Alle Publikationen
2019
-
(2019): Grund, Figur und Gleichgewichtsvorstellungen bei Gilbert Simondon. In: Gestalt Theory 41 (3), S. 293-317. DOI: 10.2478/gth-2019-0027
-
(2019) : An Exploratory Study on Proxemics Preferences of Humans in Accordance with Attributes of Service Robots: 2019 28th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN): 2019 28th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN): New Delhi, India: IEEE, S. 1-7
DOI: https://doi.org/10.1109/RO-MAN46459.2019.8956297 Abstract: Service robots that possess social interactive capabilities are vital to cater to the demand in emerging domains of robotic applications. A service robot frequently needs to interact with users when performing service tasks. The comfortability of users depends on the human-robot proxemics during these interactions. Hence, a service robot should be capable of maintaining proper proxemics that improves the comfort of users. The proxemics preferences of users might depend on diverse attributes of a robot, such as emotional state, noise level, and physical appearance. Therefore, it is vital to gain a better understanding of a robot's attributes which influence human-robot proxemics behavior. This paper contributes to an exploratory study to analyze the effects on human-robot proxemics preferences due to a robot's attributes; facial and vocal emotions, level of internal noises, and the physical appearance. Four sub-studies have been conducted to gather the required human-robot proxemics data. The gathered data have been analyzed through statistical tests. The test statistics reveal that facial and vocal emotions, internal noise level, and the physical appearance of a robot have significant effects on proxemics preferences of humans. The outcomes of this exploratory study would be useful in designing and developing human-robot proxemics strategies of a service robot that would enhance social interaction.
Keywords: emotion & social robotics, Human Factors, human-robot interaction, human-robot proxemics behavior, human-robot proxemics data, human-robot proxemics preferences, human-robot proxemics strategies, ieee xplore, Proxemics, robotic applications, service robot, service robotic, Social robotic, statistical testing, statistical tests -
(2019): Can We Keep Him Forever? Teens’ Engagement and Desire for Emotional Connection with a Social Robot. In: International Journal of Social Robotics 17 (1). DOI: 10.1007/s12369-019-00539-6
DOI: https://doi.org/10.1007/s12369-019-00539-6 Abstract: Today’s teens will most likely be the first generation to spend a lifetime living and interacting with both mechanical and social robots. Although human–robot interaction has been explored in children, adults, and seniors, examination of teen–robot interaction has been limited. In this paper, we provide evidence that teen–robot interaction is a unique area of inquiry and designing for teens is categorically different from other types of human–robot interaction. Using human-centered design, our team is developing a social robot to gather stress and mood data from teens in a public high school. To better understand teen–robot interaction, we conducted an interaction study in the wild to explore and capture teens’ interactions with a low-fidelity social robot prototype. Then, through group interviews we gathered data regarding their perceptions about social robots. Although we anticipated minimal engagement due to the low fidelity of our prototype, teens showed strong engagement and lengthy interactions. Additionally, teens expressed thoughtful articulations of how a social robot could be emotionally supportive. We conclude the paper by discussing future areas for consideration when designing for teen–robot interaction. (PsycINFO Database Record (c) 2019 APA, all rights reserved)
-
(2019): On Proactive, Transparent, and Verifiable Ethical Reasoning for Robots. In: Proceedings of the IEEE 107 (3), S. 541-561. DOI: 10.1109/JPROC.2019.2898267
DOI: https://doi.org/10.1109/JPROC.2019.2898267 Abstract: Previous work on ethical machine reasoning has largely been theoretical, and where such systems have been implemented, it has, in general, been only initial proofs of principle. Here, we address the question of desirable attributes for such systems to improve their real world utility, and how controllers with these attributes might be implemented. We propose that ethically critical machine reasoning should be proactive, transparent, and verifiable. We describe an architecture where the ethical reasoning is handled by a separate layer, augmenting a typical layered control architecture, ethically moderating the robot actions. It makes use of a simulation-based internal model and supports proactive, transparent, and verifiable ethical reasoning. To do so, the reasoning component of the ethical layer uses our Python-based belief-desire-intention (BDI) implementation. The declarative logic structure of BDI facilitates both transparency, through logging of the reasoning cycle, and formal verification methods. To prove the principles of our approach, we use a case study implementation to experimentally demonstrate its operation. Importantly, it is the first such robot controller where the ethical machine reasoning has been formally verified.
Keywords: BDI implementation, belief desire intention implementation, control engineering computing, Design methodology, ethical machine reasoning, ethical reasoning, Ethics, formal verification, ieee xplore, intelligent robots, layered control architecture, learning (artificial intelligence), machine learning, Moral & Ethik, Predictive models, Python, robot controller, robot programming, Robots, safety, simulation-based internal model, Social implications of technology, software architecture, transparency -
(2019): Large Scale GAN Training for High Fidelity Natural Image Synthesis. In: ICLR. Online verfügbar unter https://www.semanticscholar.org/paper/22aab110058ebbd198edb1f1e7b4f69fb13c0613Keywords: GAN
-
(2019): ARS: Eine technische Anwendung von psychoanalytischen Grundprinzipien für die Robotik und Automatisierungstechnik (UB Bielefeld - Katalog.plus!), S. 57-116. Online verfügbar unter https://katalogplus.ub.uni-bielefeld.de/cgi-bin/new_titel.cgi?katkey=0272574 pdx&query=technische%20anwendung%20von%20psychoanalytischen%20grundprinzipien%20f%C3%BCr%20die%20robotik%20und%20automatisierungstechnik&vr=1&pagesize=10&sprache=GER&bestand=ext&sess=9b28977aeae07f565aada251ca270e9d, zuletzt geprüft am 31.07.2019Keywords: Künstliche Intelligenz
-
(2019): Knowledge Representation for Culturally Competent Personal Robots: Requirements, Design Principles, Implementation, and Assessment. In: International Journal of Social Robotics 11 (3), S. 515-538. DOI: 10.1007/s12369-019-00519-w
-
(2019): Voraussetzungen, theoretische Grundlagen und methodische Zugänge der Erschließung und Beschreibung des Wissens über soziale Angemessenheit aus der Perspektive einer frame-theoretisch fundierten Wissensanalyse. Forschungsgutachten für poliTE
-
(2019) : Adaptive Sampling for Human-aware Path Planning in Dynamic Environments: 2019 IEEE International Conference on Robotics and Biomimetics (ROBIO): 2019 IEEE International Conference on Robotics and Biomimetics (ROBIO): Dali, China: IEEE, S. 1987-1994
DOI: https://doi.org/10.1109/ROBIO49542.2019.8961811 Abstract: Nowadays, robots are increasingly used in densely populated dynamic environments. Robots not only need to complete the navigation tasks quickly, but also need to take into account the human trajectories and the constraints of social rules. In order to avoid the robot going into the crowed areas and improve robot acceptance in the crowded public environment, we propose a human-aware motion planning algorithm that is based on sampling method. Firstly, human will be annoyed and stressed if robots disturb them during operation. To alleviate this uncomfort brought by the robot, we use probabilistic representations to build the Human Domain Zone (HDZ) of individual or crowd behaviors. Besides, we propose a sampling strategy that is capable of biasing the sampling in the area where human feel comfortable or crowd is sparse. Moreover, we put forward an evaluation function to select the optimum trajectory. This function can avoid robot falling into the crowded area through VDM which is used to model the relationship between human and robot. The proposed approach is verified with extensive experiments in simulated environments. The results show that our method has the promising performance in crowded environment. It can also generate a smooth path with higher success rate
-
(2019): A Personalized and Platform-Independent Behavior Control System for Social Robots in Therapy: Development and Applications. In: IEEE Transactions on Cognitive and Developmental Systems 11 (3), S. 334-346. DOI: 10.1109/TCDS.2018.2795343
DOI: https://doi.org/10.1109/TCDS.2018.2795343 Abstract: Social robots have been proven beneficial in different types of healthcare interventions. An ongoing trend is to develop (semi-)autonomous socially assistive robotic systems in healthcare context to improve the level of autonomy and reduce human workload. This paper presents a behavior control system for social robots in therapies with a focus on personalization and platform-independence. This system architecture provides the robot an ability to behave as a personable character, which behaviors are adapted to user profiles and responses during the human-robot interaction. Robot behaviors are designed at abstract levels and can be transferred to different social robot platforms. We adopt the component-based software engineering approach to implement our proposed architecture to allow for the replaceability and reusability of the developed components. We introduce three different experimental scenarios to validate the usability of our system. Results show that the system is potentially applicable to different therapies and social robots. With the component-based approach, the system can serve as a basic framework for researchers to customize and expand the system for their targeted healthcare applications.
-
(2019): An affordance and distance minimization based method for computing object orientations for robot human handovers. In: International Journal of Social Robotics, S. 143-162. DOI: 10.1007/s12369-019-00546-7
DOI: https://doi.org/10.1007/s12369-019-00546-7 Abstract: The ability to hand over objects to humans is an important skill for service robots. However, determining the proper object pose for handover is a challenging task. Our approach, based on observations of a set of natural human handovers, addresses three related challenges in teaching robots how to hand over objects: (1) how to compute mathematically an appropriate ‘standard’ or ‘mean’ handover orientation, (2) how to ascertain whether an observed set is of good or poor quality, and (3) using (1) and (2), how to compute an appropriate handover orientation from a set, in a manner that is robust to the quality of the set. We first compare three methods for computing mean orientations and show that our proposed distance minimization based method yields the best results. Next, we show that using the concept of affordance axes, we can evaluate the quality of a set of observed orientations. Finally, using affordance axes together with random sample consensus, we devise a method for computing an appropriate handover orientation from a set of observed natural handover orientations. User study data verified that our methods are successful in identifying both good and poor quality sets of handover orientations and in computing appropriate handover orientations from observed natural handover orientations. These results enable robots to automatically learn proper handover orientations for various objects. (PsycINFO Database Record (c) 2019 APA, all rights reserved)
-
(2019) : Equipping social robots with culturally-sensitive facial expressions of emotion using data-driven methods: 2019 14th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2019): 2019 14th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2019): Lille. France: IEEE, S. 1-8
DOI: https://doi.org/10.1109/FG.2019.8756570 Abstract: Social robots must be able to generate realistic and recognizable facial expressions to engage their human users. Many social robots are equipped with standardized facial expressions of emotion that are widely considered to be universally recognized across all cultures. However, mounting evidence shows that these facial expressions are not universally recognized - for example, they elicit significantly lower recognition accuracy in East Asian cultures than they do in Western cultures. Therefore, without culturally sensitive facial expressions, state-of-the-art social robots are restricted in their ability to engage a culturally diverse range of human users, which in turn limits their global marketability. To develop culturally sensitive facial expressions, novel data-driven methods are used to model the dynamic face movement patterns that convey basic emotions (e.g., happy, sad, anger) in a given culture using cultural perception. Here, we tested whether such dynamic facial expression models, derived in an East Asian culture and transferred to a popular social robot, improved the social signalling generation capabilities of the social robot with East Asian participants. Results showed that, compared to the social robot's existing set of facial `universal' expressions, the culturally-sensitive facial expression models are recognized with generally higher accuracy and judged as more human-like by East Asian participants. We also detail the specific dynamic face movements (Action Units) that are associated with high recognition accuracy and judgments of human-likeness, including those that further boost performance. Our results therefore demonstrate the utility of using data-driven methods that employ human cultural perception to derive culturally-sensitive facial expressions that improve the social face signal generation capabilities of social robots. We anticipate that these methods will continue to inform the design of social robots and broaden their usability and global marketability.
-
(2019): Culture as a Sensor? A Novel Perspective on Human Activity Recognition. In: International Journal of Social Robotics 11 (5), S. 797-814. DOI: 10.1007/s12369-019-00590-3
DOI: https://doi.org/10.1007/s12369-019-00590-3 Abstract: Human Activity Recognition (HAR) systems are devoted to identifying, amidst the sensory stream provided by one or more sensors located so that they can monitor the actions of a person, portions related to the execution of a number of a-priori defined activities of interest. Improving the performance of systems for Human Activity Recognition is a long-standing research goal: solutions include more accurate sensors, more sophisticated algorithms for the extraction and analysis of relevant information from the sensory data, and the enhancement of the sensory analysis with general or person-specific knowledge about the execution of the activities of interest. Following the latter trend, in this article we propose the association and enhancement of the sensory data analysis with cultural information, that can be seen as an estimate of person-specific information, relieved of the burden of a long/complex setup phase. We propose a culture-aware Human Activity Recognition system which associates the recognition response provided by a state-of-the-art, culture-unaware HAR system with culture-specific information about where and when activities are most likely performed in different cultures, encoded in an ontology. The merging of the cultural information with the culture-unaware responses is done by a Bayesian Network, whose probabilistic approach allows for avoiding stereotypical representations. Experiments performed offline and online, using images acquired by a mobile robot in an apartment, show that the culture-aware HAR system consistently outperforms the culture-unaware HAR system.
-
(2019) : Humans Socially Attune to Their “Follower” Robot: 2019 14th ACM/IEEE International Conference on Human-Robot Interaction (HRI): Daegu, Korea: IEEE, S. 538-539
-
(2019): Interactional Moral Systems: A Model of Social Mechanisms for the Moral Regulation of Exchange Processes in Agent Societies. In: IEEE Transactions on Computational Social Systems 6 (4), S. 778-796. DOI: 10.1109/TCSS.2019.2926950
DOI: https://doi.org/10.1109/TCSS.2019.2926950 Abstract: In this paper, we first introduce the concepts of moral agent and moral system of agent society and, in particular, the central concept of moral agent sensible to moral sanction. Next, we introduce the concepts of moral gain and moral loss in social exchanges and of reputation-based persistence of exchange processes. Following, we elaborate the notion of negotiated moral regulation of reputation-based persistent exchange processes. Finally, we combine those concepts in the notion of a reputation-based mechanism for the negotiation-driven moral regulation of exchange processes of agents that are sensible to moral sanctions.
Keywords: Agent societies, agent society, Avatars, Computational modeling, Ethics, ieee xplore, interactional moral systems, Law, Moral & Ethik, moral agent, moral gain, moral loss, moral regulation of social exchanges, moral sanction, Morality, multi-agent systems, negotiation-driven moral regulation, reputation-based mechanism, reputation-based persistence, reputation-based persistent exchange processes, Robots, social exchanges, social mechanisms, Social Processes -
(2019) : Robots in Need: Acquiring Assistance with Emotion: 2019 14th ACM/IEEE International Conference on Human-Robot Interaction (HRI): Daegu, Korea: IEEE, S. 706-708
DOI: https://doi.org/10.1109/HRI.2019.8673081 Abstract: There will always be occasions where robots require assistance from humans. Understanding what motivates people to help a robot, and what effect this interaction has on an individual will be essential in successfully integrating robots into our society. Emotions are important in motivating prosocial behavior between people, and therefore may also play a large role in human-robot interaction. This research explores the role of emotion in motivating people to help a robot and some of the ethical issues that arise as a result, with the ultimate aim of developing suitable methods for robots to interact with humans to acquire assistance.
-
(2019): Common knowledge, coordination, and strategic mentalizing in human social life. In: Proceedings of the National Academy of Sciences 116 (28), S. 13751-13758. DOI: 10.1073/pnas.1905518116
DOI: https://doi.org/10.1073/pnas.1905518116 Abstract: Humans are an unusually cooperative species, and our cooperation is of 2 kinds: altruistic, when actors benefit others at a cost to themselves, and mutualistic, when actors benefit themselves and others simultaneously. One major form of mutualism is coordination, in which actors align their choices for mutual benefit. Formal examples include meetings, division of labor, and legal and technological standards; informal examples include friendships, authority hierarchies, alliances, and exchange partnerships. Successful coordination is enabled by common knowledge: knowledge of others’ knowledge, knowledge of their knowledge of one’s knowledge, ad infinitum. Uncovering how people acquire and represent the common knowledge needed for coordination is thus essential to understanding human sociality, from large-scale institutions to everyday experiences of civility, hypocrisy, outrage, and taboo.
-
(2019) : A Layered Architecture for Socially Assistive Robotics as a Service: 2019 IEEE International Conference on Systems, Man and Cybernetics (SMC): 2019 IEEE International Conference on Systems, Man and Cybernetics (SMC): Bari, Italy: 10/6/2019 - 10/9/2019: [Piscataway, NJ]: IEEE, S. 352-357
Abstract: Socially assistive robotics technology is expected to play a crucial role in supporting home patients with neurological disorders. Nevertheless, the adoption of such technology in real home environments is still far to be reached since it presents several challenges mainly related to its acceptance in the everyday life. In this domain, a high degree of personalization is required usually obtained by a customization of a robotic system with respect to specific assistive tasks. On the contrary, socially assistive robots are usually general-purpose platforms requiring a considerable effort for customization. In this work, to limit static and costly customization of robotic systems, a service-oriented approach is adopted to represent and manage assistive tasks to be performed by a social robotic system, allowing to decouple a given functionality from its concrete implementation that can be provided by different devices and with different execution modalities. The service-oriented approach for robotics applications, known as Robot-as-a-Service, is becoming attractive for decoupling the robot hardware from the functionalities it provides.
-
(2019): Soziale Normen - Die Perspektive der Spieltheorie. Forschungsgutachten für poliTE
-
(2019): The Social Pragmatics of Communication with Social Robots: Effects of Robot Message Design Logic in a Regulative Context. In: International Journal of Social Robotics 25 (6). DOI: 10.1007/s12369-019-00538-7
DOI: https://doi.org/10.1007/s12369-019-00538-7 Abstract: When social robots are used in communicative contexts, the norms, values, and expectations associated with the process of communication itself are important considerations. Message design logics (MDL) are working models of communication that lead to distinct ways of thinking about communication situations and reasoning from goals to messages. The three MDLs are expressive, conventional, and rhetorical. Respectively, they treat communication as a vehicle for the transmission of information, a game to be played cooperatively according to social norms, and the creation and negotiation of social selves and situations. In human communication, there is an observed preference for partners and messages that display the most sophisticated rhetorical MDL. The purpose of this study was to test/extend the theory of MDL and communication pragmatics in HRI. An online between-subjects experiment of 511 U.S. American adults was conducted to determine the effects of a social robot’s MDL and goal structure on people’s evaluations of the message and its source in a hypothetical regulative context, or a situation in which one individual is faced with the need to control or correct the behavior of another. Results demonstrated that rhetorical message designs led to the most positive impressions of the robot in terms of predicted communication success, goal-relevant attributes (ability to motivate and provide face support), competence, credibility, and attractiveness. Findings mirror results in earlier studies of human communication establishing an MDL sophistication advantage in communication dilemmas. Analysis of qualitative responses showed that participants understood the robot’s overall communication pragmatic differently on the basis of the MDL it demonstrated. (PsycINFO Database Record (c) 2019 APA, all rights reserved)
-
(2019): Initial expectations, interactions, and beyond with social robots. In: Computers in Human Behavior 90, S. 308-314. DOI: 10.1016/j.chb.2018.08.042
DOI: https://doi.org/10.1016/j.chb.2018.08.042 Abstract: The current study builds upon our previous research on the human-to-human interaction script, which suggests that people expect to interact with other humans when encountering an initial interaction. This expectation impacts the initial impressions people have when interacting with social robots. The current experiment examined how short interactions might change those initial impressions. Participants were less uncertain and perceived greater social presence after a single brief interaction with a humanoid social robot. Social presence decreased after a short interaction with a human. These data suggest that initial impressions based on the human-to-human interaction script may impact actual interaction and the impressions that result from it. Open-ended responses suggest the potential for hyperpersonal communication in human-robot interaction. These findings are further discussed, as are limitations and directions for future research. The paper concludes with an agenda for applying constructivist interpersonal communication frameworks to human-robot interaction studies. (PsycINFO Database Record (c) 2018 APA, all rights reserved)
-
(2019): Evaluations of an artificial intelligence instructor's voice: Social Identity Theory in human-robot interactions. In: Computers in Human Behavior 90, S. 357-362. DOI: 10.1016/j.chb.2018.08.027
DOI: https://doi.org/10.1016/j.chb.2018.08.027 Abstract: This study employs the Computers are Social Actors (CASA) paradigm to extend the predictions of Social Identity Theory (SIT) to human-robot interaction (HRI) in the context of instructional communication. SIT posits that individuals gain a sense of personal worth from the groups with which they identify. Previous research has demonstrated that age group identification is meaningful to individuals’ self-concepts. Results demonstrated that higher age identified students rated the older A.I. voice instructor (representing an out-group member) higher for credibility and social presence and reported more motivation to learn than those students with low age identification. Implications are discussed for SIT and design features of computerized voices. (PsycINFO Database Record (c) 2018 APA, all rights reserved)
-
(2019): Understanding others: Emotion recognition in humans and other animals. In: Genes, brain, and behavior 18 (1). DOI: 10.1111/gbb.12544
DOI: https://doi.org/10.1111/gbb.12544 Abstract: Emotion recognition represents the ability to encode an ensemble of sensory stimuli providing information about the emotional state of another individual. This ability is not unique to humans. An increasing number of studies suggest that many aspects of higher order social functions, including emotion recognition, might be present in species ranging from primates to rodents, indicating a conserved role in social animals. The aim of this review is to examine and compare how emotions are communicated and perceived in humans and other animals, with the intent to highlight possible new behavioral approaches and research perspectives. We summarize the evidence from human emotion recognition, and latest advances in the development of nonhuman animal behavioral tests, using or implying the use of this cognitive function. The differential implication of sensory modalities used by animals to communicate and decipher emotional states is also discussed. The opportunity to measure emotion recognition abilities in rodents may allow us to better identify the neural mechanisms mediating this complex function, thus promoting the development of new intervention strategies for several neuropsychiatric disorders characterized by social cognitive dysfunctions.
-
(2019): Why Collaborative Robots Must Be Social (and even Emotional) Actors. In: Techné: Research in Philosophy and Technology 23 (3), S. 270-289. DOI: 10.5840/techne20191120104
-
(2019): The homunculus for proprioception: Toward learning the representation of a humanoid robot's joint space using self-organizing maps. In: Proceedings of the 2019 Joint IEEE 9th International Conference on Development and Learning and Epigenetic Robotics, S. 113-114. Online verfügbar unter https://arxiv.org/pdf/1909.02295
Abstract: In primate brains, tactile and proprioceptive inputs are relayed to the somatosensory cortex which is known for somatotopic representations, or, "homunculi". Our research centers on understanding the mechanisms of the formation of these and more higher-level body representations (body schema) by using humanoid robots and neural networks to construct models. We specifically focus on how spatial representation of the body may be learned from somatosensory information in self-touch configurations. In this work, we target the representation of proprioceptive inputs, which we take to be joint angles in the robot. The inputs collected in different body postures serve as inputs to a Self-Organizing Map (SOM) with a 2D lattice on the output. With unrestricted, all-to-all connections, the map is not capable of representing the input space while preserving the topological relationships, because the intrinsic dimensionality of the body posture space is too large. Hence, we use a method we developed previously for tactile inputs (Hoffmann, Straka et al. 2018) called MRF-SOM, where the Maximum Receptive Field of output neurons is restricted so they only learn to represent specific parts of the input space. This is in line with the receptive fields of neurons in somatosensory areas representing proprioception that often respond to combination of few joints (e.g. wrist and elbow).
Keywords: Neurons and Cognition (q-bio.NC), Robotics (cs.RO)