View - ResearchGate

Designing Sociable Machines 155quality of the interaction improves. Furthermore, many of these social cueswill eventually be offered in the context of teaching the robot. To be able totake advantage of this scaffolding, the robot must be able to correctly interpretand react to these social cues. There are two cases where the robot can readthe human’s social cues.The first is the ability to recognize praise, prohibition, soothing, and attentionalbids from robot-directed speech [9, 2]. This could serve as an importantteaching cue for reinforcing and shaping the robot’s behavior. Several interestinginteractions have been witnessed between Kismet and human subjectswhen Kismet recognizes and expressively responds to their tone of voice. Theyuse Kismet’s facial expression and body posture to determine when Kismet“understood” their intent. The video of these interactions suggests evidence ofaffective feedback where the subject might issue an intent (say, an attentionalbid), the robot responds expressively (perking its ears, leaning forward, androunding its lips), and then the subject immediately responds in kind (perhapsby saying, “Oh!” or, “Ah!”). Several subjects appeared to empathize withthe robot after issuing a prohibition—often reporting feeling guilty or bad forscolding the robot and making it “sad.”The second is the ability of humans to direct Kismet’s attention using naturalcues [1]. This could play an important role in socially situated learning bygiving the caregiver a way of showing Kismet what is important for the task,and for establishing a shared reference. We have found that it is important forthe robot’s attention system to be tuned to the attention system of humans. It isimportant that both human and robot find the same types of stimuli salient insimilar conditions. Kismet has a set of perceptual biases based on the humanpre-attentive visual system. In this way, both robot and humans are more likelyto find the same sorts of things interesting or attention-grabbing. As a result,people can very naturally and quickly direct the robot’s attention by bringingthe target close and in front of the robot’s face, shaking the object of interest, ormoving it slowly across the centerline of the robot’s face. Each of these cuesincreases the saliency of a stimulus by making it appear larger in the visualfield, or by supplementing the color or skin-tone cue with motion. Kismet’sattention system coupled with gaze direction provides people with a powerfuland intuitive social cue for when they have succeeded in steering the robot’sinterest.3. SummaryIn this chapter, we have outlined a set of four core design issues that haveguided our work in building Kismet. When engaging another socially, humansbring a complex set of well-established social machinery to the interaction.Our aim is not a matter of re-engineering the human side of the equation to suit