Alle Publikationen
- <<
- <
- 1
2018
-
(2018): Action Anticipation: Reading the Intentions of Humans and Robots. In: IEEE Robotics and Automation Letters 3 (4), S. 4132-4139. DOI: 10.1109/LRA.2018.2861569
DOI: https://doi.org/10.1109/LRA.2018.2861569 Abstract: Humans have the fascinating capacity of processing nonverbal visual cues to understand and anticipate the actions of other humans. This “intention reading” ability is underpinned by shared motor repertoires and action models, which we use to interpret the intentions of others as if they were our own. We investigate how different cues contribute to the legibility of human actions during interpersonal interactions. Our first contribution is a publicly available dataset with recordings of human body motion and eye gaze, acquired in an experimental scenario with an actor interacting with three subjects. From these data, we conducted a human study to analyze the importance of different nonverbal cues for action perception. As our second contribution, we used motion/gaze recordings to build a computational model describing the interaction between two persons. As a third contribution, we embedded this model in the controller of an iCub humanoid robot and conducted a second human study, in the same scenario with the robot as an actor, to validate the model's “intention reading” capability. Our results show that it is possible to model (nonverbal) signals exchanged by humans during interaction, and how to incorporate such a mechanism in robotic systems with the twin goal of being able to “read” human action intentionsand acting in a way that is legible by humans
Keywords: Blick / Gaze, Body Movement, EYE GAZE, Gaze, Gesichtserkennung, HRI, human-robot interaction, iCub, Intentionserkennung (Roboter erkennt Menschenintention), Körperbewegung, Körperhaltung, Körpersprache, Nichtverbale Kommunikation, nonverbal, Nonverbal behavior, non-verbal cues, Nonverbale Kommunikation, Soziosensitive Systeme 2016
-
(2016): Dear computer, teach me manners: Testing virtual employment interview training. In: International Journal of Selection and Assessment 24 (4), S. 312-323
Abstract: Introduced and evaluated virtual employment interview (VI) training with a focus on nonverbal behavior. In the present study, participants in the VI training group took part in a simulated interview with a virtual character. Simultaneously, the computer analyzed participants' nonverbal behavior and provided real-time feedback. A control group received parallel interview training. Following training, participants took part in mock interviews, where interviewers rated participants' nonverbal behavior, and interview performance. A total of 70 college students (mean age 24 years) participated. Measures included the Measurement of Anxiety in Selection Interviews (MASI). Results revealed (1) that participants of VI training showed better interview performance, (2) that this effect was mediated by nonverbal behavior, and (3) that VI training had a positive influence on interview anxiety. These results have important practical implications for applicants, career counseling centers, and organizations.
Keywords: Angst, Anxiety, Arbeits - und Organisationspsychologie, Berufliche Interessen, berufliche Laufbahn und Berufsberatung, Bewerbungsgespräche, Einzelstudie / spezifisch, Feedback, interpersonal communication, Interpersonale Kommunikation, interview anxiety, Job Applicant Interviews, Manieren, MASI, job interviews: virtual employment interview training, Nonverbal behavior, Kommunikation, Nonverbal communication, Nonverbale Kommunikation, Occupational Interests & Guidance, performance, Specialized Interventions, Spezielle Interventionen, Test Coaching, Testtraining, Training, Verhaltensforschung, Virtual Classrooms, Virtuelle Klassenzimmer, Wirtschaftspsychologie -
(2016) : Nonverbal Communication☆ In: Stein, John: Reference module in neuroscience and biobehavioral psychology: Place of publication not identified: Elsevier
Abstract: Nonverbal communication involves the interchange of information and influence through contextual arrangements, static physical features, and ongoing nonverbal behavior. Nonverbal communication usually operates automatically and outside of awareness and, consequently, is highly efficient. It is pervasive in face-to-face interactions and in various forms of mediated communication. Biology, culture, gender, personality, and the environment combine to shape stable patterns of nonverbal communication. The utility of nonverbal communication is reflected in a number of different social functions, including providing information, regulating interaction, expressing intimacy, exercising influence, and managing impressions.
-
(2016) : 13-year-olds approach human-robot interaction like adults: 2016 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob): Cergy-Pontoise/Paris, France: IEEE, S. 138-143
DOI: https://doi.org/10.1109/DEVLRN.2016.7846805 Abstract: Robots are at the evolution stage that will bring them to interact with humans in daily activities. This will lead to a direct contact with all the members of a household. It is important therefore to understand whether a robot behavior designed for adults could fit also the needs of their younger relatives. In particular, in this work we investigate whether the acceptance and basic understanding of robot behaviors changes between the onset of adolescence and adulthood. With a series of video-based tests we address three different aspects of the interaction: a) the a priori expectations of the prospective users on the most appropriate features of an interactive robot; b) their subjective preferences about a humanoid robot verbal and non-verbal behavior in a demonstration task; and c) the quantitative effect of robot gaze and hand motion on the ability of its human partner to understand its goal. The results show a remarkable similarity between teenagers and adults in all the subjective and quantitative metrics considered, suggesting that a robot behavior designed for adults would be probably effective also in the interaction with 13-year-olds. Our findings also underline the high relevance of an appropriate design of robot gaze direction, as both age groups relied substantially on this implicit cue in their understanding of robot goals.
Keywords: adolescence, adulthood, Angemessen(heit) (von Technik), demonstration task, goal anticipation, hand motion, Human voice, Humanoid Robot, Humanoid Robots, human-robot interaction, ieee xplore, implicit communication, interactive robot, motion control, Mouth, Nonverbal behavior, quantitative metrics, robot behavior, robot gaze direction, Robot kinematics, robot motion, Robot sensing systems, Social robotic, subjective metrics, video-based tests, Videos 2013
-
(2013): Socially Aware Virtual Characters: The Social Signal of Smiles [Social Sciences]. In: IEEE Signal Processing Magazine 30 (2), S. 128-132. DOI: 10.1109/MSP.2012.2230541
DOI: https://doi.org/10.1109/MSP.2012.2230541 Abstract: At first, machines were mainly used to solve complex mathematical problems. Today, they often embody more and more roles typically endowed by humans, such as a tutor in a virtual learning class or an assistant for virtual task realization. Moreover, the paradigm highlighted in [1] reveals that the user’s relation with the computer is intrinsically social, with high similarities compared to interpersonal relationships. For instance, people have no problem using communicative means (verbal and nonverbal behavior) to interact with artificial entities and apply polite rules. One particularly interesting aspect of the human machine interaction is the bidirectionality of the relation: users exhibit social behaviors to the computer, and the machine’s behavior affects users. Reeves and Nass [1] have shown that people tend to react naturally and socially to computers, as they would do to another person. In such a human-machine interaction, which can be seen as a particular social context with users sensitive to the computer behavior, the development of socially aware virtual characters appears fundamental.
Keywords: Context awareness, Heuristic algorithms, Human Factors, human machine interaction, ieee xplore, interpersonal relationship, Künstliche Intelligenz, Machine intelligence, Man machine systems, Nonverbal behavior, smile, Social Behavior, social sciences, social sciences computing, socially aware virtual character, user interfaces, user relation, Verbal Behavior, Virtual environments, virtual learning class, Virtual reality, virtual task realization 2012
-
(2012): Natural interaction with culturally adaptive virtual characters. In: Journal on Multimodal User Interfaces 6 (1-2), S. 39-47. DOI: 10.1007/s12193-011-0087-z
Abstract: Recently, the verbal and non-verbal behavior of virtual characters has become more and more sophisticated due to advances in behavior planning and rendering. Nevertheless, the appearance and behavior of these characters is in most cases based on the cultural background of their designers. Especially in combination with new natural interaction interfaces, there is the risk that characters developed for a particular culture might not find acceptance when being presented to another culture. A few attempts have been made to create characters that reflect a particular cultural background. However, interaction with these characters still remains an awkward experience in particular when it comes to non-verbal interaction. In many cases, human users either have to choose actions from a menu their avatar has to execute or they have to struggle with obtrusive interaction devices. In contrast, our paper combines an approach to the generation of culture-specific behaviors with full body avatar control based on the Kinect sensor. A first study revealed that users are able to easily control an avatar through their body movements and immediately adapt its behavior to the cultural background of the agents they interact with.
2006
-
(2006) : Could next generation androids get emotionally close? ‘Relational closeness’ from human dyadic interactions: ROMAN 2006 - The 15th IEEE International Symposium on Robot and Human Interactive Communication: ROMAN 2006 - The 15th IEEE International Symposium on Robot and Human: Hatfield, UK: IEEE, S. 475-479
DOI: https://doi.org/10.1109/ROMAN.2006.314373 Abstract: Studies of human-human interactions indicate that the relational dimensions encoded nonverbally between people include intimacy/involvement, status/control, and emotional valence. In assessing nonverbal behavior a key issue concerns the correct level or unit of behavior to code. Low-level codes, such as head nods, eyebrow flashes, and smiles, are concrete enough to be specified objectively. However, a coding scheme based on them may not match the phenomenology of lay people’s experiences of natural interactions. A high-level code, such as values intimacy, reliably distinguishes secure and insecure attachment styles but is underspecified at the concrete, bodily level. This paper considers what level of behavior codes may realistically be mapped onto next generation androids. New ’mid-level’ behavior codes are offered based on an experimental study of relational closeness in human dyadic interactions. These provide act specifications for a possible benchmark of relational closeness. The appropriateness of certain relational behaviors by androids is considered.
Keywords: Angemessen(heit) (von Technik), behavior codes, behavioural sciences, Biological system modeling, coding scheme, Concrete, Displays, emotional valence, Eyebrows, Human Computer Interaction, human dyadic interactions, Human Factors, Human robot interaction, human-human interactions, Humanoid Robots, ieee xplore, insecure attachment styles, next generation androids, Nonverbal behavior, Phenomenology, Prototypes, relational closeness, service robot, speech, values intimacy, Waste management
- <<
- <
- 1