-Enabled and Digital Twin Interactive Robots for Facility Hygiene and Human Health

University Of Tennessee Knoxville, Knoxville TN

Investigators

Abstract

The broader impact/commercial potential of this I-Corps project is the development of a mobile disinfection device. The COVID-19 pandemic, seasonal epidemics of flu, and other infections placed heavy burdens on society. This proposed technology may improve current cleaning and disinfection practices with an intelligent robotic system. The proposed solution is designed to improve cleaning and disinfection efficacy, enhance personal hygiene and public health, and relieve the high workload and exposure risks facing cleaning and disinfection workers. These benefits may reduce the facility operational costs as well as opportunity costs from infection within facilities, and generate positive societal and economic impacts. The proposed service business model may facilitate the adoption of disinfection and service robots as a flexible choice, creating new opportunities and serving broader areas in the post-pandemic age. This I-Corps project is based on the development of an artificial intelligence (AI)-enabled and digital-twin interactive robot that adapts to ambient environments, social processes, and building dynamics for automated, continuous, precise, and socially-friendly disinfection. The key innovations include using a digital-twin based simulation and deep learning environment to train the robots to predict and perceive contaminated areas for precision disinfection at both the building and room levels. This research improves surface disinfection efficiency and effectiveness. Pathogen infection risks derived from data-driven modeling and simulation may provide a new stream of information for robot navigation to prioritize disinfection routes. In addition to the precision disinfection that specifically targets contaminated areas, the robots will learn to understand the social contexts (e.g., human activity and privacy within a room) to operate in the presence of humans without interrupting normal activities and exposing harmful substances such as ultraviolet lights to humans, enabling safe and socially-friendly disinfection. Augmented by high-fidelity virtual simulations, imitation learning will be developed to train the robots to learn the social and physical constraints and adapt their disinfection maneuvers with respect to the context and object geometry enabling complete, efficient, and safe disinfection. The technology may enable a single smart solution to maintain environmental hygiene and human health. 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.