As autonomous social robots become more prevalent in home environments, they must decide where to position themselves within many different types of rooms or spaces, balancing accessibility with staying out of the way. This paper presents a machine learning approach to modeling user preferences for robot parking spots in the home using standard 2D occupancy maps. Our method learns spatial patterns from the information available in the occupancy maps and user-annotated floorplans without requiring specialized inputs. We evaluate the approach using floorplan data from 84 users who provided parking spot preferences after living with and evaluating a social robot in their homes for at least two weeks. Our method significantly outperforms a state-of-the-art baseline focused exclusively on avoiding walking paths. We demonstrate how the approach extends to additional map features and share insights about the types of preference patterns learned by the model. This contribution provides a framework that can incorporate new environmental inputs as robot perception capabilities evolve.

For social robots to successfully integrate into daily life in home environments, they will need reliable models of the way people perceive and use space in the home. This paper explores the problem of obtaining annotated training data at scale for subjective judgments about spatial locations. Focusing on the use case of identifying good and bad parking spots for a social robot operating in a home environment, two experiments are presented. The first study shows that the presentation of context-rich 3D images to human annotators yields notably different outcomes from those obtained when using 2D robot navigation maps. We attribute the source of these differences to a set of features visible only in the 3D views and introduce a technique for labeling these features on the 2D maps. The second study reveals that using labeled 2D maps produces annotation data very similar to that obtained using 3D images. Since a labeled 2D map can be generated at a fraction of the cost of a full set of 3D views, we recommend this method as a scalable approach to collecting subjective spatial data annotations in everyday environments.

This was the first of a series of experiments to investigate whether adults respond to a robot’s feedback as effectively as to a human’s during a virtual-reality game. Twenty adults volunteered to pop bubbles in 7 virtual-reality games, including 2 in baseline, 3 in acquisition, and 2 in extinction. Participants were randomized to receive feedback from a robot or a human during acquisition. The 80% of the average movement time at baseline was used as the target time to determine the feedback content. Feedback was the same except for the agent (robot or human). Results indicated adults responding to a robot’s feedback to shape their reaching during acquisition and extinction had faster reaching than baseline; however, their patterns were jerkier, less straight, and slower than participants’ receiving a human’s feedback. This study shows the potential to use robots as the feedback provider, though participants performed slightly better with human feedback.

Humans can perceive multiple expressions, each one with varying intensity, in the picture of a face. We propose a methodology for collecting and modeling multidimensional modulated expression annotations from human annotators. Our data reveals that the perception of some expressions can be quite different across observers; thus, our model is designed to represent ambiguity alongside intensity. An empirical exploration of how many dimensions are necessary to capture the perception of facial expression suggests six principal expression dimensions are sufficient. Using our method, we collected multidimensional modulated expression annotations for 1,000 images culled from the popular ExpW in-the-wild dataset. As a proof of principle of our improved measurement technique, we used these annotations to benchmark four public domain algorithms for automated facial expression prediction.

The growing potential for facial emotion recognition (FER) technology has encouraged expedited development at the cost of rigorous validation. Many of its use-cases may also impact the diverse global community as FER becomes embedded into domains ranging from education to security to healthcare. Yet, prior work has highlighted that FER can exhibit both gender and racial biases like other facial analysis techniques. As a result, bias-mitigation research efforts have mainly focused on tackling gender and racial disparities, while other demographic related biases, such as age, have seen less progress. This work seeks to examine the performance of state of the art commercial FER technology on expressive images of men and women from three distinct age groups. We utilize four different commercial FER systems in a black box methodology to evaluate how six emotions - anger, disgust, fear, happiness, neutrality, and sadness - are correctly detected by age group. We further investigate how algorithmic changes over the last year have affected system performance. Our results found that all four commercial FER systems most accurately perceived emotion in images of young adults and least accurately in images of older adults. This trend was observed for analyses conducted in 2019 and 2020. However, little to no gender disparities were observed in either year. While older adults may not have been the initial target consumer of FER technology, statistics show the demographic is quickly growing more keen to applications that use such systems. Our results demonstrate the importance of considering various demographic subgroups during FER system validation and the need for inclusive, intersectional algorithmic developmental practices.

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.

Social robots are robots designed to interact and communicate directly with humans, following traditional social norms. However, many of these current robots operate in discrete settings with predefined expectations for specific social interactions. In order for these machines to operate in the real world, they must be capable of understanding the multiple factors that contribute to human-human interaction. One such factor is emotional intelligence. Emotional intelligence allows one to consider the emotional state of another in order to motivate, plan, and achieve one's desires. One common method of analyzing the emotional state of an individual involves analyzing the emotion displayed on their face. Several artificial intelligence (AI) systems have been developed to conduct this task. These systems are often classifiers trained using a variety of machine learning techniques which require large amounts of training data. As such, they are susceptible to biases that may appear during performance analyses due to disproportions existing in training datasets. Children, in particular, are often less represented in the primary datasets of annotated faces used for training such emotion classification systems. This work seeks to first analyze the extent of these performance differences in commercial systems, then to present new computational techniques that work to mitigate some of the effects of minimal representation in datasets, and to finally present a social robot which utilizes an improved emotional AI to interact with children in various scenarios where emotional intelligence is key to successful human-robot interaction.

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.

Several HRI studies have investigated the use of interactive social robots to enhance a variety of activities designed for children in recent years. Notably, these robots have shown the ability to facilitate greater engagement with rehabilitative therapy exercises. Yet, very few studies have directly compared the performance of a robotic therapist with that of a human therapist during therapy sessions. This type of analysis is even less common for studies involving children. This work presents the experimental results of a between subjects study conducted with 10 children who interacted with either a robot or human therapist while playing a virtual reality rehabilitation game. The results are analyzed in terms of user intrinsic motivation and compared to previous work with adult participants. Preliminary results show a trend that children enjoyed working with the robot therapist more than the human therapist while playing the game. This finding is consistent with related work within the domain of child-robot interaction and supports the continued investigation of the potential uses of social robots in therapeutic rehabilitation protocols for children.

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.