Increasing encounters between people and autonomous service robots may lead to conflicts due to mismatches between human expectations and robot behaviour. This interactive online study (N = 335) investigated human-robot interactions at an elevator, focusing on the effect of communication and behavioural expectations on participants’ acceptance and compliance. Participants evaluated a humanoid delivery robot primed as either submissive or assertive. The robot either matched or violated these expectations by using a command or appeal to ask for priority and then entering either first or waiting for the next ride. The results highlight that robots are less accepted if they violate expectations by entering first or using a command. Interactions were more effective if participants expected an assertive robot which then asked politely for priority and entered first. The findings emphasize the importance of power expectations in human-robot conflicts for the robot’s evaluation and effectiveness in everyday situations.

Welfare technology has recently reached older adults in long-term care facilities (LTCFs).Many Swedish municipalities are introducing emerging technologies such as virtual reality, robotic assistive devices, and social robots in LTCFs as part of everyday care.However, not only older adults are affected by these deployments.Healthcare workers are left to master these technologiesand integrate them into existing care practices.Previous research has identified an increase in work-related stress associated with the introduction of technology for healthcare workers.The literature is, however, sparse on how healthcare workers in LTCFs are affected by the introduction.Therefore, we explored different factors that could affect healthcare workers' technostress through an online survey and semi-structured interviews to get a deeper understanding of how healthcare workers are experiencing deployments of welfare technology.The main findings showed that some of the healthcare workers are finding it difficult to adopt and use welfare technology due to, for example, older age, language difficulties, or a negative attitude toward technology.We conclude that municipalities and LTCFs need to invest in their healthcare workers in order to achieve better on-boarding and reduce technostress.

The rapid advancement of autonomous vehicle (AV) technology has opened up new possibilities and challenges in the domain of human–agent interaction. As AVs become increasingly prevalent on our roads, it is crucial to understand how humans perceive and interact with these intelligent systems. This workshop aims to bring together researchers and practitioners to explore the perception of cars as social agents. We explore the shift in user perception and the implications for interactions between autonomous vehicles, human drivers, and vulnerable road users (pedestrians, cyclists, etc.). Additionally, we investigate the communication of goals and intentions between cars and humans, as well as issues related to mixed agency, stakeholder perspectives, in-vehicle avatars, and human–vehicle power dynamics. The workshop aims to uncover the benefits, risks, and design principles associated with this emerging paradigm.

As automated shuttle buses gradually become a part of urban traffic solutions, their interactions with vulnerable road users need careful consideration. However, the cyclists’ perspectives on autonomous shuttle buses have not been explored extensively. This research addresses this gap by surveying 50 cyclists who regularly encounter automated shuttle buses. The results show that, in general, cyclists exhibit a high level of trust in the safety of the buses. Nevertheless, approximately one-third of the cyclists expressed disapproval as the buses tend to drive on the bicycle lane, leading them to wish for infrastructural solutions to avoid forcing cyclists to divert to pedestrian walkways. Identifying potential conflicts like these is vital for the development of effective and acceptable human-agent interactions in road traffic environments.

Prototyping methods are commonly employed iteratively throughout the design and product development, typically ranging from early low-fidelity to later high-fidelity prototypes. We present a case study focusing on prototyping a receptionist agent migrating between three platforms (a monitor on the wall, a mobile phone, and a physical robot). More specifically, we compare virtual reality (VR) and physical (real-world) prototyping methods. The two methods are compared in terms of fidelity and usability. The breadth of features, the degree of functionality, and the interactivity were similar. However, the aesthetic refinement differed. The VR prototyping method also had much higher prerequisites in terms of equipment and skills, and the learning curve for the designer was steep. Both methods were equally efficient in user testing, but the VR method revealed more usability issues in the efficiency category, while the physical space method revealed more issues in the effectiveness category.

Understanding how people attribute behavior to underlying mental states is crucial to the study of human social interactions. Previous research has established that people rely on attributing mental states to interpret and interact with artificial agents. For example, a pedestrian encountering a driverless vehicle at a crosswalk might view the vehicle as knowing (or not) that there is a pedestrian in front of it. Nevertheless, little attention has been devoted to investigating people’s attributions of higher-order mental states, i.e., mental states that are about the mental states of others (e.g., the vehicle’s beliefs about the pedestrian’s intentions). Addressing this research gap, the present study conducted a survey to explore people’s attributions and preferences concerning higher-order mental states in three types of artificial agents (AI chatbot, virtual assistant, and self-driving car), alongside two human agents (participants themselves, referred to as you, and five-year-old child).

A migrating receptionist is an intelligent virtual agent (IVA) designed to transfer from one embodiment to another. The embodiment can range from a virtual human-like form to a physical robot. We present a study of the prototyping and evaluation of a migrating virtual receptionist interface. One prototype was made in virtual reality (VR) and one in physical space. The study looks at how to design a migrating virtual receptionist for a department of computer science. The virtual receptionist was designed to migrate from a screen by the entrance, to a mobile phone used while walking, and then to a robot in the coffee area. The evaluation was conducted with 23 participants who interacted with the virtual receptionist using both prototypes. Data was collected with the System Usability Scale (SUS) and Microsoft Reaction Cards. Although the physical space and the virtual space were different, the results of the evaluation are similar. The SUS mean was 83.9 for the physical space and 78.3 for the virtual space. The reaction cards also showed more positive than negative reactions for both prototypes.

Much research in robotic artificial intelligence (AI) and Artificial Life has focused on autonomous agents as an embodied and situated approach to AI. Such systems are commonly viewed as overcoming many of the philosophical problems associated with traditional computationalist AI and cognitive science, such as the grounding problem (Harnad) or the lack of intentionality (Searle), because they have the physical and sensorimotor grounding that traditional AI was argued to lack. Robot lawn mowers and self-driving cars, for example, more or less reliably avoid obstacles, approach charging stations, and so on-and therefore might be considered to have some form of artificial intentionality or intentional directedness. It should be noted, though, that the fact that robots share physical environments with people does not necessarily mean that they are situated in the same perceptual and social world as humans. For people encountering socially interactive systems, such as social robots or automated vehicles, this poses the nontrivial challenge to interpret them as intentional agents to understand and anticipate their behavior but also to keep in mind that the intentionality of artificial bodies is fundamentally different from their natural counterparts. This requires, on one hand, a "suspension of disbelief " but, on the other hand, also a capacity for the "suspension of belief." This dual nature of (attributed) artificial intentionality has been addressed only rather superficially in embodied AI and social robotics research. It is therefore argued that Bourgine and Varela's notion of Artificial Life as the practice of autonomous systems needs to be complemented with a practice of socially interactive autonomous systems, guided by a better understanding of the differences between artificial and biological bodies and their implications in the context of social interactions between people and technology.

With more robots entering social environments, such as care homes for older adults, it is increasingly important to understand the target user groups’ perception of different robot platforms that are introduced into their immediate surroundings. To add to existing research on older adults’ attitudes toward robots after meeting a robot, and social acceptance toward certain robots, we conducted a short-term interaction study with the Furhat robot. Furhat, a blended embodiment of a physical robot head with a virtual (back-projected) face, is being marketed as one of the most social robots with high human-likeness. However, this study’s results indicates that older adults do not perceive Furhat as anthropomorphic or sentient, and they especially reported a negative attitude toward robots with emotions after meeting Furhat. Despite these scores, all participants were engaged in the interaction with the robot. However, our results differ from previous studies by indicating that older adults have relatively low social acceptance for Furhat and a relatively negative attitude toward robots after meeting Furhat.

The topic of mental state attribution to robots has been approached by researchers from a variety of disciplines, including psychology, neuroscience, computer science, and philosophy. As a consequence, the empirical studies that have been conducted so far exhibit considerable diversity in terms of how the phenomenon is described and how it is approached from a theoretical and methodological standpoint. This literature review addresses the need for a shared scientific understanding of mental state attribution to robots by systematically and comprehensively collating conceptions, methods, and findings from 155 empirical studies across multiple disciplines. The findings of the review include that: (1) the terminology used to describe mental state attribution to robots is diverse but largely homogenous in usage; (2) the tendency to attribute mental states to robots is determined by factors such as the age and motivation of the human as well as the behavior, appearance, and identity of the robot; (3) there is a computer < robot < human pattern in the tendency to attribute mental states that appears to be moderated by the presence of socially interactive behavior; (4) there are conflicting findings in the empirical literature that stem from different sources of evidence, including self-report and non-verbal behavioral or neurological data. The review contributes toward more cumulative research on the topic and opens up for a transdisciplinary discussion about the nature of the phenomenon and what types of research methods are appropriate for investigation.

During the past year with a pandemic, there have been many discussions of the use of robots in healthcare, and in particular the care of older adults. There are reports that COVID-19 drives adoption of robot technologies, and that health institutions are more positive to the use of robots due to the lower risk of virus spread, among other reasons. The media have contributed significantly to an increased interest in caring robots and from a societal perspective — given recent lockdowns, social distancing, etc. — an increase of robot usage in health care settings is not difficult to imagine. Older adults have in many countries been isolated, either at home or in care homes. This group, and especially individuals with dementia, were already vulnerable before the pandemic, living with an increased risk for loneliness and depression. For the last 10 years in Sweden, many actions have been taken to improve these people’s well-being and quality of life, including the use of social companion robots as psychological interventions. Given the increased isolation due to the pandemic, we wanted to investigate how the use of social companion robots has been affected in care homes during this time. We, therefore, interviewed nine health care staff members from seven different care homes for older adults in Sweden. The results summarised in this paper provides a real-world status report, one year after the outbreak, of how the pandemic has affected the usage of social companion robots in care homes.

introduction Open AccessIntroduction to the Special Issue on Explainable Robotic Systems Share on Authors: Maartje M. A. De Graaf Utrecht University Utrecht UniversityView Profile , Anca Dragan University of California, Berkeley University of California, BerkeleyView Profile , Bertram F. Malle Brown University Brown UniversityView Profile , Tom Ziemke Linkoping University Linkoping UniversityView Profile Authors Info & Claims ACM Transactions on Human-Robot InteractionVolume 10Issue 3July 2021 Article No.: 22pp 1–4https://doi.org/10.1145/3461597Online:11 July 2021Publication History 0citation320DownloadsMetricsTotal Citations0Total Downloads320Last 12 Months320Last 6 weeks80 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteView all FormatsPDF

The explainability of robotic systems depends on people’s ability to reliably attribute perceptual beliefs to robots, i.e., what robots know (or believe) about objects and events in the world based on their perception. However, the perceptual systems of robots are not necessarily well understood by the majority of people interacting with them. In this article, we explain why this is a significant, difficult, and unique problem in social robotics. The inability to judge what a robot knows (and does not know) about the physical environment it shares with people gives rise to a host of communicative and interactive issues, including difficulties to communicate about objects or adapt to events in the environment. The challenge faced by social robotics researchers or designers who want to facilitate appropriate attributions of perceptual beliefs to robots is to shape human–robot interactions so that people understand what robots know about objects and events in the environment. To meet this challenge, we argue, it is necessary to advance our knowledge of when and why people form incorrect or inadequate mental models of robots’ perceptual and cognitive mechanisms. We outline a general approach to studying this empirically and discuss potential solutions to the problem.

Several Wizard-of-Oz techniques have been developed to make robots appear autonomous and more social in human-robot interaction. Many of the existing solutions use control interfaces that introduce significant time delays and hamper the robot operator's ability to produce socially appropriate responses in real time interactions. We present work in progress on a novel wizard control interface designed to overcome these limitations:a motion tracking-based system which allows the wizard to act as if he or she is the robot. The wizard sees the other through the robot's perspective, and uses his or her own bodily movements to control it. We discuss potential applications and extensions of this system, and conclude by discussing possible methodological advantages and disadvantages.

In an explorative study concerning the social acceptance of two specific humanoid robots, the experimenter asked participants (N = 36) to place a book in an adjacent room. Upon entering the room, participants were confronted by a NAO or a Pepper robot expressing persistent opposition against the idea of placing the book in the room. On average, 72% of participants facing NAO complied with the robot's requests and returned the book to the experimenter. The corresponding figure for the Pepper robot was 50%, which shows that the two robot morphologies had a different effect on participants' social behavior. Furthermore, results from a post-study questionnaire (GODSPEED) indicated that participants perceived NAO as more likable, intelligent, safe and lifelike than Pepper. Moreover, participants used significantly more positive words and fewer negative words to describe NAO than Pepper in an open-ended interview. There was no statistically significant difference between conditions in participants' negative attitudes toward robots in general, as assessed using the NARS questionnaire.

The present workshop focuses on the topic of intention recognition in HRI. To be able to recognise intentions of other agents is a fundamental prerequisite to engage in, for instance, instrumental helping or mutual collaboration. It is a necessary aspect of natural interaction. In HRI, the problem is therefore bi-directional: not only does a robot need the ability to infer intentions of humans; humans also need to infer the intentions of the robot. From the human perspective, this inference draws both on the ability to attribute cognitive states to lifeless shapes, and the ability to understand actions of other agents through, for instance, embodied processes or internal simulations (i.e the human ability to form a theory of mind of other agents). How precisely, and to what degree these mechanisms are at work when interacting with social artificial agents remains unknown. From the robotic perspective, this lack of understanding of mechanisms underlying human intention recognition, or the capacity for theory of mind in general, is also challenging: the solution can, for instance, not simply be to make autonomous systems work “just like” humans by copying the biological solution and implementing some technological equivalent. It is therefore important to be clear about the theoretical framework(s) and inherent assumptions underlying technological implementations related to mutual intention. This remains very much an active research area in which further development is necessary. The core purpose of this workshop is thus to contribute to - and advance the state of the art in - this area.

We present a reinforcement learning algorithm based on Dyna-Sarsa that utilizes separate representations of reward and punishment when guiding state-action value learning and action selection. The adoption of policy meta-learning optimized by a genetic algorithm is explored and results in the context of a two-armed bandit goal-navigation task in a simple grid world are presented. The findings argue for an important role for a genetic algorithm approach for constructing the foundations of autonomous reinforcement learning agents.

The somatic marker hypothesis (SMH) posits that the role of emotions and mental states in decision-making manifests through bodily responses to stimuli of import to the organism's welfare. The Iowa Gambling Task (IGT), proposed by Bechara and Damasio in the mid-1990s, has provided the major source of empirical validation to the role of somatic markers in the service of flexible and cost-effective decision-making in humans. In recent years the IGT has been the subject of much criticism concerning: (1) whether measures of somatic markers reveal that they are important for decision-making as opposed to behaviour preparation; (2) the underlying neural substrate posited as critical to decision-making of the type relevant to the task; and (3) aspects of the methodological approach used, particularly on the canonical version of the task. In this paper, a cognitive robotics methodology is proposed to explore a dynamical systems approach as it applies to the neural computation of reward-based learning and issues concerning embodiment. This approach is particularly relevant in light of a strongly emerging alternative hypothesis to the SMH, the reversal learning hypothesis, which links, behaviourally and neurocomputationally, a number of more or less complex reward-based decision-making tasks, including the ‘A-not-B’ task – already subject to dynamical systems investigations with a focus on neural activation dynamics. It is also suggested that the cognitive robotics methodology may be used to extend systematically the IGT benchmark to more naturalised, but nevertheless controlled, settings that might better explore the extent to which the SMH, and somatic states per se, impact on complex decision-making.

The computational modelling of affective mechanisms – emotion and motivation in particular – has been an area of growing interest in adaptive behaviour, cognitive systems and robotics research in r...

Research on the neural bases of emotion raises much controversy and few quantitative models exist that can help address the issues raised. Here we replicate and dissect one of those models, Armony and colleagues’ neurocomputational model of fear conditioning, which is based on LeDoux's dual-route hypothesis regarding the rat fear circuitry. The importance of the model's modular abstraction of the neuroanatomy, its use of population coding, and in particular the interplay between thalamo-amygdala and thalamo-cortical pathways are tested. We show that a trivially minimal version of the model can produce conditioning to a reinforced stimulus without recourse to the dual pathway structure, but a modification of the original model, which nevertheless preserves the thalamo-amygdala and (reduced) thalamo-cortical pathways, enables stronger conditioning to a conditioned stimulus. Implications for neurocomputational modelling approaches are discussed.

According to Noë’s enactive theory of perception, sensorimotor knowledge allows us to predict the sensory outcomes of our actions. This paper suggests that tuning input filters with such predictions may be the cause of sustained inattentional blindness. Most models of learning capture statistically salient regularities in and between data streams. Such analysis is, however, severely limited by both the problem of marginal regularity and the credit assignment problem. A neurocomputational reservoir system can be used to alleviate these problems without training by enhancing the separability of regularities in input streams. However, as the regularities made separable vary with the state of the reservoir, feedback in the form of predictions of future sensory input can both enhance expected discriminations and hinder unanticipated ones. This renders the model blind to features not made separable in the regions of state space the reservoir is manipulated towards. This is demonstrated in a computational model of sustained inattentional blindness, leading to predictions about human behaviour that have yet to be tested.

The surveillance of large sea areas often generates huge amounts of multidimensional data. Exploring, analyzing and finding anomalous behavior within this data is a complex task. Confident decisions upon the abnormality of a particular vessel behavior require a certain level of situation awareness that may be difficult to achieve when the operator is overloaded by the available information. Based on a visual analytics process model, we present a novel system that supports the acquisition of situation awareness and the involvement of the user in the anomaly detection process using two layers of interactive visualizations. The system uses an interactive data mining module that supports the insertion of the user's knowledge and experience in the creation, validation and continuous update of the normal model of the environment.

The purpose of information fusion is to support and improve decision making. However, theories of decision making differ significantly on their view of what a good decision actually is. Hence, depending on which decision making theory one (un)consciously adopts there are different requirements for information fusion as decision support Information fusion researchers and practitioners should therefore be more explicit about their assumptions regarding decision making by carefully describing their theoretical frameworks. To illustrate this point the 'theory of sensemaking' by Karl Weick is presented as one example of a decision making theory. Major differences between decision making assumptions in that theory and assumptions common in much information fusion research are highlighted. Implications and challenges for information fusion are discussed.

The focus of most information fusion research, so far, has been on the technology, i.e. information processing techniques and algorithms. Consequently, there is a lack of research concerning the actual usage of information fusion systems in terms of cognitive and organisational issues such as supporting both individual and group decision making. This paper provides a retrospective of information fusion research so far and a future vision of information fusion systems as actual decision support systems. A methodology for developing decision support systems is suggested which could not only ensure the effectiveness of information fusion systems as decision support systems but also provide a natural user perspective and top-down approach to information fusion in general.

This paper focuses on the capability of artificial evolution to produce tool use behaviors of different complexity in simulated robotic agents and in the absence of learning or other lifetime methods. The results show by example that tool use behaviors of different complexity can evolve and do not necessarily rely on reasoning abilities

In this paper a mapping between retail concepts and the JDL model is proposed. More specifically, the benefits of using solutions to military problems as inspiration to retail specific problems are discussed. The somewhat surprising conclusion is that there are several similarities between the military and retail domains, and that these similarities potentially could be exploited. A few examples of retail problems that could benefit from theories and techniques commonly used in the information fusion community are given. All examples are taken from recently started or planned projects within the information fusion research program at the University of Skovde, Sweden

The focus of most information fusion research, so far, has been on the technology, i.e. information processing in machines. However, the importance of also understanding human information processing, and the interaction between humans and machines, is gaining increasing recognition. This position paper argues that a distributed cognition perspective, which considers cognitive processes not as taking place solely inside people's heads, but as distributed over human thought processes and the material, social and organizational environment they are embedded in, may help to provide a deeper understanding of information fusion processes

During the past two decades, embodiment has become an important concept in many areas of cognitive science, but so far there is no common understanding of what constitutes embodied cognition and what kind of body an artificial humanlike cognizer would require. Work in embodied artificial intelligence and robotics has addressed, to some degree, what kind of bodily implementation is necessary for embodied cognition, but crucial factors such as the role of social interaction and the ‘body-in-motion’ have still not received much attention. We argue that, in the human child, the interplay of social scaffolding and self-induced locomotion is fundamental to the development of joint attention and a ‘self’. Furthermore, we discuss the implications of the social dynamics of bodily experience for android science. We argue that keeping scientific and engineering perspectives apart, but also understanding their relation, is important for clarifying the objectives of android science.

This paper provides an overview of a collaborative research program in information fusion from databases, sensors and simulations. Information fusion entails the combination of data from multiple sources, to generate information that cannot be derived from the individual sources. This area is of strategic importance for industry and defense, as well as public administration areas such as health care, and needs to be pursued as an academic subject. A large number of industrial partners are supporting and participating in the development of the area. The paper describes the program’s general approach and main research areas, with a particular focus on the role of information fusion in systems development.

Many researchers in embodied cognitive science and artificial intelligence, and evolutionary robotics in particular, emphasize the interaction of brain, body and environment as crucial to the emergence of intelligent, adaptive behaviour. Accordingly, the interaction between agent and environment, as well as the co-adaptation of artificial brains and bodies, has been the focus of much research in evolutionary robotics. Hence, there are plenty of studies of robotic agents/species adapting to a given environment. Many animals, on the other hand, in particular humans, to some extent can choose to adapt the environment to their own needs instead of adapting (only) themselves. That alternative has been studied relatively little in robot experiments. This paper, therefore, presents some simple initial simulation experiments, in a delayed response task setting, that illustrate how the evolution of environment adaptation can serve to provide cognitive scaffolding that reduces the requirements for individual agents. Furthermore, theoretical implications, open questions and future research directions for evolutionary robotics are discussed.

In their introduction to the first International Workshop on Epigenetic Robotics, Zlatev and Balkenius (2001) suggested the term epigenetic robotics to denote a new field of research resulting from...

This letter shows how seemingly minor differences in training and evaluation procedures used in recent studies of recurrent neural networks as context free language predictors can lead to significant differences in apparent network performance. We suggest standard evaluation procedures whose use would facilitate better reproductibility and comparability.

The new wave of robotics aims to provide robots with the capacity to learn, develop and evolve in interaction with their environments using biologically inspired techniques. This work is placed in perspective by considering its biological and psychological basis with reference to some of the grand theorists of living systems. In particular, we examine what it means to have a body by outlining theories of the mechanisms of bodily integration in multicellular organisms and their means of solidarity with the environment. We consider the implications of not having a living body for current ideas on robot learning, evolution, and cognition and issue words of caution about wishful attributions that can smuggle more into observations of robot behaviour than is scientifically supportable. To round off the arguments we take an obligatory swipe at ungrounded artificial intelligence but quickly move on to assess physical grounding and embodiment in terms of the rooted cognition of the living.

This paper presents a novel approach to the segmentation and integration of (radar) images using a second-order recurrent artificial neural network architecture consisting of two sub-networks: a function network that classifies radar measurements into four different categories of objects in sea environments (water, oil spills, land and boats), and a context network that dynamically computes the function network's input weights. It is shown that in experiments (using simulated radar images) this mechanism outperforms conventional artificial neural networks since it allows the network to learn to solve the task through a dynamic adaptation of its classification function based on its internal state closely reflecting the current context.