Conceptual Spaces and Robotic Emotions

Abstract

In recent years, there has been a growing interest in modelling emotional responses inside the perception—action loop of an autonomous robot. One of the motivations of this trend is that an emotional system could introduce complex decision making capabilities in robots in a faster and more flexible way than symbolic deliberative architectures. However, recent proposals in literature model emotions at a very low level (Arkin et al., 2003, Murphy et al., 2002). Briefly, a robot emotional state is simply associated with suitable parameters of the reactive behaviors. Instead, emotions may have an important role at a higher, conceptual level of reasoning of the robot. It is claimed that the emotional states of an agent may be related with its internal motivations (Balkenius, 1995). For example, an agent has a pleasure response when its motivations are well satisfied. More in details, a difference is usually made between primary and higher-order emotions. Primary emotions are related with the immediate perceptions and motivations of the agent. They can be hardwired or, if learned, they are difficultly forgotten. Higher-order emotions are instead related with the long—term motivations of the agent; in general they are learned during the operation tasks. In the proposed system, both primary and higher-order robot emotions are represented in terms of a conceptual space (Gardenfors, 2000). The system has been implemented in the autonomous robot operating at the Robotics Laboratory of the University of Palermo (a RWI B21 equipped with laser and stereo head). The task of the robot is to offer guided tours in the Museum of Electrical Equipments at the Department of Electrical Engineering.