The Influence of Acute Stress on the Perception of Robot Emotional Body Language: Implications for Robot Design in Healthcare and Other High-Risk Domain

In coming years, emotionally expressive social robots will permeate many facets of our lives. Yet, although researchers have explored robot design parameters that may facilitate human-robot interaction, remarkably little attention has been paid to the human perceptual and other psychological factors that may impact human ability to engage with robots. In high-risk settings, such as healthcare---where the use of robots is expected to increase markedly---it is paramount to understand the influence of a patient's stress level, temperament, and attitudes towards robots as negative interactions could harm a patient's experience and hinder recovery. Using a novel between-subject paradigm, we investigated how the experimental induction of acute physiological and cognitive stress versus low stress influences perception of normed robot emotional body language as conveyed by a physically-present versus virtual reality generated robot.;Following high or low stress induction, participants were asked to rate the valence (negative/unhappy to positive/happy) and level of arousal (calm/relaxed to animated/excited) conveyed by poses in five emotional categories: negative valence-high arousal, negative valence-low arousal, neutral, positive valence-low arousal, positive valence-high arousal. Poses from the categories were randomly intermixed and each pose was presented two or three times. Ratings were then correlated with temperament (as assessed by the Adult Temperament Questionnaire), attitudes towards and experience with robots (a new questionnaire that included measures from the Godspeed Scales and Negative Attitudes about Robots Survey), and chronic stress.;The acute stress induction especially influenced the evaluation of high arousal poses -- both negative and positive -- with both valence and arousal rated lower under high than low stress. Repeated presentation impacted perception of low arousal (negative and positive) and neutral poses, with increases in perceived valence and arousal for later presentations. There were also effects of robot type specifically for positively-valenced emotions, such that these poses were rated as more positive for the physically-present than virtually-instantiated robot. Temperament was found to relate to emotional robot body language. Trait positive affect was associated with higher valence ratings for positive and neutral poses. Trait negative affect was correlated with higher arousal ratings for negative valence-low arousal poses. Subcategories within the robot attitudes questionnaire were correlated with emotional robot poses and temperament.;To our knowledge this dissertation is the first exploration of the effects of acute and chronic stress on human perception of robot emotional body language, with implications for robot design, both physical and virtual. Given the largely parallel findings that we observed for the poses presented by the physically-present versus virtually-instantiated robot, it is proposed that the use of virtual reality may provide a viable "sandbox" tool for more efficiently and thoroughly experimenting with possible robot designs, and variants in their emotional expressiveness. Broader psychological, physiological, and other factors that designers should consider as they create robots for high-risk applications are also discussed.