Spontaneous Human-Robot Emotional Interaction Through Facial Expressions

摘要

One of the main issues in the field of social and cognitive robotics is the robot's ability to recognize emotional states and emotional interaction between robots and humans. Through effective emotional interaction, robots will be able to perform many tasks in human society. In this research, we have developed a robotic platform and a vision system to recognize the emotional state of the user through its facial expressions, which leads to a more realistic human-robot interaction (HRI). First, a number of features are extracted according to points detected by a vision system from the face of the user. Then, the emotional state of the user is analyzed with the help of these features. For the decision making unit, a state machine is designed that utilizes the results obtained from the emotional state analysis to generate the robot's response. Finally, a fuzzy algorithm is used to improve the quality of emotional interaction and the results are implemented on a commercial humanoid robot platform which has the ability of producing facial expressions.