Abstract
Service robots with social interactive features are developed to cater to the demand in various application domains. These robots often need to approach toward users to accomplish typical day-to-day services. Thereby, the approaching behavior of a service robot is a crucial factor in developing social interactivity between users and the robot. In this regard, a robot should be capable of maintaining proper proxemics at the termination position of an approach that improves the comfort of users. Proxemics preferences of humans depend on physical user behavior as well as personal factors. Therefore, this paper proposes a novel method to adapt the termination position of an approach based on physical user behavior and user feedback. Physical behavior of a user is perceived by the robot through analyzing skeletal joint movements of the user. These parameters are taken as inputs for a fuzzy neural network that determines the appropriate interpersonal distance. The preference of a user is learnt by modifying the internal parameters of the fuzzy neural network based on user feedback. A user study has been conducted to compare and contrast behavior of the proposed system over the existing approaches. The outcomes of the user study confirm a significant improvement in user satisfaction due to the adaptation toward users based on feedback.