User evaluation of a multi-user social interaction model implemented on a Nao robot

This paper describes the results from a user evaluation of a robot bartender system, which supports situated, social interaction with multiple customers. The system is a Nao-based version of an existing robot bartender, developed in the JAMES project [1]. The Nao-based version has provided us with a local experimentation platform, bearing in mind that our focus is on social multi-user interaction, rather than the robot technology of object manipulation. We will describe the design of the Nao-based system and discuss the differences with the original JAMES system. The user evaluation is similar to an evaluation carried out recently with the JAMES robot, comparing a trained and a handcoded version of the action selection component of the system, which uses Markov Decision Processes [2]. Task success was found to be almost 20% higher with the trained policy, with interaction times being about 10% shorter. Participants also rated the trained system as being significantly more natural, more understanding, and better at providing appropriate attention. These new results on the Nao platform confirm the conclusions of the previous experiment and provide further evidence in favour of the trained action selection mechanism.