A Network Robot System for Cooperative Guide Service in a Shopping Mall

Abstract

In this paper, we report a field trial with a network robot system in a shopping mall. Our network robot system consists of three components: environmental sensors, network robot platform and social robots. Multiple laser range finders are used as the environmental sensors to estimate people's positions. Position data is used to estimate such human walking behaviors as “stopping” or “idle walking,” to direct robots to provide appropriate tasks to appropriate people. By using this information, the network robot platform coordinates multiple social robots to provide efficient service to customers. It coordinates the tasks of robots based on their positions and people's walking behavior, the paths of robots, and the conversation-performance between two robots. Each social robot interacts with people to provide recommendation information about shops and route information of the mall. The system sometimes simultaneously uses two robots to lead people from one place to the specific shop. We conducted a field trial in a shopping mall, in which four robots interacted with 414 people. It demonstrated the effectiveness of the network robot system for guiding people around a shopping mall as well as increasing their interest.