Emotional body language displayed by artificial agents

Abstract

Complex and natural social interaction between artificial agents (computer generated or robotic) and humans necessitates the display of rich emotions in order to be believable, socially relevant and accepted, and to generate the natural emotional responses that humans show in the context of social interaction, such as engagement or empathy. Whereas some robots use faces to display (simplified) emotional expressions, for other robots such as Nao, body language is the best medium available given their inability to convey facial expressions. Displaying emotional body language that can be interpreted whilst interacting with the robot should significantly improve naturalness. This research investigates the creation of an Affect Space for the generation of emotional body language to be displayed by humanoid robots. To do so, three experiments investigating how emotional body language displayed by agents is interpreted were conducted. The first experiment compared the interpretation of emotional body language displayed by humans and agents. The results showed that emotional body language displayed by an agent or a human is interpreted in a similar way in terms of recognition. Following these results, emotional key poses were extracted from an actor"s performances and implemented in a Nao robot. The interpretation of these key poses was validated in a second study where it was found that participants were better than chance at interpreting the key poses displayed. Finally, an Affect Space was generated by blending key poses and validated in a third study. Overall, these experiments confirmed that body language is an appropriate medium for robots to display emotions and suggest that an Affect Space for body expressions can be used to improve the expressiveness of humanoid robots.

Multimodal Child-Robot Interaction: Building Social Bonds

“…We previously found that adults were able to interpret body poses displayed by the robot as conveying certain emotions, which is particularly relevant for the Nao robot used in ALIZ-E since it does not have facial articulation and as such is very limited in communicating emotion when not moving its body. We also noted that changing the robot's head position affects the expressiveness of the poses (Beck, Cañamero, & Bard, 2010;Beck, Stevens, Bard, & Cañamero, 2012). As with adults, it was found that moving the head upwards increased children's identification of emotions such as pride, happiness, and excitement, whereas moving the head downwards increased the correct identification for other displays (anger and sadness).…”

Mimebot—Investigating the Expressibility of Non-Verbal Communication Across Agent Embodiments

“…eir results suggested that the perception of emotions are not a ected by the appearance of the character. In a similar setup, Beck et al [5] found that emotions were perceived more strongly on a real actor than on a virtual agent, and that stylized emotions were perceived more strongly than natural.…”

“…Emotional body laguage for the Nao robot was studied by [5] and [12]. For a non-humanoid sphere-shaped robot (Maru), sound, colors, and vibrations were used to express emotional behaviors [26].…”

Living with robots : investigating the user acceptance of social robots in domestic environments

“…Research has shown that human body language can be interpreted accurately without facial or vocal cues (Beck et al, 2012;de Gelder, 2006;Kleinsmith, De Silva, & Biachi-Berthouze, 2006). Based on Cassell (2000) and Vinayagamoorthy et al (2006), Beck et al (2013) robot body language can be classified into three different areas broadly used in the literature: posture, movement and proxemics.…”