I-Corps: Learning-based Navigation Technology-enabled Service Robots for the Retail Industry

The broader impact/commercial potential of this I-Corps project is the development of a retail service robot utilizing state-of-the-art, human-friendly navigation technology developed for densely crowded environments. As per the current industry estimates, retailers are losing $1 trillion worldwide due to inventory aberrations. Retail customers are frequently disappointed by out-of-stock items because of poor inventory management, leading to reduced customer loyalty.

To survive current market trends in which most items may be purchased online, brick-and-mortar stores need to modernize, and use automated solutions wherever possible to free up associates’ time and focus more on the customer experience.

This I-Corps project is based on the development of a robot enabled with state-of-the-art collision avoidance technology. It is capable of operating in crowds of a density greater than 1 person/square meter. The robot detects pedestrian movements using commodity visual sensors and smartly plans a path that is least obtrusive to humans.

The collision avoidance technology also significantly reduces (by > 50%) the occurrence of the robot suddenly freezing or halting, which is a common phenomenon in dense scenarios. The I-Corps program will help better understand the applications of such a robot in the retail industry. The proposed robot will navigate in a densely crowded store and will perform volumetric scans to capture real-time data about the items on the shelves and customer buying patterns, leading to an increase in efficiency and accuracy in managing a store’s inventory.

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.