Bryant, D., Borenstein, J. & Howard, A. (Human Robot Interaction 2020)
The attribution of human-like characteristics onto humanoid robots has become a common practice in Human-Robot Interaction by designers and users alike. Robot gendering, the attribution of gender onto a robotic platform via voice, name, physique, or other features is a prevalent technique used to increase aspects of user acceptance of robots. One important factor relating to acceptance is user trust. As robots continue to integrate themselves into common societal roles, it will be critical to evaluate user trust in the robot's ability to perform its job. This paper examines the relationship among occupational gender-roles, user trust and gendered design features of humanoid robots. Results from the study indicate that there was no significant difference in the perception of trust in the robot's competency when considering the gender of the robot. This expands the findings found in prior efforts that suggest performance-based factors have larger influences on user trust than the robot's gender characteristics. In fact, our study suggests that perceived occupational competency is a better predictor for human trust than robot gender or participant gender. As such, gendering in robot design should be considered critically in the context of the application by designers. Such precautions would reduce the potential for robotic technologies to perpetuate societal gender stereotypes.
Read More Watch Presentation
Bryant, D., & Howard, A. (AI, Ethics, and Society 2019)
In recent news, organizations have been considering the use of facial and emotion recognition for applications involving youth such as tackling surveillance and security in schools. However, the majority of efforts on facial emotion recognition research have focused on adults. Children, particularly in their early years, have been shown to express emotions quite differently than adults. Thus, before such algorithms are deployed in environments that impact the wellbeing and circumstance of youth, a careful examination should be made on their accuracy with respect to appropriateness for this target demographic. In this work, we utilize several datasets that contain facial expressions of children linked to their emotional state to evaluate eight different commercial emotion classification systems. We compare the ground truth labels provided by the respective datasets to the labels given with the highest confidence by the classification systems and assess the results in terms of matching score (TPR), positive predictive value, and failure to compute rate. Overall results show that the emotion recognition systems displayed subpar performance on the datasets of children's expressions compared to prior work with adult datasets and initial human ratings. We then identify limitations associated with automated recognition of emotions in children and provide suggestions on directions with enhancing recognition accuracy through data diversification, dataset accountability, and algorithmic regulation.
Bryant, D., Xu, J. & Howard, A. (Human Robot Interaction 2019)
Xu, J., Bryant, D. & Howard, A. (ISMR 2018)
Cerebral Palsy (CP) is the most common motor disability in childhood, affecting nearly 1 in 323 children in the United States. Repetitive therapeutic exercises play a key role in upper-body rehabilitation interventions during which a therapist provides corrective feedback to a patient based on the patient's motor skill performance. Recently, an innovative system combining a serious game with an interactive robot has emerged as a powerful tool in enhancing upper-body rehabilitation and intervention outcomes. Although several studies have shown that integrating robots into physical therapy sessions can encourage engagement and improve the efficacy of the rehabilitation protocol, most studies have not directly compared outcomes when using a robot therapist versus a human therapist. The present study aims to evaluate whether a therapy intervention coupled with a robot agent is as effective as an intervention coupled with a human agent. We evaluate this effectiveness in terms of human motor performance and intrinsic motivation. A between-subject experiment was performed with twenty participants. All participants were randomly assigned to one of the following groups: 1) participants received corrective feedback from a robot agent or 2) participants received corrective feedback from a human agent. Results showed that participants in the robot therapy group improved faster than participants in the human therapy group, but the effect from the corrective feedback lasted longer in the human therapy group than the robot therapy group. The Intrinsic Motivation Inventory (IMI) survey indicated comparable results between the two groups. The experimental results provide further evidence towards supporting the efficacy of a robotic therapy coach for children with disabilities, and motivate future studies in this domain.
Ogunyale, T.,Bryant, D., & Howard, A. (Fairness, Accountability, and Transparency in Machine Learning 2018)
Robots capable of participating in complex social interactions have shown great potential in a variety of applications. As these robots grow more popular, it is essential to continuously evaluate the dynamics of the human-robot relationship. One factor shown to have potential impacts on this critical relationship is the human projection of stereotypes onto social robots, a practice that is implicitly known to effect both developers and users of this technology. As such, in this research, we wished to investigate the difference in participants' perceptions of the robot interaction if we removed stereotype priming. This has not yet been a common practice in similar studies. Given the stereotypes of emotions among ethnic groups, especially in the U.S., this study specifically sought to investigate the impact that robot "skin color" could potentially have on the human perception of a robot's emotional expressive behavior. A between-subject experiment with 198 individuals was conducted. The results showed no significant differences in the overall emotion classification or intensity ratings for the different robot skin colors. These results lend credence to our hypothesis that when individuals are not primed with information related to human stereotypes, robots are evaluated based on functional attributes versus stereotypical attributes. This provides some confidence that robots, if designed correctly, can potentially be used as a tool to override stereotype-based biases associated with human behavior.
Xu, J., Bryant, D. & Howard, A. (RO-MAN 2018)
With the recent advances in computing, artificial intelligence (AI) is quickly becoming a key component in the future of advanced applications. In one application in particular, AI has played a major role - that of revolutionizing traditional healthcare assistance. Using embodied interactive agents, or interactive robots, in healthcare scenarios has emerged as an innovative way to interact with patients. As an essential factor for interpersonal interaction, trust plays a crucial role in establishing and maintaining a patient-agent relationship. In this paper, we discuss a study related to healthcare in which we examine aspects of trust between humans and interactive robots during a therapy intervention in which the agent provides corrective feedback. A total of twenty participants were randomly assigned to receive corrective feedback from either a robotic agent or a human agent. Survey results indicate trust in a therapy intervention coupled with a robotic agent is comparable to that of trust in an intervention coupled with a human agent. Results also show a trend that the agent condition has a medium-sized effect on trust. In addition, we found that participants in the robot therapist condition are 3.5 times likely to have trust involved in their decision than the participants in the human therapist condition. These results indicate that the deployment of interactive robot agents in healthcare scenarios has the potential to maintain quality of health for future generations.
Bryant, D., Liles, K., & Beer, J. (2017)
In this paper we discuss details on the preliminary development of an interactive, educational game that will be used to engage rural, minority, middle school students in computer science by incorporating hip-hop dance with a simulated robot. Although this work is in progress, our aim is to develop a culturally tailored educational experience, so that students will have increased perceptions and openness to computer science after interacting with the robot hip-hop programming game. In this short report, we discuss details of our game design. We also describe the methodology, in-progress usability assessments on lesson content, as well as the robot dance moves to include in the game development.
Liles, K., Bryant, D., & Beer, J. (2017)
In this paper, we describe the social perceptions and emotions of 5th grade students (N=22) studying multiplication with a social robot by measuring students' multiplication knowledge, their perceptions of the technologies, emotions after interaction, willingness to continue, and preference for technology use. The goal of this study was to investigate specific social traits that lead to increasing students' motivation to learn math with a robot and promoting robot acceptance. Our results show that students' positive perceptions and attitudes toward a robot tutor leads to student motivation, as well as intentional acceptance of the technology.
Bryant, D., Boyd, J., Harris, J., Smith, M., Garcia-Vergara, S., Chen, Y., & Howard, A. (2017)
Observations of spontaneous kicking patterns in infants have presented valuable insights into their development. At times, these kicking patterns can detect potential developmental delays in at-risk infants to help support diagnosis and intervention. However, the prevalence of developmental disabilities has increased and a protocol for early diagnosis is still not widely available outside of direct clinical observations. This paper presents a mobile system that aims at providing a prompt method for detecting atypical kicking patterns in at-risk infants. The Infant Smart-Mobile uses a robotic mobile coupled with wearable sensors for monitoring infant leg movements. We test the feasibility of the Infant Smart-Mobile by evaluating it with respect to data collected from a robotic humanoid designed to simulate kicking in a manner similar to that of infants with typical or atypical motor behavior.
Bryant, D., Boren, M., Liles, K., & Beer, J. (2015)
The goal of this study was to determine the therapeutic benefit of incorporating assistive robotics technology (NAO) into the music therapy sessions of children diagnosed with Autism Spectrum Disorders (ASD). Participants were video recorded and observed during regularly scheduled music therapy sessions. The child was led by the robot to follow along to a dance that gave verbal instructions. These sessions continued over the duration of several weeks. Parents of the child and the therapist completed complete pre, mid, and post interviews, as well as weekly assessments. I assisted as a technical assistant for this project.