"Robots for good": Ten defining questions.

Ten questions to guide reflection and assessment of the "good" in robotics projects are suggested.

Behavioural Models of Risk-Taking in Human-Robot Tactile Interactions.

Touch can have a strong effect on interactions between people, and as such, it is expected to be important to the interactions people have with robots. In an earlier work, we showed that the intensity of tactile interaction with a robot can change how much people are willing to take risks. This study further develops our understanding of the relationship between human risk-taking behaviour, the physiological responses by the user, and the intensity of the tactile interaction with a social robot. We used data collected with physiological sensors during the playing of a risk-taking game (the Balloon Analogue Risk Task, or BART). The results of a mixed-effects model were used as a baseline to predict risk-taking propensity from physiological measures, and these results were further improved through the use of two machine learning techniques-support vector regression (SVR) and multi-input convolutional multihead attention (MCMA)-to achieve low-latency risk-taking behaviour prediction during human-robot tactile interaction. The performance of the models was evaluated based on mean absolute error (MAE), root mean squared error (RMSE), and R squared score (R2), which obtained the optimal result with MCMA yielding an MAE of 3.17, an RMSE of 4.38, and an R2 of 0.93 compared with the baseline of 10.97 MAE, 14.73 RMSE, and 0.30 R2. The results of this study offer new insights into the interplay between physiological data and the intensity of risk-taking behaviour in predicting human risk-taking behaviour during human-robot tactile interactions. This work illustrates that physiological activation and the intensity of tactile interaction play a prominent role in risk processing during human-robot tactile interaction and demonstrates that it is feasible to use human physiological data and behavioural data to predict risk-taking behaviour in human-robot tactile interaction.

Do different robot appearances change emotion recognition in children with ASD?

Introduction: Socially Assistive Robotics has emerged as a potential tool for rehabilitating cognitive and developmental disorders in children with autism. Social robots found in the literature are often able to teach critical social skills, such as emotion recognition and physical interaction. Even though there are promising results in clinical studies, there is a lack of guidelines on selecting the appropriate robot and how to design and implement the child-robot interaction. Methods: This work aims to evaluate the impacts of a social robot designed with three different appearances according to the results of a participatory design (PD) process with the community. A validation study in the emotion recognition task was carried out with 21 children with autism. Results: Spectrum disorder results showed that robot-like appearances reached a higher percentage of children's attention and that participants performed better when recognizing simple emotions, such as happiness and sadness. Discussion: This study offers empirical support for continuing research on using SAR to promote social interaction with children with ASD. Further long-term research will help to identify the differences between high and low-functioning children.

Personalised socially assistive robot for cardiac rehabilitation: Critical reflections on long-term interactions in the real world.

Lack of motivation and low adherence rates are critical concerns of long-term rehabilitation programmes, such as cardiac rehabilitation. Socially assistive robots are known to be effective in improving motivation in therapy. However, over longer durations, generic and repetitive behaviours by the robot often result in a decrease in motivation and engagement, which can be overcome by personalising the interaction, such as recognising users, addressing them with their name, and providing feedback on their progress and adherence. We carried out a real-world clinical study, lasting 2.5 years with 43 patients to evaluate the effects of using a robot and personalisation in cardiac rehabilitation. Due to dropouts and other factors, 26 patients completed the programme. The results derived from these patients suggest that robots facilitate motivation and adherence, enable prompt detection of critical conditions by clinicians, and improve the cardiovascular functioning of the patients. Personalisation is further beneficial when providing high-intensity training, eliciting and maintaining engagement (as measured through gaze and social interactions) and motivation throughout the programme. However, relying on full autonomy for personalisation in a real-world environment resulted in sensor and user recognition failures, which caused negative user perceptions and lowered the perceived utility of the robot. Nonetheless, personalisation was positively perceived, suggesting that potential drawbacks need to be weighed against various benefits of the personalised interaction.

Coffee With a Hint of Data: Towards Using Data-Driven Approaches in Personalised Long-Term Interactions.

While earlier research in human-robot interaction pre-dominantly uses rule-based architectures for natural language interaction, these approaches are not flexible enough for long-term interactions in the real world due to the large variation in user utterances. In contrast, data-driven approaches map the user input to the agent output directly, hence, provide more flexibility with these variations without requiring any set of rules. However, data-driven approaches are generally applied to single dialogue exchanges with a user and do not build up a memory over long-term conversation with different users, whereas long-term interactions require remembering users and their preferences incrementally and continuously and recalling previous interactions with users to adapt and personalise the interactions, known as the lifelong learning problem. In addition, it is desirable to learn user preferences from a few samples of interactions (i.e., few-shot learning). These are known to be challenging problems in machine learning, while they are trivial for rule-based approaches, creating a trade-off between flexibility and robustness. Correspondingly, in this work, we present the text-based Barista Datasets generated to evaluate the potential of data-driven approaches in generic and personalised long-term human-robot interactions with simulated real-world problems, such as recognition errors, incorrect recalls and changes to the user preferences. Based on these datasets, we explore the performance and the underlying inaccuracies of the state-of-the-art data-driven dialogue models that are strong baselines in other domains of personalisation in single interactions, namely Supervised Embeddings, Sequence-to-Sequence, End-to-End Memory Network, Key-Value Memory Network, and Generative Profile Memory Network. The experiments show that while data-driven approaches are suitable for generic task-oriented dialogue and real-time interactions, no model performs sufficiently well to be deployed in personalised long-term interactions in the real world, because of their inability to learn and use new identities, and their poor performance in recalling user-related data.

A Socially Assistive Robot for Long-Term Cardiac Rehabilitation in the Real World.

What are the benefits of using a socially assistive robot for long-term cardiac rehabilitation? To answer this question we designed and conducted a real-world long-term study, in collaboration with medical specialists, at the Fundación Cardioinfantil-Instituto de Cardiología clinic (Bogotá, Colombia) lasting 2.5 years. The study took place within the context of the outpatient phase of patients' cardiac rehabilitation programme and aimed to compare the patients' progress and adherence in the conventional cardiac rehabilitation programme (control condition) against rehabilitation supported by a fully autonomous socially assistive robot which continuously monitored the patients during exercise to provide immediate feedback and motivation based on sensory measures (robot condition). The explicit aim of the social robot is to improve patient motivation and increase adherence to the programme to ensure a complete recovery. We recruited 15 patients per condition. The cardiac rehabilitation programme was designed to last 36 sessions (18 weeks) per patient. The findings suggest that robot increases adherence (by 13.3%) and leads to faster completion of the programme. In addition, the patients assisted by the robot had more rapid improvement in their recovery heart rate, better physical activity performance and a higher improvement in cardiovascular functioning, which indicate a successful cardiac rehabilitation programme performance. Moreover, the medical staff and the patients acknowledged that the robot improved the patient motivation and adherence to the programme, supporting its potential in addressing the major challenges in rehabilitation programmes.

The Robot Made Me Do It: Human-Robot Interaction and Risk-Taking Behavior.

Empirical evidence has shown that peer pressure can impact human risk-taking behavior. With robots becoming ever more present in a range of human settings, it is crucial to examine whether robots can have a similar impact. Using the balloon analogue risk task (BART), participants' risk-taking behavior was measured when alone, in the presence of a silent robot, or in the presence of a robot that actively encouraged risk-taking behavior. In the BART, shown to be a proxy for real risk-taking behavior, participants must weigh risk against potential payout. Our results reveal that participants who were encouraged by the robot did take more risks, while the mere presence of the robot in the robot control condition did not entice participants to show more risk-taking behavior. Our results point to both possible benefits and perils that robots might pose to human decision-making. Although increasing risk-taking behavior in some cases has obvious advantages, it could also have detrimental consequences that are only now starting to emerge.

The DREAM Dataset: Supporting a data-driven study of autism spectrum disorder and robot enhanced therapy.

We present a dataset of behavioral data recorded from 61 children diagnosed with Autism Spectrum Disorder (ASD). The data was collected during a large-scale evaluation of Robot Enhanced Therapy (RET). The dataset covers over 3000 therapy sessions and more than 300 hours of therapy. Half of the children interacted with the social robot NAO supervised by a therapist. The other half, constituting a control group, interacted directly with a therapist. Both groups followed the Applied Behavior Analysis (ABA) protocol. Each session was recorded with three RGB cameras and two RGBD (Kinect) cameras, providing detailed information of children's behavior during therapy. This public release of the dataset comprises body motion, head position and orientation, and eye gaze variables, all specified as 3D data in a joint frame of reference. In addition, metadata including participant age, gender, and autism diagnosis (ADOS) variables are included. We release this data with the hope of supporting further data-driven studies towards improved therapy methods as well as a better understanding of ASD in general.

Teaching robots social autonomy from in situ human guidance.

Striking the right balance between robot autonomy and human control is a core challenge in social robotics, in both technical and ethical terms. On the one hand, extended robot autonomy offers the potential for increased human productivity and for the off-loading of physical and cognitive tasks. On the other hand, making the most of human technical and social expertise, as well as maintaining accountability, is highly desirable. This is particularly relevant in domains such as medical therapy and education, where social robots hold substantial promise, but where there is a high cost to poorly performing autonomous systems, compounded by ethical concerns. We present a field study in which we evaluate SPARC (supervised progressively autonomous robot competencies), an innovative approach addressing this challenge whereby a robot progressively learns appropriate autonomous behavior from in situ human demonstrations and guidance. Using online machine learning techniques, we demonstrate that the robot could effectively acquire legible and congruent social policies in a high-dimensional child-tutoring situation needing only a limited number of demonstrations while preserving human supervision whenever desirable. By exploiting human expertise, our technique enables rapid learning of autonomous social and domain-specific policies in complex and nondeterministic environments. Last, we underline the generic properties of SPARC and discuss how this paradigm is relevant to a broad range of difficult human-robot interaction scenarios.

What Can You See? Identifying Cues on Internal States From the Movements of Natural Social Interactions.

In recent years, the field of Human-Robot Interaction (HRI) has seen an increasing demand for technologies that can recognize and adapt to human behaviors and internal states (e.g., emotions and intentions). Psychological research suggests that human movements are important for inferring internal states. There is, however, a need to better understand what kind of information can be extracted from movement data, particularly in unconstrained, natural interactions. The present study examines which internal states and social constructs humans identify from movement in naturalistic social interactions. Participants either viewed clips of the full scene or processed versions of it displaying 2D positional data. Then, they were asked to fill out questionnaires assessing their social perception of the viewed material. We analyzed whether the full scene clips were more informative than the 2D positional data clips. First, we calculated the inter-rater agreement between participants in both conditions. Then, we employed machine learning classifiers to predict the internal states of the individuals in the videos based on the ratings obtained. Although we found a higher inter-rater agreement for full scenes compared to positional data, the level of agreement in the latter case was still above chance, thus demonstrating that the internal states and social constructs under study were identifiable in both conditions. A factor analysis run on participants' responses showed that participants identified the constructs interaction imbalance, interaction valence and engagement regardless of video condition. The machine learning classifiers achieved a similar performance in both conditions, again supporting the idea that movement alone carries relevant information. Overall, our results suggest it is reasonable to expect a machine learning algorithm, and consequently a robot, to successfully decode and classify a range of internal states and social constructs using low-dimensional data (such as the movements and poses of observed individuals) as input.

Generating Spatial Referring Expressions in a Social Robot: Dynamic vs. Non-ambiguous.

Generating spatial referring expressions is key to allowing robots to communicate with people in an environment. The focus of most algorithms for generation is to create a non-ambiguous description, and how best to deal with the combination explosion this can create in a complex environment. However, this is not how people naturally communicate. Humans tend to give an under-specified description and then rely on a strategy of repair to reduce the number of possible locations or objects until the correct one is identified, what we refer to here as a dynamic description. We present here a method for generating these dynamic descriptions for Human Robot Interaction, using machine learning to generate repair statements. We also present a study with 61 participants in a task on object placement. This task was presented in a 2D environment that favored a non-ambiguous description. In this study we demonstrate that our dynamic method of communication can be more efficient for people to identify a location compared to one that is non-ambiguous.

The PInSoRo dataset: Supporting the data-driven study of child-child and child-robot social dynamics.

The study of the fine-grained social dynamics between children is a methodological challenge, yet a good understanding of how social interaction between children unfolds is important not only to Developmental and Social Psychology, but recently has become relevant to the neighbouring field of Human-Robot Interaction (HRI). Indeed, child-robot interactions are increasingly being explored in domains which require longer-term interactions, such as healthcare and education. For a robot to behave in an appropriate manner over longer time scales, its behaviours have to be contingent and meaningful to the unfolding relationship. Recognising, interpreting and generating sustained and engaging social behaviours is as such an important-and essentially, open-research question. We believe that the recent progress of machine learning opens new opportunities in terms of both analysis and synthesis of complex social dynamics. To support these approaches, we introduce in this article a novel, open dataset of child social interactions, designed with data-driven research methodologies in mind. Our data acquisition methodology relies on an engaging, methodologically sound, but purposefully underspecified free-play interaction. By doing so, we capture a rich set of behavioural patterns occurring in natural social interactions between children. The resulting dataset, called the PInSoRo dataset, comprises 45+ hours of hand-coded recordings of social interactions between 45 child-child pairs and 30 child-robot pairs. In addition to annotations of social constructs, the dataset includes fully calibrated video recordings, 3D recordings of the faces, skeletal informations, full audio recordings, as well as game interactions.

Experiences of a Motivational Interview Delivered by a Robot: Qualitative Study.

BACKGROUND: Motivational interviewing is an effective intervention for supporting behavior change but traditionally depends on face-to-face dialogue with a human counselor. This study addressed a key challenge for the goal of developing social robotic motivational interviewers: creating an interview protocol, within the constraints of current artificial intelligence, which participants will find engaging and helpful. OBJECTIVE: The aim of this study was to explore participants' qualitative experiences of a motivational interview delivered by a social robot, including their evaluation of usability of the robot during the interaction and its impact on their motivation. METHODS: NAO robots are humanoid, child-sized social robots. We programmed a NAO robot with Choregraphe software to deliver a scripted motivational interview focused on increasing physical activity. The interview was designed to be comprehensible even without an empathetic response from the robot. Robot breathing and face-tracking functions were used to give an impression of attentiveness. A total of 20 participants took part in the robot-delivered motivational interview and evaluated it after 1 week by responding to a series of written open-ended questions. Each participant was left alone to speak aloud with the robot, advancing through a series of questions by tapping the robot's head sensor. Evaluations were content-analyzed utilizing Boyatzis' steps: (1) sampling and design, (2) developing themes and codes, and (3) validating and applying the codes. RESULTS: Themes focused on interaction with the robot, motivation, change in physical activity, and overall evaluation of the intervention. Participants found the instructions clear and the navigation easy to use. Most enjoyed the interaction but also found it was restricted by the lack of individualized response from the robot. Many positively appraised the nonjudgmental aspect of the interview and how it gave space to articulate their motivation for change. Some participants felt that the intervention increased their physical activity levels. CONCLUSIONS: Social robots can achieve a fundamental objective of motivational interviewing, encouraging participants to articulate their goals and dilemmas aloud. Because they are perceived as nonjudgmental, robots may have advantages over more humanoid avatars for delivering virtual support for behavioral change.

Social robots for education: A review.

Social robots can be used in education as tutors or peer learners. They have been shown to be effective at increasing cognitive and affective outcomes and have achieved outcomes similar to those of human tutoring on restricted tasks. This is largely because of their physical presence, which traditional learning technologies lack. We review the potential of social robots in education, discuss the technical challenges, and consider how the robot's appearance and behavior affect learning outcomes.

Children conform, adults resist: A robot group induced peer pressure on normative social conformity.

People are known to change their behavior and decisions to conform to others, even for obviously incorrect facts. Because of recent developments in artificial intelligence and robotics, robots are increasingly found in human environments, and there, they form a novel social presence. It is as yet unclear whether and to what extent these social robots are able to exert pressure similar to human peers. This study used the Asch paradigm, which shows how participants conform to others while performing a visual judgment task. We first replicated the finding that adults are influenced by their peers but showed that they resist social pressure from a group of small humanoid robots. Next, we repeated the study with 7- to 9-year-old children and showed that children conform to the robots. This raises opportunities as well as concerns for the use of social robots with young and vulnerable cross-sections of society; although conforming can be beneficial, the potential for misuse and the potential impact of erroneous performance cannot be ignored.

Guidelines for Designing Social Robots as Second Language Tutors.

In recent years, it has been suggested that social robots have potential as tutors and educators for both children and adults. While robots have been shown to be effective in teaching knowledge and skill-based topics, we wish to explore how social robots can be used to tutor a second language to young children. As language learning relies on situated, grounded and social learning, in which interaction and repeated practice are central, social robots hold promise as educational tools for supporting second language learning. This paper surveys the developmental psychology of second language learning and suggests an agenda to study how core concepts of second language learning can be taught by a social robot. It suggests guidelines for designing robot tutors based on observations of second language learning in human-human scenarios, various technical aspects and early studies regarding the effectiveness of social robots as second language tutors.

Human-robot sensor interface for cardiac rehabilitation.

Cardiovascular disease is the leading cause of death in the world. A program of cardiac rehabilitation (CR) is related to physical activities or exercises to regain the optimal quality of life. CR relies on the necessity to evaluate, control and supervise a patient's status and progress. This work has two objectives: on the one hand, provide a tool for clinicians to assess the patient's status during CR. On the other hand, there is evidence that robots can motivate patients during therapeutic procedures. Our sensor interface explores the possibility to integrate a robotic agent into cardiac therapy. This work presents an exploratory experiment for on-line assessment of typical CR routines.

Robot education peers in a situated primary school study: Personalisation promotes child learning.

The benefit of social robots to support child learning in an educational context over an extended period of time is evaluated. Specifically, the effect of personalisation and adaptation of robot social behaviour is assessed. Two autonomous robots were embedded within two matched classrooms of a primary school for a continuous two week period without experimenter supervision to act as learning companions for the children for familiar and novel subjects. Results suggest that while children in both personalised and non-personalised conditions learned, there was increased child learning of a novel subject exhibited when interacting with a robot that personalised its behaviours, with indications that this benefit extended to other class-based performance. Additional evidence was obtained suggesting that there is increased acceptance of the personalised robot peer over a non-personalised version. These results provide the first evidence in support of peer-robot behavioural personalisation having a positive influence on learning when embedded in a learning environment for an extended period of time.

Why Robots Should Be Social: Enhancing Machine Learning through Social Human-Robot Interaction.

Social learning is a powerful method for cultural propagation of knowledge and skills relying on a complex interplay of learning strategies, social ecology and the human propensity for both learning and tutoring. Social learning has the potential to be an equally potent learning strategy for artificial systems and robots in specific. However, given the complexity and unstructured nature of social learning, implementing social machine learning proves to be a challenging problem. We study one particular aspect of social machine learning: that of offering social cues during the learning interaction. Specifically, we study whether people are sensitive to social cues offered by a learning robot, in a similar way to children's social bids for tutoring. We use a child-like social robot and a task in which the robot has to learn the meaning of words. For this a simple turn-based interaction is used, based on language games. Two conditions are tested: one in which the robot uses social means to invite a human teacher to provide information based on what the robot requires to fill gaps in its knowledge (i.e. expression of a learning preference); the other in which the robot does not provide social cues to communicate a learning preference. We observe that conveying a learning preference through the use of social cues results in better and faster learning by the robot. People also seem to form a "mental model" of the robot, tailoring the tutoring to the robot's performance as opposed to using simply random teaching. In addition, the social learning shows a clear gender effect with female participants being responsive to the robot's bids, while male teachers appear to be less receptive. This work shows how additional social cues in social machine learning can result in people offering better quality learning input to artificial systems, resulting in improved learning performance.