Effectiveness of Cooperative Customer Navigation from Robots around a Retail Shop

Abstract

Applying the technologies of a network robot system, we incorporate the recommendation methods used in E-commerce in a retail shop in the real world. We constructed a platform for ubiquitous-networked robots that focuses on a shop environment where communication robots perform customer navigation. The platform estimates customer interests from their pre-purchasing behaviors observed by networked sensors without concrete IDs and controls visible-type communication robots in the environment to perform customer navigation. The system can perform collaborative filtering-based recommendations without excessively intruding upon the privacy of customers. Since observations and recommendations in real environments are intrinsically annoying, the robot scenarios are also important for interacting with customers as well as the system. Two types of navigation scenarios are implemented and investigated in experiments using 80 participants. The results indicate that in the cooperative navigation scenario, the participants who interacted with the communication robots located both outside and inside the shop felt friendlier toward the robots and found it easy to understand what they said.