3. Human robot interaction

Human robot interaction (HRI) is an emerging research area, originating from the fast increasing integration of robots in our daily lives. In contrast to conventional human computer interaction models which usually involve interaction between users and a passive machine, human robot interaction is influenced by several factors. Researchers have tried to categorize HRI approaches. Goodrich and Schultz [33], divided HRI into two broad categories i.e. remote interaction and proximate interaction, based on the proximity level of both human and robot during interaction. According to Sheridan [34], HRI can be divided based on nature of application, i.e. tele-robots, tele-operators and social robots. HRI model for tele-robots mainly consists of human supervisory control of robots in performance of routine tasks. Such robots have limited capability of automation and rely on commands of their human supervisor. Telerobots are mostly used in assembly lines, packaging, mail sorting, offices, and hospitals. They are capable of sensing their environment and reporting back to a human operator. HRI model for tele-operators involves remote control of robots in challenged environments like space, air, terrestrial, and under water for non-routine tasks. Both of these interaction models are basically master–slave in nature. Interaction with social robots is different from that of tele-robots and tele-operators mainly because it perceives robots not just as slaves but as peer-to-peer collaborators.

#### 3.1. Human robot social interaction

According to Dautenhahn [35], human robot social interaction approaches can be divided into three general categories, i.e. robot-centered approaches, human-centered approaches and robot cognition-centered approaches. In robot-centered HRI model, social robots are preprogrammed to interact with humans. Sociable robots are usually designed based on such approaches. They proactively engage people in a social manner and the interaction is designed to be mutually beneficial for both participants i.e. humans can be motivated to perform a specific task (e.g. for therapeutic purposes etc.) whereas robots can use the conversation for learning purposes. On the other hand, socially evocative robots are designed to interact with humans based on human-centered perspective. Anthropomorphism plays a key role in such kind of interaction. In a way, human participant attributes social responsiveness to the robot participant. Reasoning and consequently learning capabilities of the robot are not central objective in this HRI model. Socially interactive robots have instigated another HRI approach which is centered on robot cognition. These robots aim to intelligently interact with their human counterparts. Nevertheless such type of HRI models are greatly influenced by various factors and mainly require deep modeling of human cognition.
