Cultural Social Signal Interplay with an Expressive Robot

McKenna, Peter E.; Ghosh, Ayan; Aylett, Ruth; Broz, Frank; Rajendran, Gnanathusharan

doi:10.1145/3267851.3267905

Cited by 5 publications

(4 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, one barrier to accepting our task was that workers had to demonstrate fluency in written English; also, according to [14], on the days we collected labels, the majority of our workers were based in the United States. 3 Additionally, studies demonstrating a cultural influence on emotional experience and representation are not conclusive, as noted in [20].…”

Section: A Data Collectionmentioning

confidence: 99%

Predicting Human Interpretations of Affect and Valence in a Social Robot

McNeill¹,

Kennington

2019

Robotics: Science and Systems XV

View full text Add to dashboard Cite

In this paper we seek to understand how people interpret a social robot's performance of an emotion, what we term 'affective display,' and the positive or negative valence of that affect. To this end, we tasked annotators with observing the Anki Cozmo robot perform its over 900 pre-scripted behaviors and labeling those behaviors with 16 possible affective display labels (e.g., interest, boredom, disgust, etc.). In our first experiment, we trained a neural network to predict annotated labels given multimodal information about the robot's movement, face, and audio. The results suggest that pairing affects to predict the valence between them is more informative, which we confirmed in a second experiment. Both experiments show that certain modalities are more useful for predicting displays of affect and valence. For our final experiment, we generated novel robot behaviors and tasked human raters with assigning scores to valence pairs instead of applying labels, then compared our model's predictions of valence between the affective pairs and compared the results to the human ratings. We conclude that some modalities have information that can be contributory or inhibitive when considered in conjunction with other modalities, depending on the emotional valence pair being considered.

show abstract

Section: A Data Collectionmentioning

confidence: 99%

Predicting Human Interpretations of Affect and Valence in a Social Robot

McNeill¹,

Kennington

2019

Robotics: Science and Systems XV

View full text Add to dashboard Cite

show abstract

“…It has been discussed that there is no consensus in the literature on the definition of emotion [22], and this article also does not argue it. However, we need to mention that the human perception that is studied in this article can be affected by cultural and contextual factors [3,10,18,32], which will be discussed in detail in Section 8.3.…”

Section: Premisesmentioning

confidence: 99%

“…Cultural factors have also been discussed for the emotional expression of social robots [10,27,32]. Our design of thermal stimuli used conceptual metaphors related to emotional states.…”

Section: Contextual Factors In Emotional Expressionmentioning

confidence: 99%

Human Perception of Social Robot’s Emotional States via Facial and Thermal Expressions

Peña

Tanaka

2020

J. Hum.-Robot Interact.

View full text Add to dashboard Cite

Facial and thermal expressions can be used by humans to interpret emotions. While facial expressions can be a voluntary reaction, the change of temperature in the body is often not. Thus, a facial expression may not always be consistent with the emotional state that is expressed by the body temperature. This article aims to study the human perception of the emotional expression and the emotional state of a robot that simultaneously uses its face and body temperature. To this end, a robot, named TherMoody, which has the capability to change its body temperature from 10-55 • C, was used. Then, 25 combinations (5x5: one facial expression and one thermal expression for anger, joy, fear, sadness, and neutral state) were evaluated by 15 participants. Thermal expressions were designed based on the metaphors of emotions related to temperature. The results show people tend to base their judgment of the robot's emotional expression exclusively in its facial expression, regardless of the change of its body temperature. However, there are combinations where the thermal expression predominates over the facial expression when judging the robot's emotional state. Thus, these combinations may produce the perception that the robot's emotional expression is, in fact, genuine, simulated, masked, or neutralized. CCS Concepts: • Human-centered computing → User studies; Haptic devices; • Computer systems organization → Robotics;

show abstract

“…SARs have been deployed successfully in a wide range of healthcare domains, particularly in the care for the elderly [ 8 ]. More recently, they have been applied in pediatric settings to assist with autism diagnosis and therapy [ 9 , 10 ] and to help children with pain and distress during short- and long-term hospitalizations [ 11 , 12 , 13 ]. However, a recent scoping review of social robotics in children identified important gaps in this area: small sample sizes, lack of end-users in the design process, non-clinical trial designs, and lack of effectiveness outcomes [ 11 ].…”

Section: Introductionmentioning

confidence: 99%

Perspectives of Healthcare Providers to Inform the Design of an AI-Enhanced Social Robot in the Pediatric Emergency Department

Hudson,

Nishat,

Stinson

et al. 2023

Children

View full text Add to dashboard Cite

Children commonly experience pain and distress in healthcare settings related to medical procedures such as blood tests and intravenous insertions (IVIs). Inadequately addressed pain and distress can result in both short- and long-term negative consequences. The use of socially assistive robotics (SARs) to reduce procedure-related distress and pain in children’s healthcare settings has shown promise; however, the current options lack autonomous adaptability. This study presents a descriptive qualitative needs assessment of healthcare providers (HCPs) in two Canadian pediatric emergency departments (ED) to inform the design an artificial intelligence (AI)-enhanced social robot to be used as a distraction tool in the ED to facilitate IVIs. Semi-structured virtual individual and focus group interviews were conducted with eleven HCPs. Four main themes were identified: (1) common challenges during IVIs (i.e., child distress and resource limitations), (2) available tools for pain and distress management during IVIs (i.e., pharmacological and non-pharmacological), (3) response to SAR appearance and functionality (i.e., personalized emotional support, adaptive distraction based on child’s preferences, and positive reinforcement), and (4) anticipated benefits and challenges of SAR in the ED (i.e., ensuring developmentally appropriate interactions and space limitations). HCPs perceive AI-enhanced social robots as a promising tool for distraction during IVIs in the ED.

show abstract

Cultural Social Signal Interplay with an Expressive Robot

Cited by 5 publications

References 23 publications

Predicting Human Interpretations of Affect and Valence in a Social Robot

Predicting Human Interpretations of Affect and Valence in a Social Robot

Human Perception of Social Robot’s Emotional States via Facial and Thermal Expressions

Perspectives of Healthcare Providers to Inform the Design of an AI-Enhanced Social Robot in the Pediatric Emergency Department

Contact Info

Product

Resources

About