Human Agent Interaction

As robots become more advanced and capable, developing trust is an important factor of human-robot interaction and cooperation. However, as multiple environmental and social factors can influence trust, it is important to develop more elaborate scenarios and methods to measure human-robot trust. A widely used measurement of trust in social science is the investment game. In this study, we propose a scaled-up, immersive, science fiction Human-Robot Interaction (HRI) scenario for intrinsic motivation on human-robot collaboration, built upon the investment game and aimed at adapting the investment game for human-robot trust. For this purpose, we utilise two Neuro-Inspired Companion (NICO) -robots and a projected scenery. We investigate the applicability of our space mission experiment design to measure trust and the impact of nonverbal communication. We observe a correlation of 0.43 (p = 0.02) between self-assessed trust and trust measured from the game and a positive impact of non-verbal communication on trust (p = 0.0008) and robot perception for anthropomorphism (p = 0.007) and animacy (p = 0.00002). We conclude that our scenario is an appropriate method to measure trust in human-robot interaction and also to study how non-verbal communication influences a human's trust in robots.

Modeling Human-Agent Interaction with Active Ontologies Didier Guzzoni and Charles Baur Robotics Systems Laboratory Swiss Federal Institute of Technology (EPFL) 1015 Lausanne, Switzerland [email protected], [email protected] ... Active Console Active Editor ...

We conducted a study with 25 children to investigate the efectiveness of a robot measuring and encouraging production of spatial concepts in a second language compared to a human experimenter. Productive vocabulary is often not measured in second language learning, due to the diiculty of both learning and assessing productive learning gains. We hypothesized that a robot peer may help assessing productive vocabulary. Previous studies on foreign language learning have found that robots can help to reduce language anxiety, leading to improved results. In our study we found that a robot is able to reach a similar performance to the experimenter in getting children to produce, despite the person's advantages in social ability, and discuss the extent to which a robot may be suitable for this task. CCS CONCEPTS • Human-centered computing → User studies; • Social and professional topics → Assistive technologies; • Computing methodologies → Natural language processing; Cognitive robotics;

We present a corpus of 44 human-agent verbal and gestural story retellings designed to explore whether humans would gesturally entrain to an embodied intelligent virtual agent. We used a novel data collection method where an agent presented story components in installments, which the human would then retell to the agent. At the end of the installments, the human would then retell the embodied animated agent the story as a whole. This method was designed to allow us to observe whether changes in the agent’s gestural behavior would result in human gestural changes. The agent modified its gestures over the course of the story, by starting out the first installment with gestural behaviors designed to manifest extraversion, and slowly modifying gestures to express introversion over time, or the reverse. The corpus contains the verbal and gestural transcripts of the human story retellings. The gestures were coded for type, handedness, temporal structure, spatial extent, and the degree to ...

Advancements in Human-Robot Interaction involve robots being more responsive and adaptive to the human user they are interacting with. For example, robots model a personalised dialogue with humans, adapting the conversation to accommodate the user's preferences in order to allow natural interactions. This study investigates the impact of such personalised interaction capabilities of a human companion robot on its social acceptance, perceived intelligence and likeability in a human-robot interaction scenario. In order to measure this impact, the study makes use of an object learning scenario where the user teaches different objects to the robot using natural language. An interaction module is built on top of the learning scenario which engages the user in a personalised conversation before teaching the robot to recognise different objects. The two systems, i.e. with and without the interaction module, are compared with respect to how different users rate the robot on its intelligence and sociability. Although the system equipped with personalised interaction capabilities is rated lower on social acceptance, it is perceived as more intelligent and likeable by the users.

As robots become more advanced and capable, developing trust is an important factor of human-robot interaction and cooperation. However, as multiple environmental and social factors can influence trust, it is important to develop more elaborate scenarios and methods to measure human-robot trust. A widely used measurement of trust in social science is the investment game. In this study, we propose a scaled-up, immersive, science fiction Human-Robot Interaction (HRI) scenario for intrinsic motivation on human-robot collaboration, built upon the investment game and aimed at adapting the investment game for human-robot trust. For this purpose, we utilise two Neuro-Inspired Companion (NICO)-robots and a projected scenery. We investigate the applicability of our space mission experiment design to measure trust and the impact of nonverbal communication. We observe a correlation of 0.43 (p = 0.02) between self-assessed trust and trust measured from the game and a positive impact of non-verbal communication on trust (p = 0.0008) and robot perception for anthropomorphism (p = 0.007) and animacy (p = 0.00002). We conclude that our scenario is an appropriate method to measure trust in human-robot interaction and also to study how non-verbal communication influences a human's trust in robots.

Prior work notes dispositional, learned, and situational aspects of trust in automation. However, no work has investigated the relative role of these factors in initial trust of an automated system. Moreover, trust in automation researchers often consider trust unidimensionally, whereas ability, integrity, and benevolence perceptions (i.e., trusting beliefs) may provide a more thorough understanding of trust dynamics. To investigate this, we recruited 163 participants on Amazon's Mechanical Turk (MTurk) and randomly assigned each to one of 4 videos describing a hypothetical drone system: one control, the others with additional system performance or process, or both types of information. Participants reported on trusting beliefs in the system, propensity to trust other people, risk-taking tendencies, and trust in the government law enforcement agency behind the system. We found that financial risk-taking tendencies influenced trusting beliefs. Also, those who received process information were likely to have higher integrity and ability beliefs than those not receiving process information, while those who received performance information were likely to have higher ability beliefs. Lastly, perceptions of structural assurance positively influenced all three trusting beliefs. Our findings suggest that a) users' risktaking tendencies influence trustworthiness perceptions of systems, b) different types of information about a system have varied effects on the trustworthiness dimensions, and c) institutions play an important role in users' calibration of trust. Insights gained from this study can help design training materials and interfaces that improve user trust calibration in automated systems.

Sharing a same rhythm among different agents matures close empathic relationship. However it is still unclear how rhythmic information is transferred to emphatic emotion in our brain. In this paper, we propose human-robot drumming interaction system to investigate how rhythmic physical interaction brings emphatic emotion. In this paper, we introduce the detail of our proposed system.

We present a study that investigates the effect of incorporating memory in the interaction for a virtual robotic tutor in terms of helping children achieve a pedagogical goal and the perceived likeability and empathy of the tutor. The domain is a virtual robotic tutor who is guiding and helping learners through a mobile Treasure Hunt exercise that tests their map reading skills. The contribution described in this paper is the discovery that incorporating 'memory' through utterances that recall events from previous interactions significantly increases the learner's ability to perform a pedagogical task. However, the virtual tutor with memory was perceived as less likeable and the instructions given as harder to follow than with a virtual tutor without memory. In addition, there was a significant drop in perceived empathy. This work has a large potential influence in the field of interaction design for agents as one cannot blindly add in human-like features, such as, memory that improve task performance without considering the potential detrimental effects to the perceived empathy and likeability.

SWoOZ is an intuitive teleoperation platform using a humanoid robot as a proxy between two humans: a remote user teleoperating the robot and a local user interacting directly with it. NAO (Aldebaran) is the proxy used in this study. The remote user controls its head motion with his own movements (live) while his real voice is transmitted to the local user with an unnoticeable lag time. This paper presents a user study of the platform in the context of a long-distance survey and investigates the possible effect of the remote user's previous experience with robots on the local users' evaluation of the proxy. Although found useful, likable and satisfying by all the local users, only the ones interviewed by the non-naive user find it averagely credible. Results fail to validate an effect of the remote users' previous experience with robots on the local users.

For dissemination of knowledge on maritime safety culture and safety management to differentactors and stakeholders in the maritime sector, a didactic design is required and must bedeveloped. Using modern multimedia didactic tools, teachers can apply interactive scenario-basedmodels. The experience-based learning can connect theory and practice. The students of maritimeuniversities can be chosen as target groups and the didactic design can be adapted for them. Didactic design can be tested in a classroom, including later interaction and can be used forlearning the topics on safety culture and safety management.

This paper summarizes our efforts to bring together and extend the best in current theory and technologies for teamwork-centered autonomy for space applications. Traditional planning technologies at the foundation of intelligent robotic systems typically take an autonomycentered approach, with representations, mechanisms, and algorithms that have been designed to ingest a set of goals and output a complete plan in the most efficient and sound fashion possible. A teamwork-centered autonomy approach, on the other hand, takes as a beginning premise ...

Care issues and costs associated with an increasing elderly population is becoming a major concern for many countries. The use of assistive robots in 'smart-home' environments has been suggested as a possible partial solution to these concerns. One of the many challenges faced is the personalisation of the robot to meet the changing needs of the elderly person over time. One approach is to allow the elderly person, or their carers or relatives, to teach the robot to both recognise activities in the smart home and to teach it to carry out behaviours in response to these activities. The overriding premise being that such teaching is both intuitive and 'non-technical'. As part of a European project researching and evaluating these issues a commercially available autonomous robot has been deployed in a fully sensorised but otherwise ordinary suburban house. Occupants of the house are equipped with a non-technical teaching and learning system. This paper details the design approach to the teaching, learning, robot and smart home systems as an integrated unit and presents results from an evaluation of the teaching component and a preliminary evaluation of the learning component in a Human-Robot interaction experiment. Results from this evaluation indicated that participants overall found this approach to personalisation useful, easy to use, and felt that they would be capable of using it in a real-life situation both for themselves and for others. However there were also some salient individual differences within the sample.

We present our study of Calamaro: a robotic platform designed to investigate the impact of emotive motion on people, and its deployment in an extensive field study in a busy public space at the University of Calgary campus. Our paper details the design of the Calamaro robot, the field study conducted with it, including hundreds of observers and 88 participants, and our quantitative and qualitative findings. The paper provides a thorough discussion of the implications of our results on the design of robotic emotive motions, and reflections on the deployment of robotic interfaces in field studies.

The aim of intelligence analysis is to make sense of information that is often conflicting or incomplete, and to weigh competing hypotheses that may explain a situation. This imposes a high cognitive load on analysts, and there are few automated tools to aid them in their task. In this paper, we present an agent-based tool to help analysts in acquiring, evaluating and interpreting information in collaboration with others. Agents assist analysts in reasoning with different types of evidence to identify what happened and why, what is credible, and how to obtain further evidence. Argumentation schemes lie at the heart of the tool, and sensemaking agents assist analysts in structuring evidence and identifying plausible hypotheses. A crowdsourcing agent is used to reason about structured information explicitly obtained from groups of contributors, and provenance is used to assess the credibility of hypotheses based on the origins of the supporting information.

Robotic emotional expressions could benefit social communication between humans and robots, if the cues such expressions contain were to be intelligible to human observers. In this paper, we present a design framework for modelling emotionally expressive robotic movements. The framework combines approach-avoidance with Shape and Effort dimensions, derived from Laban, and makes use of anatomical body planes that are general to both humanoid and non-humanoid body forms. An experimental validation study is reported with 34 participants rating an implementation of five expressive behaviours on a non-humanoid robotic platform. The results demonstrate that such expressions can encode basic emotional information, in that the parameters of the proposed design model can convey the meaning of emotional dimensions of valence, arousal and dominance. The framework thus creates a basis for implementing a set of emotional expressions that are appropriately adapted to contexts of humanrobot joint activity.

This paper presents a study that analyzes the effects of robots' gaze hints on children's performance in a cardmatching game. We conducted a within-subjects study, in which children played a card game "Memory" in the presence of a robot tutor in two sessions. In one session, the robot gave hints to help the child find matching cards by looking at the correct match and, in the other session, the robot only looked at the child and did not give them any help. Our findings show that the use of gaze hints (help condition) made the matching task significantly easier and that children used a significantly fewer number of tries than without help. This study provides guidelines on how to design interactive behaviors for robots taking the role of tutors to elicit help-seeking behavior in children.

Gaze is an important nonverbal cue in human-human communication, for example, in communicating direction of attention. Therefore, presumably being able to understand and provide gaze cues is an important aspect in robot's interactive behavior. While there is considerable progress, as regards the design of social gaze cues for robots, there is little that has been done to examine the ability of humans to read and accept help signals from a robot's gaze. In this study, we examine how people perceive gaze cues and head angles directed towards different target positions on a table when human and NAO robot are sitting against each other as in board game scenarios. From the results, we show that when the head pitch angle is higher (24±2) and the depth is less, approximately 20 cm from the robot, participants detected the positions with good accuracy. Unexpectedly, the locations on the left of the robot were detected with lower accuracy. In conclusion, we discuss the implications of this research for design of interaction settings between human and a robot that is intended for social and educational support.

Multimodal corpora prove useful at different stages of the development process of embodied conversational agents. Insights into human-human communicative behaviors can be drawn from such corpora. Rules for planning and generating such behavior in agents can be derived from this information. And even the evaluation of human-agent interactions can rely on corpus data from human-human communication. In this paper, we exemplify how corpora can be exploited at the different development steps, starting with the question of how corpora are annotated and on what level of granularity. The corpus data can be used either directly for imitating the human behavior recorded in the corpus or rules can be derived from the data which govern the behavior planning process. Corpora can even play a vital role in the evaluation of agent systems. Several studies are presented that make use of corpora for the evaluation task.

This paper concerns interaction with social robots and focuses on the evaluation of a robot application that allows users to access interesting information from Wikipedia. The evaluation method compares the users' expectations with their experience with the robot, and takes into account their self-declared previous experience with robots. The results show that most participants had an overall positive experience, even though the averages indicate a slight negative tendency related to expectations of the robot's behavior and being understood by the robot. Interestingly, the most experienced users seem to be the most critical.

This paper presents a study that analyzes the effects of robots' gaze hints on children's performance in a cardmatching game. We conducted a within-subjects study, in which children played a card matching game "Memory" in the presence of a robot tutor in two sessions. In one session, the robot gave hints to help the child find matching cards by looking at the correct match and, in the other session, the robot only looked at the child and did not give them any help. Children performance was measured using the number of tries and overall time used to complete the game. Our findings show that the use of gaze hints (help condition) made the matching task significantly easier and that children used significantly fewer tries than without help.

Gaze is an important nonverbal cue in human-human communication, for example, in communicating direction of attention. Therefore, presumably being able to understand and provide gaze cues is an important aspect in robot's interactive behavior. While there is considerable progress, as regards the design of social gaze cues for robots, there is little that has been done to examine the ability of humans to read and accept help signals from a robot's gaze. In this study, we examine how people perceive gaze cues and head angles directed towards different target positions on a table when human and NAO robot are sitting against each other as in board game scenarios. From the results, we show that when the head pitch angle is higher (24±2) and the depth is less, approximately 20 cm from the robot, participants detected the positions with good accuracy. Unexpectedly, the locations on the left of the robot were detected with lower accuracy. In conclusion, we discuss the implications of this research for design of interaction settings between human and a robot that is intended for social and educational support.

The development of automated technologies in our daily life has transformed the role of human operators from a controller to a teammate who shares control with automated agents. However, this 'teammate' relationship between humans and automation raises an important but challenging research question regarding the formation of human-agent trust. Considering that the formation of human-agent trust is a dynamic and sophisticated process involving human factors, this study conducted a two-phase online experiment to examine personal influences on users' trust propensity and their trust formation in human-agent interactions. Our findings revealed distinctive personal influences on dispositional trust and the formation of human-agent trust at different stages. We found that users who exhibit higher trust propensities in humans also develop higher trust toward automated agents in initial stages. This study, as the first of its kind, not only fills the gap of knowledge about personal influences on human-agent trust, but also offers opportunities to enhance the future design of automated agent systems.

The successful integration of automation in systems that affect human experiences requires the user acceptance of those automated functionalities. For example, the human comfort felt during a ride is affected by the automated control behavior of the vehicle. The challenge presented in this paper is how to develop an intelligent agent that learns its users' driving preferences and adjusts the vehicle control in real time, accordingly, minimizing the number of otherwise required manual interventions. This is a hard problem since users' preferences can be complex, context dependent and do not necessarily translate to the language of machines in a simple and straightforward manner. Our solution includes (1) a simulation test bed, (2) an adaptive intelligent interface and (3) an adaptive agent that learns to predict user's driving discomfort and it also learns to compute corrective actions that maximize user acceptance of automated driving. Overall, we conducted three user studies with 94 subjects in simulated driving scenarios. Our results show that our intelligent agent learned to successfully predict how to adjust the automated driving style to increase user' acceptance by decreasing the number of user manual interventions.

Conversational agents can provide valuable cognitive and/or emotional assistance to elderly users or people with cognitive impairments who often have difficulties in organizing and following a structured day schedule. Previous research showed that a virtual assistant that can interact in spoken language would be a desirable help for those users. However, these user groups pose specific requirements for spoken dialogue interaction that existing systems hardly meet. This paper presents work on a virtual conversational assistant that was designed for, and together with, elderly as well as cognitively handicapped users. It has been specifically developed to enable ‘socially cooperative dialogue’ – adaptive and aware conversational interaction in which mutual understanding is co-constructed and ensured collaboratively. The technical approach is described and results of evaluation studies are reported.

This paper investigates the effects of a listener robot that joins a storytelling situation for children as a sideparticipant. For this purpose, we develop a storytellingrobot system that consists of both reader and listener robots. Our semi-autonomous system involves a human operator who makes correct responses and provides easily understandable answers to the children's questions during storytelling. We develop a gaze model for the natural and autonomous gaze behaviors of a reader robot by considering multiple listeners and a storytelling object (a display that shows images). We conducted an experiment with 16 children to investigate whether they preferred storytelling with/without the listener robot and the changes of speech activities during the storytelling. Children preferred storytelling with the listener robot to storytelling without it. Their speech activities decreased when the listener robot was involved in the storytelling.

In this video submission, we describe a scenario developed in the EMOTE project. The overall goal of the EMOTE project is to develop an empathic robot tutor for 11-13 year old school students in an educational setting. The pedagogical domain here is to assist students in learning and testing their map-reading skills typically learned as part of the geography curriculum in schools. We show this scenario with a NAO robot interacting with the students whilst performing mapreading tasks on a touch-screen device in this video.

To my dearest mother, Esmat Malekzadeh, who has been my rock through thick and thin, and whose sacrifices and love have kept me going. Your unending support and faith in my abilities have guided my steps. To my beloved wife, Tianshu Wang, whose patience, understanding, wisdom, and constant support have enabled me to endure. Your love and unwavering support have shone a light on this difficult but ultimately rewarding journey. This thesis stands as a testament to the love, sacrifices, and unwavering support of these remarkable, kind, and supportive angels of my life. Thank you for being my guiding stars, shaping my aspirations, and standing by me throughout this remarkable odyssey.

In this paper, we outline an approach to policy-based coordination in joint human-agent activity. The approach is grounded in a theory of joint activity originally developed in the context of discourse, and now applied to the broader realm of human-agent interaction. We have been gradually implementing selected aspects of policy-based coordination within the KAoS services framework and have been developing a body of examples that will guide additional testing of these ideas through detailed studies of work practice.

Politeness is at the core of the common set of behavioral norms that regulate human communication and is therefore of significant interest in the design of Human-Robot Interactions. In this paper, we investigate how the politeness behaviors of a humanoid robot impact human decisions about where to join a group of two robots. We also evaluate the resulting impact on the perception of the robot's politeness. In a study involving 59 participants, the main (Pepper) robot in the group invited participants to join using six politeness behaviors derived from Brown and Levinson's politeness theory. It requests participants to join the group at the furthest side of the group which involves more effort to reach than a closer side that is also available to the participant but would ignore the request of the robot. We evaluated the robot's effectiveness in terms of persuasiveness, politeness, and clarity. We found that more direct and explicit politeness strategies derived from the theory have a higher level of success in persuading participants to join at the furthest side of the group. We also evaluated participants' adherence to social norms i.e. not walking through the center, or o-space, of the group when joining it. Our results showed that participants tended to adhere to social norms when joining at the furthest side by not walking through the center of the group of robots, even though they were informed that the robots were fully automated.

State of the art visual question answering (VQA) methods rely heavily on deep network architectures. These methods require a large labeled dataset for training, which is not available in many domains. Also, it is difficult to explain the working of deep networks learned from such datasets. Towards addressing these limitations, this paper describes an architecture inspired by research in cognitive systems that integrates commonsense logical reasoning with deep learning algorithms. In the context of answering explanatory questions about scenes and the underlying classification problems, the architecture uses deep networks for processing images and for generating answers to queries. Between these deep networks, it embeds components for non-monotonic logical reasoning with incomplete commonsense domain knowledge and for decision tree induction. Experimental results show that this architecture outperforms an architecture based only on deep networks when the training dataset is small, provides comparable performance on larger datasets, and provides intuitive answers to explanatory questions. CCS CONCEPTS • Computing methodologies → Nonmonotonic, default reasoning and belief revision; Logic programming and answer set programming; Scene understanding; Neural networks;

State of the art visual question answering (VQA) methods rely heavily on deep network architectures. These methods require a large labeled dataset for training, which is not available in many domains. Also, it is difficult to explain the working of deep networks learned from such datasets. Towards addressing these limitations, this paper describes an architecture inspired by research in cognitive systems that integrates commonsense logical reasoning with deep learning algorithms. In the context of answering explanatory questions about scenes and the underlying classification problems, the architecture uses deep networks for processing images and for generating answers to queries. Between these deep networks, it embeds components for non-monotonic logical reasoning with incomplete commonsense domain knowledge and for decision tree induction. Experimental results show that this architecture outperforms an architecture based only on deep networks when the training dataset is small, provides comparable performance on larger datasets, and provides intuitive answers to explanatory questions. CCS CONCEPTS • Computing methodologies → Nonmonotonic, default reasoning and belief revision; Logic programming and answer set programming; Scene understanding; Neural networks;

In the context of human-agent interaction, we see the emergence of computational artefacts that display hybridity because they can be experienced as tools and agents. In this paper we propose a tool-agent spectrum as an analytical lens that uses 'intention' as a central concept. This spectrum aims to clarify how a computational object can change from being conducive to the intentions of others ('tool') to appearing to have intentions of its own ('agent'), or vice versa. We have applied this analytical lens to unravel people's experiences in two hybrid cases; guide dogs as a living mobility aid for the visually impaired and an experimental wearable object named "BagSight" as a rudimentary artificial counterpart. We compared both cases through the lens of a toolagent spectrum and elaborate on these results by discussing some of the principles by which computational artefacts can shift across the spectrum. We conclude by discussing the limitations of this study and provide suggestions for future work.

Aiming to increase the believability of intelligent virtual agents, this paper describes the implementation of a parameterizable gaze behavior system based on psychological notions of human gaze. The resulting gaze patterns and agent behaviors cover a wide range of possible uses due to this parametrization. We also show how we integrated and used the system within a virtual environment.

Speech-based dialog systems primarily interact with users through their spoken responses. Understanding users' perception of, and subconscious behaviors toward, the system's speech are crucial for improving their design. In the current study, a voice chatbot designed for having a conversation with users in the domain of music is used to test the impact of emotional expressiveness in its text-to-speech (TTS) output. We parametrically manipulated the degree of emotional expressiveness via prosody and lexical choice across conditions. We used a two-pronged approach to test these effects on users: a user interaction study (Experiment 1-betweensubjects design) and an independent perception study (Experiment 2-within-subjects design). Both studies provide converging evidence that increasing emotional prosody yields more positive perceptions of chatbot interactions, in increasing perception of emotional expressiveness (Experiments 1 and 2) as well as overall engagement, human-likeness, and likability of the bot (Experiment 2). We discuss these findings in terms of theories of human-computer interaction, as well as their implications for conversational design. CCS CONCEPTS • Human-centered computing → HCI design and evaluation methods; Empirical studies in HCI .

Cet article décrit Iagotchi, un personnage virtuel philosophique et artistique qui apprend et développe des connaissances à partir de ses interactions avec l'humain. Iagotchi se présente à la fois comme un apprenant et un expert avec comme objectifs principaux (1) d'accompagner l'homme dans ses questionnements, (2) de lui fournir des réponses pertinentes sur la base de ses requêtes et (3) de générer des textes poétiques cohérents. Dans ce travail, nous décrivons l'architecture du système de Iagotchi et les composants clés tels que le moteur de conversation, le gestionnaire de sujets et le générateur de poésies.

The focus of the research described in this paper is to explore children's perception of a social robot's learning abilities and behavior in an educational context. With this purpose, we conducted a long-term study with children in a school by adopting the learning-by-teaching learning method. The scenario involves a "learner-agent" (a robot) which seeks help from a child (a teacher) in correcting the shapes of a few letters it writes. Two versions of the robot were built: one where it learns and another where it does not improve over time. The results of the study suggest that children's social relationship with the robot was not affected by the learning abilities of the agent.

Human beings live in a society with a complex system of social-emotional relations. Trust is one key concept in this system. It can help to reduce the social complexity, mainly in those cases where it is necessary to cooperate. Thus, the area of social robotics has been studying different approaches to perform cooperative tasks between humans and robots. Here, we examine the influence of a set of factors (gender, emotional representation, making Small Talk and embodiment) that may affect the trustworthiness of a robot. The results showed that these factors influence the level of trust that people put in robots. Specifically, a social robot with embodiment telling a sad story with sad facial expression and gestures has more influence on the trust level of a female subject.

The recognition of an indicated object by an interacting person is an essential function for a robot that acts in daily environments. To improve recognition accuracy, clarifying the goal of the indicating behaviors is needed. For this purpose, we experimentally compared two kinds of interaction strategies: a robot that explicitly provides instructions to people about how to refer to objects or a robot that implicitly aligns with the people's indicating behaviors. Even though our results showed that participants evaluated the implicit approach to be more natural than the explicit approach, the recognition performances of the two approaches were not significantly different.

In order to be believable, embodied conversational agents (ECAs) must show expression of emotions in a consistent and natural looking way across modalities. The ECA has to be able to display coordinated signs of emotion during realistic emotional behaviour. Such a capability requires one to study and represent emotions and coordination of modalities during non-basic realistic human behaviour, to define languages for representing such behaviours to be displayed by the ECA, to have access to mono-modal representations such as gesture repositories. This chapter is concerned about coordinating the generation of signs in multiple modalities in such an affective agent. Designers of an affective agent need to know how it should coordinate its facial expression, speech, gestures and other modalities in view of showing emotion. This synchronisation of modalities is a main feature of emotions.

The research on ambient assistive technology is concerned with features humanoid agents should show in order to gain user acceptance. However, differently aged groups may have different requirements. This paper is particularly focused on agent's voice preferences among elders, young adults, and adolescents. To this aim 316 users organized in groups of 45/46 subjects of which 3 groups of elders (65+ years old), 2 of young adults (aged between 22-35 years), and 2 of adolescents (aged between 14-16 years) were recruited and administered the Virtual Agent Acceptance Questionnaire (VAAQ), after watching video-clips of mute and speaking agents, in order to test their preferences in terms of willingness to interact, pragmatic and hedonic qualities, and attractiveness, of proposed speaking and mute agents. In addition, the elders were also tested on listening only the agent's. The results suggest that voice is primary for getting elder's acceptance of virtual humanoid agents in contrast to young adults and adolescents which accept equally well either mute or speaking agents.

In this paper, we present our humanoid robot Meka, participating in a multi party human robot dialogue scenario. Active arbitration of the robot's attention based on multi-modal stimuli is utilised to observe persons which are outside of the robots field of view. We investigate the impact of this attention management and addressee recognition on the robot's capability to distinguish utterances directed at it from communication between humans. Based on the results of a user study, we show that mutual gaze at the end of an utterance, as a means of yielding a turn, is a substantial cue for addressee recognition. Verification of a speaker through the detection of lip movements can be used to further increase precision. Furthermore, we show that even a rather simplistic fusion of gaze and lip movement cues allows a considerable enhancement in addressee estimation, and can be altered to adapt to the requirements of a particular scenario.

Because ever more powerful intelligent agents will interact with people in increasingly sophisticated and important ways, greater attention must be given to the technical and social aspects of how to make agents acceptable to people [87]. The technical challenge is to devise a computational structure that guarantees that from the technical standpoint all is under control. The social challenge is to ensure that agents and people interact gracefully and to provide reassurance to people that all is working according to plan. In this chapter, we outline our efforts to address some of these technical and social concerns through the use of a policy-based approach as implemented in the KAoS framework. From a technical perspective, we want to be able to help ensure the protection of agent state, the viability of agent communities, and the reliability of the resources on which they depend. To accomplish this, we must guarantee, insofar as is possible, that the autonomy of agents can always be bounded by explicit enforceable policy that can be continually adjusted to maximize the agents' effectiveness and safety in both human and computational environments. From a social perspective, we want agents to be designed to fit well with how people actually work together. Explicit policies governing human-agent interaction, based on careful observation of work practice and an understanding of current social science research, can help assure that effective and natural coordination, appropriate levels and modalities of feedback, and adequate predictability and responsiveness to human control are maintained. These factors are key to providing the reassurance and trust that are the prerequisites to the widespread acceptance of agent technology for nontrivial applications. 8 As a matter of practice, while systems should be designed to accommodate policy changes by an authorized person or trusted component of the policy management infrastructure at any time, we do not normally allow agents themselves the same privilege-certainly not, at least, the agent on whom the policy is being enforced. This is consistent with the main premise of David Billings' desiderata for human-centered systems [10] ("Humans are responsible for outcomes in human-machine systems") which implicitly assumes a fundamental asymmetry between humans and today's agents. Notwithstanding this assumption, we expect the broad balance between human and agent initiative and responsibility to co-evolve commensurate with the degree of trust humans are willing (or required) to exercise in particular kinds of technology for specific contexts of use. Already people rely routinely on technology to do things automatically for them that were unthinkable not too long ago.

This poster presents an ongoing study on affective humanrobot interaction. In our previous research, touch type is shown to be informative for communicated emotion. Here, a soft matrix array sensor is used to capture the tactile interaction between human and robot and 6 machine learning methods including CNN, RNN and C3D are implemented to classify different touch types, constituting a pre-stage to recognizing emotional tactile interaction. Results show an average recognition rate of 95% by C3D for classified touch types, which provide stable classification results for developing social touch technology.

Conversational AI agents are proliferating, embodying a range of devices such as smart speakers, smart displays, robots, cars, and more. We can envision a future where a personal conversational agent could migrate across different form factors and environments to always accompany and assist its user to support a far more continuous, personalized and collaborative experience. This opens the question of what properties of a conversational AI agent migrates across forms, and how it would impact user perception. To explore this, we developed a Migratable AI system where a user's information and/or the agent's identity can be preserved as it migrates across form factors to help its user with a task. We designed a 2x2 betweensubjects study to explore the effects of information migration and identity migration on user perceptions of trust, competence, likeability and social presence. Our results suggest that identity migration had a positive effect on trust, competence and social presence, while information migration had a positive effect on trust, competence and likeability. Overall, users report highest trust, competence, likeability and social presence towards the conversational agent when both identity and information were migrated across embodiments.