scispace - formally typeset
Search or ask a question

Showing papers presented at "International Conference on Social Robotics in 2015"


Book ChapterDOI
26 Oct 2015
TL;DR: The effects of a robot apologizing for its mistake, promising to do better in the future, and providing additional reasons to trust it in a simulated office evacuation conducted in a virtual environment are evaluated.
Abstract: Even the best robots will eventually make a mistake while performing their tasks. In our past experiments, we have found that even one mistake can cause a large loss in trust by human users. In this paper, we evaluate the effects of a robot apologizing for its mistake, promising to do better in the future, and providing additional reasons to trust it in a simulated office evacuation conducted in a virtual environment. In tests with 319 participants, we find that each of these techniques can be successful at repairing trust if they are used when the robot asks the human to trust it again, but are not successful when used immediately after the mistake. The implications of these results are discussed.

87 citations


Book ChapterDOI
26 Oct 2015
TL;DR: In this article, the authors present a study on the effect of two different social characters of a robot (peer vs. tutor) on children's task engagement and show that in the peer condition, children paid attention to the robot and the task for a longer period of time and solved the puzzles quicker and better than in the tutor character condition.
Abstract: An increasing number of applications for social robots focuses on learning and playing with children. One of the unanswered questions is what kind of social character a robot should have in order to positively engage children in a task. In this paper, we present a study on the effect of two different social characters of a robot (peer vs. tutor) on children’s task engagement. We derived peer and tutor robot behaviors from the literature and we evaluated the two robot characters in a WoZ study where 10 pairs of children aged 6 to 9 played Tangram puzzles with a Nao robot. Our results show that in the peer character condition, children paid attention to the robot and the task for a longer period of time and solved the puzzles quicker and better than in the tutor character condition.

54 citations


Book ChapterDOI
26 Oct 2015
TL;DR: Towards Safe and Trustworthy Social Robots: Ethical Challenges and Practical Issues.
Abstract: As robots are increasingly developed to assist humans socially with everyday tasks in home and healthcare settings, questions regarding the robot’s safety and trustworthiness need to be addressed. The present work investigates the practical and ethical challenges in designing and evaluating social robots that aim to be perceived as safe and can win their human users’ trust. With particular focus on collaborative scenarios in which humans are required to accept information provided by the robot and follow its suggestions, trust plays a crucial role and is strongly linked to persuasiveness. Accordingly, human-robot trust can directly affect people’s willingness to cooperate with the robot, while under- or overreliance may have severe or even dangerous consequences. Problematically, investigating trust and human perceptions of safety in HRI experiments proves challenging in light of numerous ethical concerns and risks, which this paper aims to highlight and discuss based on experiences from HRI practice.

51 citations


Book ChapterDOI
26 Oct 2015
TL;DR: Given a dressing task, the approach finds a solution involving manipulator motions and also user repositioning requests that allows the robot and user to take turns moving in the same space and is cognizant of the user’s limitations.
Abstract: In this paper, we present an approach for a robot to provide personalized assistance for dressing a user. In particular, given a dressing task, our approach finds a solution involving manipulator motions and also user repositioning requests. Specifically, the solution allows the robot and user to take turns moving in the same space and is cognizant of the user’s limitations. To accomplish this, a vision module monitors the human’s motion, determines if he is following the repositioning requests, and infers mobility limitations when he cannot. The learned constraints are used during future dressing episodes to personalize the repositioning requests. Our contributions include a turn-taking approach to human-robot coordination for the dressing problem and a vision module capable of learning user limitations. After presenting the technical details of our approach, we provide an evaluation with a Baxter manipulator.

50 citations


Book ChapterDOI
26 Oct 2015
TL;DR: The results showed the subjects’ large learning gains which were fairly persistent according to their performances on the delayed post-test, and the difference observed between the learning gains of the high-functioning and low- functioning participants is discussed.
Abstract: The present case study investigated the effect of applying a humanoid robot as a teacher assistant to teach a foreign language (English in this case) to Iranian children with autism. To do this, there were 4 male autistic children, 7–9 years old, 3 with high-functioning autism and one with low-functioning autism. The humanoid robot NAO was used as the main instrument of this study. There were 12 sessions including 10 teaching sessions. This study used a pre-test, mid-test, immediate post-test, and delayed post-test design to measure the learning gains of the autistic children participating in the robot-assisted language learning (RALL) program. The results showed the subjects’ large learning gains which were fairly persistent according to their performances on the delayed post-test. The difference observed between the learning gains of the high-functioning and low-functioning participants is also discussed.

47 citations


Book ChapterDOI
26 Oct 2015
TL;DR: A set of social behaviors and certain specific features social robots should possess based on user’s experience in a longitudinal home study are provided and whether robots can actually be social is discussed.
Abstract: A common description of a social robot is for it to be capable of communicating in a humanlike manner. However, a description of what communicating in a ‘humanlike manner’ means often remains unspecified. This paper provides a set of social behaviors and certain specific features social robots should possess based on user’s experience in a longitudinal home study, discusses whether robots can actually be social, and presents some recommendations to build better social robots.

45 citations


Book ChapterDOI
26 Oct 2015
TL;DR: It is found that children who interact with the robot exhibiting more immediate nonverbal behaviour make significant learning gains, whereas those interacting with the less immediate robot do not.
Abstract: Nonverbal immediacy has been positively correlated with cognitive learning gains in human-human interaction, but remains relatively under-explored in human-robot interaction contexts. This paper presents a study in which robot behaviour is derived from the principles of nonverbal immediacy. Both high and low immediacy behaviours are evaluated in a tutoring interaction with children where a robot teaches how to work out whether numbers are prime. It is found that children who interact with the robot exhibiting more immediate nonverbal behaviour make significant learning gains, whereas those interacting with the less immediate robot do not. A strong trend is found suggesting that the children can perceive the differences between conditions, supporting results from existing work with adults.

45 citations


Book ChapterDOI
26 Oct 2015
TL;DR: Results showed improvement in RJA skills post training, relative to a pre-training test, which shows that with the use of objective measures and protocols grounded in methods of experimental psychology, it is possible to design efficient training of specific social cognitive mechanisms, which are the basis for more complex social skills.
Abstract: Due to technological and scientific advances, a new approach to autism therapy has emerged, namely robot-assisted therapy. However, as of now, no systematic studies have examined the specific cognitive mechanisms that are affected by robot-assisted training. This study used knowledge and methodology of experimental psychology to design a training protocol involving a pet robot CuDDler (A*STAR Singapore), which targeted at the specific cognitive mechanism of responding to joint attention (RJA). The training protocol used a modified attention cueing paradigm, where head direction of the robot cued children’s spatial attention to a stimulus presented on one of the sides of the robot. The children were engaged in a game that could be completed only through following the head direction of the robot. Over several weeks of training, children learned to follow the head movement of the robot and thus trained their RJA skills. Results showed improvement in RJA skills post training, relative to a pre-training test. Importantly, the RJA skills were transferred from interaction with the robot to interaction with the human experimenter. This shows that with the use of objective measures and protocols grounded in methods of experimental psychology, it is possible to design efficient training of specific social cognitive mechanisms, which are the basis for more complex social skills.

41 citations


Book ChapterDOI
26 Oct 2015
TL;DR: Four case studies of older adults who had chronic health conditions in a rural community given a healthcare robot in their homes for a period of three months to a year showed decreases in primary care visits and phone calls to the practitioners while the robot was present and increases in quality of life.
Abstract: Older adults in rural communities who have chronic health conditions are often isolated from social support and medical clinics. Robots may be able to assist with day to day healthcare and provide companionship. This paper presents four case studies of older adults who had chronic health conditions in a rural community. They were given a healthcare robot in their homes for a period of three months to a year. The robot reminded people to take medications, had entertainment and memory games, and skype. Rates of hospitalizations, primary care visits, and phone calls to the medical practitioners before the study began were compared to rates during the study period. Participants also completed questionnaires about their quality of life, mental health, medication adherence, and robot attitudes and were interviewed. The results showed a decrease in primary care visits and phone calls to the practitioners while the robot was present and increases in quality of life were observed. Despite encountering technical issues, patients were mostly positive and accepting of the robot, acknowledging its benefits as a companion.

40 citations


Book ChapterDOI
26 Oct 2015
TL;DR: Insight from the literature is extended to include tools from user-centered design and analyses of human-human interaction as the basis of a multidisciplinary approach in the development of an empathic robotic tutor.
Abstract: Within any learning process, the formation of a socio-emotional relationship between learner and teacher is paramount to facilitating a good learning experience. The ability to form this relationship may come naturally to an attentive teacher; but how do we endow an unemotional robot with this ability? In this paper, we extend upon insights from the literature to include tools from user-centered design (UCD) and analyses of human-human interaction (HHI) as the basis of a multidisciplinary approach in the development of an empathic robotic tutor. We discuss the lessons learned in respect to design principles with the aim of personalised learning with empathic robotic tutors.

35 citations


Book ChapterDOI
26 Oct 2015
TL;DR: A user study shows that controlling a learning robot enables supervisors to achieve similar task performance as with a non-learning robot, but with both fewer interventions and a reduced perception of workload.
Abstract: The Wizard-of-Oz robot control methodology is widely used and typically places a high burden of effort and attention on the human supervisor to ensure appropriate robot behaviour, which may distract from other aspects of the task engaged in. We propose that this load can be reduced by enabling the robot to learn online from the guidance of the supervisor to become progressively more autonomous: Supervised Progressively Autonomous Robot Competencies (SPARC). Applying this concept to the domain of Robot Assisted Therapy (RAT) for children with Autistic Spectrum Disorder, a novel methodology is employed to assess the effect of a learning robot on the workload of the human supervisor. A user study shows that controlling a learning robot enables supervisors to achieve similar task performance as with a non-learning robot, but with both fewer interventions and a reduced perception of workload. These results demonstrate the utility of the SPARC concept and its potential effectiveness to reduce load on human WoZ supervisors.

Book ChapterDOI
26 Oct 2015
TL;DR: This paper aims to present the activities in which independent-living older adults, i.e., older adults that do not depend upon anyone to carry out their activities, require a robot, and set specific goals for the future research in the field of Human-Robot Interaction (HRI).
Abstract: According to the United Nations World Population Prospects, the world’s population is aging. Older adults constitute a fragile part of society, as aging is always accompanied by major psychological and physical challenges. A way to cope with those challenges is to strive for a good Quality of Life (QoL) and contribute to successful aging. Social robots can play an important role in the promotion of QoL by integrating activities with independent-living older adults. Using a qualitative design through a focus group method, this paper aims to present the activities in which independent-living older adults, i.e., older adults that do not depend upon anyone to carry out their activities, require a robot. By understanding the activities where robots can positively influence and contribute to older adults’ QoL, we set specific goals for the future research in the field of Human-Robot Interaction (HRI).

Book ChapterDOI
26 Oct 2015
TL;DR: It is concluded that social gaze in assembly scenarios fulfills floor management functions and provides an indicator for the robot’s affordance, yet that it does not influence likability, mutual interest and suspected competence of the robot.
Abstract: In this paper we explore how social gaze in an assembly robot affects how naive users interact with it. In a controlled experimental study, 30 participants instructed an industrial robot to fetch parts needed to assemble a wooden toolbox. Participants either interacted with a robot employing a simple gaze following the movements of its own arm, or with a robot that follows its own movements during tasks, but which also gazes at the participant between instructions. Our qualitative and quantitative analyses show that people in the social gaze condition are significantly more quick to engage the robot, smile significantly more often, and can better account for where the robot is looking. In addition, we find people in the social gaze condition to feel more responsible for the task performance. We conclude that social gaze in assembly scenarios fulfills floor management functions and provides an indicator for the robot’s affordance, yet that it does not influence likability, mutual interest and suspected competence of the robot.

Book ChapterDOI
26 Oct 2015
TL;DR: Since children's designs may be influenced by their knowledge of robotics it is important to be aware of children's backgrounds and take those into account when including children in the design process.
Abstract: This paper presents an exploratory study on children's contributions to the design of a robotic teaching assistant for use in the classroom. The study focuses on two main questions: 1) How do children's designs differ from interaction designers'? 2) How are children's designs influenced by their knowledge of robotics (or lack thereof)? Using a creative drawing approach we collected robot drawings and design discussions from 53 participants divided into 11 groups: 5 groups of interaction designers (24 participants), 3 groups of children with robotics knowledge (14 participants), and 3 groups of children without formal robotics knowledge (15 participants). These data revealed that (1) interaction designers envisioned a small or child-sized non-gendered animal- or cartoon-like robot, with clear facial features to express emotions and social cues while children envisioned a bigger human-machine robot (2) children without formal robotics knowledge, envisioned a robot in the form of a rather formal adult-sized human teacher with some robotic features while children with robotics knowledge envisioned a more machine-like child-sized robot. This study thus highlights the importance of including children in the design of robots for which they are the intended users. Furthermore, since children's designs may be influenced by their knowledge of robotics it is important to be aware of children's backgrounds and take those into account when including children in the design process.

Book ChapterDOI
26 Oct 2015
TL;DR: The Multi-dimensional Robot Attitude Scale proposed in this study is designed to comprehensively assess attitudes towards domestic robots, allowing for a multifaceted understanding of people’s attitudes.
Abstract: This study investigated dimensions that construct people’s attitudes toward domestic robots, and developed a comprehensive measurement by which to assess such dimensions. Potential elements of attitudes were extracted from participants’ free descriptions and interviews, as well as a literature review. A questionnaire-based investigation was conducted using these elements, and a 12-factor structure was extracted employing factor analysis. A measurement called the Multi-dimensional Robot Attitude Scale was proposed to assess attitudes towards robots based on 12 dimensions. The internal reliability and representativeness of the proposed scale were verified. The Multi-dimensional Robot Attitude Scale proposed in this study is designed to comprehensively assess attitudes towards domestic robots, allowing for a multifaceted understanding of people’s attitudes.

Book ChapterDOI
26 Oct 2015
TL;DR: This paper reports the project of a shopping mall guide robot, named KeJia, which is designed for customer navigation, information providing and entertainment in a real environment and demonstrates the stability, validity and feasibility of this robot system.
Abstract: This paper reports the project of a shopping mall guide robot, named KeJia, which is designed for customer navigation, information providing and entertainment in a real environment. Our introduction focuses on the designs of robot’s hardware and software, faced challenges and the multimodal interaction methods including using a mobile phone app. In order to adapt the current localization and navigation techniques to such large and complex shopping mall environment, a series of related improvements and new methods are proposed. The robot is deployed in a large shopping mall for field test and stable operation for a fairly long time. The result demonstrates the stability, validity and feasibility of this robot system, and gives a positive reward to our original design motivation.

Book ChapterDOI
26 Oct 2015
TL;DR: This work is based on the hypothesis that personality traits and attitude towards robot appear in the behavioural response of humans during HRI, and proposes a set of four non-verbal movement features that characterize human behavior during the interaction.
Abstract: In this paper we present a system for automatic prediction of extraversion during the first thin slices of human-robot interaction (HRI). This work is based on the hypothesis that personality traits and attitude towards robot appear in the behavioural response of humans during HRI. We propose a set of four non-verbal movement features that characterize human behavior during the interaction. We focus our study on predicting Extraversion using these features extracted from a dataset consisting of 39 healthy adults interacting with the humanoid iCub. Our analysis shows that it is possible to predict to a good level (64 %) the Extraversion of a human from a thin slice of interaction relying only on non-verbal movement features. Our results are comparable to the state-of-the-art obtained in HHI [23].

Book ChapterDOI
26 Oct 2015
TL;DR: An original analysis methodology is proposed which blends behavioral cues and reported phenomenological perceptions into a compound index and shows the impact of unexpected robot behaviors on the perception of a robot by children and their subsequent engagement in a playful interaction based on a novel “domino” task.
Abstract: We present a study on the impact of unexpected robot behaviors on the perception of a robot by children and their subsequent engagement in a playful interaction based on a novel “domino” task. We propose an original analysis methodology which blends behavioral cues and reported phenomenological perceptions into a compound index.

Book ChapterDOI
26 Oct 2015
TL;DR: Evidence is provided that suggests prominent gender stereotypes might not be as pronounced in human-robot interaction as may be expected based on previous research, and that interface and robot designers need to be wary of which stereotypes they bring to the table.
Abstract: In this paper, we provide evidence that suggests prominent gender stereotypes might not be as pronounced in human-robot interaction as may be expected based on previous research. We investigate stereotypes about people interacting with robots, such as men being more engaged, and stereotypes which may be applied to robots that have a perceived gender, such as female robots being perceived as more suitable for household duties. Through a user study, we not only fail to find support for many existing stereotypes, but our analysis suggests that if such effects exist, they may be small. This implies that interface and robot designers need to be wary of which stereotypes they bring to the table, and should understand that even stereotypes with prior experimental evidence may not manifest strongly in social human-robot interaction.

Book ChapterDOI
26 Oct 2015
TL;DR: The results show that displaying familiarity with a user as well as eliciting the user's self-disclosure in off-activity talk contribute to the user’s perception of the social robot as a friend.
Abstract: Establishing a positive relationship between a user and a system is considered important or even necessary in applications of social robots or other computational artifacts which require long-term engagement. We discuss several experiments investigating the effects of specific relational verbal behaviors within the broader context of developing a social robot for long-term support of self-management improvement in children with Type 1 diabetes. Our results show that displaying familiarity with a user as well as eliciting the user’s self-disclosure in off-activity talk contribute to the user’s perception of the social robot as a friend. We also observed increased commitment to interaction success related to familiarity display and increased interest in further interactions related to off-activity talk.

Book ChapterDOI
26 Oct 2015
TL;DR: Investigating whether the social relevance of a robot can be manipulated via its physical appearance and whether there is a linear relationship between appearance and gaze following in a counter-predictive gaze cueing paradigm shows that while robots are capable of inducing gaze following, the degree to which gaze is passively followed does not linearly decrease with physical human-likeness.
Abstract: Gaze following occurs automatically in social interactions, but the degree to which we follow gaze strongly depends on whether an agent is believed to have a mind and is therefore socially relevant for the interaction. The current paper investigates whether the social relevance of a robot can be manipulated via its physical appearance and whether there is a linear relationship between appearance and gaze following in a counter-predictive gaze cueing paradigm (i.e., target appears with a high likelihood opposite of the gazed-at location). Results show that while robots are capable of inducing gaze following, the degree to which gaze is passively followed does not linearly decrease with physical human-likeness. Rather, the relationship between appearance and gaze following is best described by an inverted u-shaped pattern, with automatic cueing effects (i.e., attending to the cued location) for agents of mixed human-likeness and reversed cueing effects (i.e., attending to the predicted location) for agents of either full human-likeness (100% human) or full robot-likeness (100% robot). The results are interpreted with regard to cognitive resource theory and design implications are discussed.

Book ChapterDOI
26 Oct 2015
TL;DR: To study the possible role of experience as a mediator between expectation and satisfaction, a scale for HRI is developed that measures expectations and satisfaction of the users and a study with end-users interacting with a social robot.
Abstract: Before interacting with a futuristic technology such as a robot, there is a lot of space for the creation of a whole set of expectations towards that interaction. Once that interaction happens, users can be left with a hand full of satisfaction, dissatisfaction, or even a mix of both. To study the possible role of experience as a mediator between expectation and satisfaction, we developed a scale for HRI that measures expectations and satisfaction of the users. Afterwards, we conducted a study with end-users interacting with a social robot. The robot is being developed to be an empathic robotic tutor to be used in real schools, with input from primary end-users (children). Children’s expectations and subsequent satisfaction after the interaction with the robotic tutor were analysed. The results can be fed back to the system developers on how well it is being designed for such a target population, and what factors regarding their expectation and satisfaction have shifted after the experience of interaction. By delivering on the children’s expectations, we aim to design a robotic tutor that provides enough satisfaction to sustain an enjoyable and natural interaction in the real educational environment.

Book ChapterDOI
26 Oct 2015
TL;DR: A user evaluation study on location at the Royal Alcazar in Seville, Spain, with the fully autonomous tour guide robot FROG indicates that even if isolated technical features work perfectly in controlled settings, they might not work well in the integrated system, because naive people interact with the system in an unforeseen manner.
Abstract: In this paper we present a user evaluation study on location at the Royal Alcazar in Seville, Spain, with the fully autonomous tour guide robot FROG. In this robot, technological innovations in navigation and vision were integrated with state-of-the-art design for robot behavior in order to provide interactive tours and adaptive content to visitors. In our user evaluation study we aimed to gain insights in user experiences of and attitudes and responses towards this fully autonomous social robot. Such studies are important, because they provide information about how people interact with social robots outside a controlled setting. Invited as well as spontaneous visitors followed tours guided by FROG and were interviewed about their opinions and experiences. Our findings indicate that even if isolated technical features work perfectly in controlled settings, they might not work well in the integrated system, because naive people interact with the system in an unforeseen manner.

Book ChapterDOI
26 Oct 2015
TL;DR: This research presents a thorough case study regarding interaction of individuals having PMLD with a humanoid robot in different possible categories of robotic interaction and suggests that robotic interactions can help to induce a target behavior among these individuals.
Abstract: A tremendous amount of research is being performed regarding robot interaction with individuals having intellectual disability, especially for kids with Autism Spectrum Disorders (ASD). These researches have shown many promising advancements about the use of interactive robots for rehabilitation of such individuals. However, these studies fail to analyze and explore the effects of robotics interaction with individuals having profound and multiple learning disabilities (PMLD). This research presents a thorough case study regarding interaction of individuals having PMLD with a humanoid robot in different possible categories of robotic interaction. Separate interaction activities are designed as a representative for the different categories of possible clinical applications of the interactive robot. All the trials were assessed using different evaluation techniques. Finally, the results strongly suggest that robotic interactions can help to induce a target behavior among these individuals, to teach and to encourage them which can bring an autonomy to certain extent in their life.

Book ChapterDOI
26 Oct 2015
TL;DR: Results indicate that manipulations of robot’s age and gender are successful for all voice conditions, however some voices are preferred over the others by children in Ireland.
Abstract: This paper presents a study of children’s responses to the perceived gender and age of a humanoid robot Nao that communicated with four genuine synthesized child voices. This research investigates children’s preferences for an English accent. Results indicate that manipulations of robot’s age and gender are successful for all voice conditions, however some voices are preferred over the others by children in Ireland.

Book ChapterDOI
26 Oct 2015
TL;DR: It was found that participants showed social signals in 49.3% of error situations, more during social norm violations and less during technical failures, while participants showed more social signals when the robot did not react.
Abstract: Human-robot interaction experiments featuring error situations are often excluded from analysis. We argue that a lot of value lies hidden in this discarded data. We analyzed a corpus of 201 videos that show error situations in human-robot interaction experiments. The aim of our analysis was to research (a) if and which social signals the experiment participants show in reaction to error situations, (b) how long it takes the participants to react in the error situations, and (c) whether different robot actions elicit different social signals. We found that participants showed social signals in 49.3% of error situations, more during social norm violations and less during technical failures. Task-related actions by the robot elicited less social signals by the participants, while participants showed more social signals when the robot did not react. Finally, the participants had an overall reaction time of 1.64 seconds before they showed a social signal in response to a robot action. The reaction times are specifically long (4.39 seconds) during task-related actions that go wrong during execution.

Book ChapterDOI
26 Oct 2015
TL;DR: The hypothesis that acceptance of a robot could be directly proportional to cultural closeness was supported, while the hypothesis that similar foreign robots are equally less accepted regardless of the country was rejected.
Abstract: A complex relationship exists between people’s cultural background and their general acceptance towards robots. Previous studies supported the idea that humans may accept more easily a robot that can adapt to their specific culture. However, it is not clear whether between two robots which are identified as foreign robots because of their verbal and non-verbal expressions, the one that is culturally closer may be preferred or not. In this experiment, participants of Dutch nationality were engaged in a simulated video conference with a robot that is greeting and speaking either in German or in Japanese; they completed a questionnaire assessing their preferences and their emotional state. As Dutch participant showed less signs of discomfort and better acceptance when interacting with a German robot, the hypothesis that acceptance of a robot could be directly proportional to cultural closeness was supported, while the hypothesis that similar foreign robots are equally less accepted regardless of the countrywas rejected. Implications are discussed for how robots should be designed to be employed in different countries.

Book ChapterDOI
26 Oct 2015
TL;DR: This paper has designed and implemented a robotic head, “Ava”, which turns toward the speaker in noisy environments, and employs three different algorithms simultaneously for feature extraction and a two-layer perceptron neural network for localization.
Abstract: Socially cognitive robots are supposed to communicate and interact with humans and other robots in the most natural way. Listeners turn their heads to-ward speakers to enhance communicative attention; this is also an act of appreciation to the speaker. In this paper we have designed and implemented a robotic head, “Ava”, which turns toward the speaker in noisy environments. Ava employs a Speech Activity Detection system which differentiates speech segments of non-speech. Then the speech segments are processed to reduce different kinds of noise levels. The speaker localization system then finds the speaker position in the azimuth plane and commands motors to turn horizon-tally toward the speaker in a smooth trajectory. Ava has two built-in micro-phones inside its ears and employs three different algorithms simultaneously for feature extraction and a two-layer perceptron neural network for localization. Ava operates real-time and updates the position even in its moving phase. Experiments show a precision of +/-5 degrees in white noise in SNR of 10 dB.

Book ChapterDOI
26 Oct 2015
TL;DR: A feasible framework composed of three technologies: a tablet to train facial expressions recognition, a humanoid robot as reinforcer, and a wearable device to quantify smiles is proposed.
Abstract: Different studies explore the use of electronic screen media to train specific social skills, since they provide visual elements which are well accepted by children with ASD. However, even if children have high levels of attention to the screen, this might also reduce the possibilities of interacting with others. The challenge lays on finding ways to encourage and motivate the child to keep learning and share the experience with others. For this reason, we propose a feasible framework composed of three technologies: a tablet to train facial expressions recognition, a humanoid robot as reinforcer, and a wearable device to quantify smiles. We did a feasibility test with adults not only to verify the machine response, but also to obtain qualitative data regarding the interaction with the robot. In this study we analyze the importance and the synergistic effect of combining screen media with the robot embodiment and affective computing technologies.

Book ChapterDOI
26 Oct 2015
TL;DR: A robotic system able to guide a person to a destination in a socially acceptable way that is able to estimate if the user is still actively following and react accordingly, and base the planning model on Hierarchical Mixed Observability Markov Decision Processes to decompose the task in smaller subsets, simplifying the computation of a solution.
Abstract: In this paper we present a robotic system able to guide a person to a destination in a socially acceptable way. Our robot is able to estimate if the user is still actively following and react accordingly. This is achieved by stopping and waiting for the user or by changing the robot's speed to adapt to his needs. We also investigate how the robot can influence a person's behavior by changing its speed, to account for the urgency of the current task or for environmental stimulus, and by interacting with him when he stops following it. We base the planning model on Hierarchical Mixed Observability Markov Decision Processes to decompose the task in smaller subsets, simplifying the computation of a solution. Experimental results suggest the efficacy of our model.