Alle Publikationen
2019
-
(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): Understanding of Human Behavior with a Robotic Agent Through Daily Activity Analysis. In: International Journal of Social Robotics 11 (3), S. 437-462. DOI: 10.1007/s12369-019-00513-2
DOI: https://doi.org/10.1007/s12369-019-00513-2 Abstract: Personal assistive robots to be realized in the near future should have the ability to seamlessly coexist with humans in unconstrained environments, with the robot’s capability to understand and interpret the human behavior during human–robot cohabitation significantly contributing towards this end. Still, the understanding of human behavior through a robot is a challenging task as it necessitates a comprehensive representation of the high-level structure of the human’s behavior from the robot’s low-level sensory input. The paper at hand tackles this problem by demonstrating a robotic agent capable of apprehending human daily activities through a method, the Interaction Unit analysis, that enables activities’ decomposition into a sequence of units, each one associated with a behavioral factor. The modelling of human behavior is addressed with a Dynamic Bayesian Network that operates on top of the Interaction Unit, offering quantification of the behavioral factors and the formulation of the human’s behavioral model. In addition, light-weight human action and object manipulation monitoring strategies have been developed, based on RGB-D and laser sensors, tailored for onboard robot operation. As a proof of concept, we used our robot to evaluate the ability of the method to differentiate among the examined human activities, as well as to assess the capability of behavior modeling of people with Mild Cognitive Impairment. Moreover, we deployed our robot in 12 real house environments with real users, showcasing the behavior understanding ability of our method in unconstrained realistic environments. The evaluation process revealed promising performance and demonstrated that human behavior can be automatically modeled through Interaction Unit analysis, directly from robotic agents.
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 2017
-
(2017): Social Scene Understanding: End-to-End Multi-Person Action Localization and Collective Activity Recognition. Online verfügbar unter http://arxiv.org/pdf/1611.09078v1
Abstract: We present a unified framework for understanding human social behaviors in raw image sequences. Our model jointly detects multiple individuals, infers their social actions, and estimates the collective actions with a single feed-forward pass through a neural network. We propose a single architecture that does not rely on external detection algorithms but rather is trained end-to-end to generate dense proposal maps that are refined via a novel inference scheme. The temporal consistency is handled via a person-level matching Recurrent Neural Network. The complete model takes as input a sequence of frames and outputs detections along with the estimates of individual actions and collective activities. We demonstrate state-of-the-art performance of our algorithm on multiple publicly available benchmarks.
-
Burgoon, Judee K.; Magnenat-Thalmann, Nadia; Pantic, Maja (Hg.) (2017): Social signal processing. Cambridge: Cambridge University Press
Abstract: Social Signal Processing is the first book to cover all aspects of the modeling, automated detection, analysis, and synthesis of nonverbal behavior in human-human and human-machine interactions. Authoritative surveys address conceptual foundations, machine analysis and synthesis of social signal processing, and applications. Foundational topics include affect perception and interpersonal coordination in communication; later chapters cover technologies for automatic detection and understanding such as computational paralinguistics and facial expression analysis and for the generation of artificial social signals such as social robots and artificial agents. The final section covers a broad spectrum of applications based on social signal processing in healthcare, deception detection, and digital cities, including detection of developmental diseases and analysis of small groups. Each chapter offers a basic introduction to its topic, accessible to students and other newcomers, and then outlines challenges and future perspectives for the benefit of experienced researchers and practitioners in the field.
Keywords: Computer vision, Computerwissenschaft, Disziplin, doppelter Treffer, Favoriten, Human behaviour analysis', Interaktion, Mensch-Technik-Relationen (MTR), Modelle/Theorien, Realtechnik, Sammelband, Signal, Signale, Signaling social preferences/ Social signal processing, Social interactions, social signal processing, Social Signal Processing (SSP), social signalling, Social signals, Soziale Angemessenheit, soziale Kognition, Soziosensitive Systeme, speech processing, Technik -
(2017): ‘What I see is not what you get’. Why culture-specific behaviours for virtual characters should be user-tested across cultures. In: AI & Society 32 (1), S. 37-49. DOI: 10.1007/s00146-014-0567-2
DOI: https://doi.org/10.1007/s00146-014-0567-2 Abstract: Abstract Integrating culture into the behavioural models of virtual characters requires knowledge from very different disciplines such as cross-cultural psychology and computer science. If culture-related behavioural differences are simulated with a virtual character system, users might not necessarily understand the intent of the designer. This is, in part, due to the influence of culture on not only users, but also designers. To gain a greater understanding of the instantiation of culture in the behaviour of virtual characters, and on this potential mismatch between designer and user, we have conducted two experiments. In these experiments, we tried to simulate one dimension of culture (Masculinity vs. Femininity) in the behaviour of virtual characters. We created four scenarios in the first experiment and six in the second. In each of these scenarios, the same two characters interact with each other. The verbal and non-verbal behaviour of these characters differs depending on their cultural scripts. In two user perception studies, we investigated how these differences are judged by human participants with different cultural backgrounds. Besides expected differences between participants from Masculine and Feminine countries, we found significant differences in perception between participants from Individualistic and Collectivistic countries. We also found that the user’s interpretation of the character’s motivation had a significant influence on the perception of the scenarios. Based on our findings, we giverecommendations for researchers that aim to design culture-specific behaviours for virtual characters.
Keywords: Agent-based Modelling, Behaviour modelling, Culture, Design, Disziplin, Evaluation, Favoriten, Interaktion, Kognitionswissenschaft/Social Sciences/Humanities, Kultur, Kultursensibilität, Kulturspezifizität, Kulturtheorie, Mensch-Technik-Relationen (MTR), Modell, Modelle/Theorien, Modellierung, Realtechnik, social importance dynamics, Soziosensitive Systeme, Technik, User testing, Virtual characters -
(2017): Sociality and Normativity for Robots. Philosophical Inquiries into Human-Robot Interactions. Cham: Springer International Publishing (Studies in the Philosophy of Sociality). Online verfügbar unter https://ebookcentral.proquest.com/lib/gbv/detail.action?docID=4867905
Abstract: This volume offers eleven philosophical investigations into our futurerelations with social robots--robots that are specially designed to engage andconnect with human beings.The contributors present cutting edge research thatexamines whether, and on which terms, robots can become members ofhuman societies. Can our relations to robots be said to be 'social'?Can robots enter into normative relationships with human beings? Howwill human social relations change when we interact with robots atwork and at home?The authors of this volume explore these questions from theperspective of philosophy, cognitive science, psychology, androbotics. The first three chapters offer a taxonomy for the classificationof simulated social interactions, investigate whether human socialinteractions with robots can be genuine, and discuss the significanceof social relations for the formation of human individuality.Subsequent chapters clarify whether robots could be said to actuallyfollow social norms, whether they could live up to the socialmeaning of care in caregiving professions, and how we will need toprogram robots so that they can negotiate the conventions of humansocial space and collaborate with humans. Can we perform jointactions with robots, where both sides need to honour commitments, andhow will such new commitments and practices change our regionalcultures?The authors connect research in social robotics andempirical studies in Human-Robot Interaction to recent debates insocial ontology, social cognition, as well as ethics and philosophy oftechnology.The book is a response to the challenge that social robotics presentsfor our traditional conceptions of social interaction, whichpresuppose such essential capacities as consciousness, intentionality,agency, and normative understanding. The authors develop insightfulanswers along new interdisciplinarypathways in 'robophilosophy,' a new research area that will help us toshape the 'robot revolution,' the distinctive technological change ofthe beginning 21st century. Raul Hakli (PhD) studied philosophy and computer science at theUniversity of Helsinki, Finland. He received his PhD in theoreticalphilosophy in 2010. While editing the book he was Associate Professorat the Aarhus University, Denmark. Currently he works as a researcherat the University of Helsinki, Finland. His research interests includesocial ontology, collective intentionality, epistemology, philosophyof social robotics, and philosophy of the social sciences. Johanna Seibt (PhD. at the Univ of Pittsburg, USA; Dr. phil. habil. atthe Univ of Konstanz, Germany) is Professor for Applied ProcessOntology and Integrative Social Robotics, Aarhus University, Denmark;previously she taught at the Univ of Texas at Austin, USA. Her mainresearch area is in analytical ontology and metaphysics. More recentlyshe works also in philosophy of social robotics. She is head of theResearch Unit for Robophilosophy at the School for Culture and Society, Aarhus University, which conducts interdisciplinaryHumanities research of and in social robotics and coordinates theinternational Research Network for Transdisciplinary Studies in SocialRobotics (TRANSOR).
-
(2017): Design and Evaluation of a Unique Social Perception System for Human–Robot Interaction. In: IEEE Transactions on Cognitive and Developmental Systems 9 (4), S. 341-355. DOI: 10.1109/TCDS.2016.2598423
Abstract: Robot's perception is essential for performing high-level tasks such as understanding, learning, and in general, human-robot interaction (HRI). For this reason, different perception systems have been proposed for different robotic platforms in order to detect high-level features such as facial expressions and body gestures. However, due to the variety of robotics software architectures and hardware platforms, these highly customized solutions are hardly interchangeable and adaptable to different HRI contexts. In addition, most of the developed systems have one issue in common: they detect features without awareness of the real-world contexts (e.g., detection of environmental sound assuming that it belongs to a person who is speaking, or treating a face printed on a sheet of paper as belonging to a real subject). This paper presents a novel social perception system (SPS) that has been designed to address the previous issues. SPS is an out-ofthe- box system that can be integrated into different robotic platforms irrespective of hardware and software specifications. SPS detects, tracks, and delivers in real-time to robots, a wide range of human-and environment-relevant features with the awareness of their real-world contexts. We tested SPS in a typical scenario of HRI for the following purposes: to demonstrate the system capability in detecting several high-level perceptual features as well as to test the system capability to be integrated into different robotics platforms. Results show the promising capability of the system in perceiving real world in different social robotics platforms, as tested in two humanoid robots, i.e., FACE and ZENO.
Keywords: Design, Disziplin, Fähigkeit, das Gesicht eines Menschen von einem Poster im Hintergrund zu unterscheiden, Fähigkeit, Hintergrundgeräusche von einer Stimme zu unterscheiden, Fähigkeit, menschliche Anwesenheit zu erkennen, Fähigkeit, Relevantes von Irrelevantem zu unterscheiden, Favoriten, Ingenieurswissenschaft, Intelligenz, Mensch oder Maschine, Mensch-Technik-Relationen (MTR), Realtechnik, Social Perception System (SPS), Sozial Intelligente Agenten, Soziale Robotik, Soziosensitive Systeme, Technik, Technische Modelle/Frameworks/Algorithmen 2016
-
(2016): Knowledge Transfer for Scene-specific Motion Prediction. Online verfügbar unter http://arxiv.org/pdf/1603.06987v2
Abstract: When given a single frame of the video, humans can not only interpret the content of the scene, but also they are able to forecast the near future. This ability is mostly driven by their rich prior knowledge about the visual world, both in terms of (i) the dynamics of moving agents, as well as (ii) the semantic of the scene. In this work we exploit the interplay between these two key elements to predict scene-specific motion patterns. First, we extract patch descriptors encoding the probability of moving to the adjacent patches, and the probability of being in that particular patch or changing behavior. Then, we introduce a Dynamic Bayesian Network which exploits this scene specific knowledge for trajectory prediction. Experimental results demonstrate that our method is able to accurately predict trajectories and transfer predictions to a novel scene characterized by similar elements.
-
(2016): Interactive Human Intention Reading by Learning Hierarchical Behavior Knowledge Networks for Human-Robot Interaction. In: ETRI Journal 38 (6), S. 1229-1239. DOI: 10.4218/etrij.16.0116.0106
Abstract: For efficient interaction between humans and robots, robots should be able to understand the meaning and intention of human behaviors as well as recognize them. This paper proposes an interactive human intention reading method in which a robot develops its own knowledge about the human intention for an object. A robot needs to understand different human behavior structures for different objects. To this end, this paper proposes a hierarchical behavior knowledge network that consists of behavior nodes and directional edges between them. In addition, a human intention reading algorithm that incorporates reinforcement learning is proposed to interactively learn the hierarchical behavior knowledge networks based on context information and human feedback through human behaviors. The effectiveness of the proposed method is demonstrated through play-based experiments between a human and a virtual teddy bear robot with two virtual objects. Experiments with multiple participants are also conducted.
-
(2016): Behavior Hierarchy-Based Affordance Map for Recognition of Human Intention and Its Application to Human–Robot Interaction. In: IEEE Transactions on Human-Machine Systems 46 (5), S. 708-722. DOI: 10.1109/THMS.2016.2558539
Abstract: To prepare for the anticipated age of human-robot symbiosis, robots should be able to interact and cooperate with humans effectively by understanding the meaning and intention of human behavior. In this paper, we define human intention as "desired behavior of the human using objects." To infer the defined human intention, a robot should learn the object affordance along with a behavior hierarchy structure. Thus, in this paper, we propose a behavior hierarchy-based affordance network (BHAN) and a behavior hierarchy-based affordance map (BHAM) to represent the object affordance, behavior hierarchy structure, and object hierarchy structure, simultaneously. Autonomous and interactive BHAN/BHAM learning algorithms are also proposed to make a robot develop the BHAN and BHAM by itself, as well as by interacting with a human. Based on the newly developed BHANs and BHAM, a robot could infer the human intention from information observed in context and from human behavior. The effectiveness of the proposed method was demonstrated through experiments on human-robot interaction with building blocks using a simulated differential wheel robot and a real human-sized humanoid robot.
-
(2016): DeeperCut. A Deeper, Stronger, and Faster Multi-Person Pose Estimation Model. Online verfügbar unter http://arxiv.org/pdf/1605.03170v3
Abstract: The goal of this paper is to advance the state-of-the-art of articulated pose estimation in scenes with multiple people. To that end we contribute on three fronts. We propose (1) improved body part detectors that generate effective bottom-up proposals for body parts; (2) novel image-conditioned pairwise terms that allow to assemble the proposals into a variable number of consistent body part configurations; and (3) an incremental optimization strategy that explores the search space more efficiently thus leading both to better performance and significant speed-up factors. Evaluation is done on two single-person and two multi-person pose estimation benchmarks. The proposed approach significantly outperforms best known multi-person pose estimation results while demonstrating competitive performance on the task of single person pose estimation. Models and code available at http://pose.mpi-inf.mpg.de
-
(2016): Anticipating Human Activities Using Object Affordances for Reactive Robotic Response. In: IEEE transactions on pattern analysis and machine intelligence 38 (1), S. 14-29. DOI: 10.1109/TPAMI.2015.2430335
DOI: http://www.ncbi.nlm.nih.gov/pubmed/26656575 Abstract: An important aspect of human perception is anticipation, which we use extensively in our day-to-day activities when interacting with other humans as well as with our surroundings. Anticipating which activities will a human do next (and how) can enable an assistive robot to plan ahead for reactive responses. Furthermore, anticipation can even improve the detection accuracy of past activities. The challenge, however, is two-fold: We need to capture the rich context for modeling the activities and object affordances, and we need to anticipate the distribution over a large space of future human activities. In this work, we represent each possible future using an anticipatory temporal conditional random field (ATCRF) that models the rich spatial-temporal relations through object affordances. We then consider each ATCRF as a particle and represent the distribution over the potential futures using a set of particles. In extensive evaluation on CAD-120 human activity RGB-D dataset, we first show that anticipation improves the state-of-the-art detection results. We then show that for new subjects (not seen in the training set), we obtain an activity anticipation accuracy (defined as whether one of top three predictions actually happened) of 84.1, 74.4 and 62.2 percent for an anticipation time of 1, 3 and 10 seconds respectively. Finally, we also show a robot using our algorithm for performing a few reactive responses.
Keywords: Affordance, affordances, Affordanz, Algorithms, Aniticipation, Human Activities, Humans, Imaging, Intentionserkennung (Roboter erkennt Menschenintention), J. J. Gibson's theory of affordance, machine learning, MODELS, Movement, PERCEPTION, Psychological, Robotics, Soziosensitive Systeme, Soziosensitivität, Statistical, Three-Dimensional, Video Recording -
(2016) : Learning Social Etiquette: Human Trajectory Understanding In Crowded Scenes In: Leibe, Frankie: Computer vision - ECCV 2016: 14th European Conference, Amsterdam, the Netherlands, October 11-14, 2016 : proceedings, 9912: Cham, Switzerland: Springer (LNCS sublibrary: SL6 - Image processing, computer vision, pattern recognition, and graphics), S. 549-565
DOI: https://doi.org/10.1007/978-3-319-46484-8_33 Abstract: Humans navigate crowded spaces such as a university campus by following common sense rules based on social etiquette. In this paper, we argue that in order to enable the design of new target tracking or trajectory forecasting methods that can take full advantage of these rules, we need to have access to better data in the first place. To that end, we contribute a new large-scale dataset that collects videos of various types of targets (not just pedestrians, but also bikers, skateboarders, cars, buses, golf carts) that navigate in a real world outdoor environment such as a university campus. Moreover, we introduce a new characterization that describes the “social sensitivity” at which two targets interact. We use this characterization to define “navigation styles” and improve both forecasting models and state-of-the-art multi-target tracking–whereby the learnt forecasting models help the data association step.
-
(2016): A context-aware approach in realization of socially intelligent industrial robots. In: Robotics and Computer-Integrated Manufacturing 37, S. 79-89. DOI: 10.1016/j.rcim.2015.07.002
Abstract: Contemporary industrial environments are usually constrained or limited in order to fit a fast, cheap and non-error prone production. Human-like system capabilities are not generally desirable there. But, recent trends in industrial robotics demand robust, flexible and efficient robots with a certain level of autonomy. Therefore, new and different approaches and perspectives in designing of industrial facilities are required. This paper reveals how a context-based reasoning can be used to achieve an intelligent robot group behavior. In order to achieve adaptivity, self-recovery or scalability of the system, a COgnitive MOdel for the Robot group control (COMOR) is developed. COMOR can be understood as an interpreter used to transform high-level context to low-level data, allowing machines to make context-based decisions. COMOR has three main parts and relies on a simulated Social Capital phenomenon as a feature of people. The first part is used to collect significant information from the environment. The second part is used to provide a set of possible solutions respecting the semantic domain description. The last part of COMOR is used to provide a behavioral component ensuring an optimal solution to given environmental conditions.
Keywords: adaptivity, Cognitive robotics, COMOR, COMOR / Social Capital, Context-awareness, Kognitionswissenschaft/Social Sciences/Humanities, Mensch-Technik-Relationen (MTR), Ontology, Probabilistic graphical models, Realtechnik, Sozial Intelligente Agenten, Soziale Robotik, Soziosensitive Systeme, Technik, Ubiquitous computing -
(2016): Accessible Robots for Improving Social Skills of Individuals with Autism. In: Journal of Artificial Intelligence and Soft Computing Research 6 (4). DOI: 10.1515/jaiscr-2016-0020
Abstract: This paper reports on an ongoing project between members of the computer science and special education departments of Bradley University and Murray State University, detailing the robotic platforms developed and investigated as a potential tool to improve social interactions among individuals with Autism Spectrum Disorders (ASD). Development of a fourth generation robotic agent is described, which uses economically available robotic platforms (Lego NXT) as Socially Assistive Robotics (SAR), combined with direct instruction pedagogy and social scripts to support an alternative educational approach to teaching social behavior. Specifically, in this fourth generation, changes to the physical design of the robots were made to improve the maintainability, reliability, maneuverability, and aesthetics of the robots. The software architecture was designed for modularity, configurability, and reusability of the software.
Keywords: Assitive technology, Autism, Autism spectrum disorder, Autism Spectrum Disorders (ASD), Interaktion, interdisziplinär, Mensch-Maschine-Kommunikation, Mensch-Technik-Relationen (MTR), Pathologie, Realtechnik, robot teacher, script, Serviceroboter, Social robotic, Social Skills, Socially Assistive Robotics (SAR), Soziale Robotik, Soziosensitive Systeme, teaching social behaviour, Technik, Telemanipulation, Telerobotics 2015
-
(2015): Deconstructing Ethnography. Towards a Social Methodology for Ubiquitous Computing and Interactive Systems Design. Cham: Springer (Human-Computer Interaction Series). Online verfügbar unter http://search.ebscohost.com/login.aspx?direct=true&scope=site&db=nlebk&AN=1081941
DOI: http://search.ebscohost.com/login.aspx?direct=true&scope=site&db=nlebk&AN=1081941 Abstract: In Deconstructing Ethnography the authors show how ‘new’ calls are returning systems design to ‘old’ and problematic ways of understanding the social. They argue that systems design can be appropriately grounded in the social through the ordinary methods that members use to order their actions and interactions. This work is written for post-graduate students and researchers alike, as well as design practitioners who have an interest in bringing the social to bear on design in a systematic rather than a piecemeal way. This is not a ‘how to’ book, but instead elaborates the foundations upon which the social can be systematically built into the design of ubiquitous and interactive systems
Keywords: Application software, Computer Science, Design, Design Thinking, Design(theorie), Design-Prozess, Disziplin, Ethnomethodologie, Ingenieurswissenschaft, Intellektualtechnik, Koordination, Mensch-Technik-Relationen (MTR), Realtechnik, social sciences, Soziale Angemessenheit, Soziologie, Soziosensitive Systeme, Technik, User interfaces (Computer systems), Voraussetzungen für sozial angemessenes Verhalten, Wissenschaftskritik -
(2015): Use of Scripted Role-Play in Evaluation of Multiple-User Multiple-Service Mobile Social and Pervasive Systems. In: International Journal of Mobile Human Computer Interaction 7 (4), S. 35-52. DOI: 10.4018/IJMHCI.2015100103
Abstract: Mobile and social computing is rapidly evolving towards a deeper integration with the physical world due to the proliferation of smart connected objects. It is widely acknowledged that involving end users in the design, development and evaluation of applications that function within the resulting complex socio-technical systems is crucial. However, reliable methods for managing evaluation of medium fidelity prototypes, whose utility is often dependent on rich data sets and/or the presence of multiple users simultaneously engaging in multiple activities, have not yet emerged. The authors report on the use of scripted role-play as an experimental approach applied in a mixed-methods evaluation of early prototypes of a suite of professional networking applications targeting a conference attendance scenario. Their evaluation was significantly constrained by the limited availability of a small cohort of end users for a relatively short period of time, which pose a challenge to define interactions that would ensure these users could experience and understand the novel application features. The authors observed that participatory role-play facilitated deeper user engagement with, exploration of, and discussion about, the mobile social applications than would have been possible with traditional usability approaches given the small user cohort and the time-constrained conditions.
Keywords: Beteiligung von Endnutzern, Communities, Computerwissenschaft, Human Factors, Im (wissenschaftlichen) Diskurs, Mensch-Technik-Relationen (MTR), Participatory Approaches, Pervasive Computing, Realtechnik, Reflexionen über MTR, scripted role-play, Social Computing, sociotechnical systems, Soziosensitive Systeme, Technik, Technikentwicklungsprozess, usability, User Evaluation -
(2015) : Building autonomous sensitive artificial listeners (Extended abstract): 2015 International Conference on Affective Computing and Intelligent Interaction (ACII 2015): Xi'an, China, 21 - 24 September 2015: Piscataway, NJ: IEEE, S. 456-462
Abstract: This paper describes a substantial effort to build a real-time interactive multimodal dialogue system with a focus on emotional and non-verbal interaction capabilities. The work is motivated by the aim to provide technology with competences in perceiving and producing the emotional and non-verbal behaviours required to sustain a conversational dialogue. We present the Sensitive Artificial Listener (SAL) scenario as a setting which seems particularly suited for the study of emotional and non-verbal behaviour, since it requires only very limited verbal understanding on the part of the machine. This scenario allows us to concentrate on non-verbal capabilities without having to address at the same time the challenges of spoken language understanding, task modeling etc. We first summarise three prototype versions of the SAL scenario, in which the behaviour of the Sensitive Artificial Listener characters was determined by a human operator. These prototypes served the purpose of verifying the effectiveness of the SAL scenario and allowed us to collect data required for building system components for analysing and synthesising the respective behaviours. We then describe the fully autonomous integrated real-time system we created, which combines incremental analysis of user behaviour, dialogue management, and synthesis of speaker and listener behaviour of a SAL character displayed as a virtual agent. We discuss principles that should underlie the evaluation of SAL-type systems. Since the system is designed for modularity and reuse, and since it is publicly available, the SAL system has potential as a joint research tool in the affective computing research community.
Keywords: deutsche Community, Emotionserkennung, Emotionssensitive Systeme, Favoriten, Interaktion, Künstliche Intelligenz, Mensch-Technik-Relationen (MTR), Nonverbal communication, Nonverbale Kommunikation, Realtechnik, Sensitive Artificial Listener, Sozial Intelligente Agenten, Soziale Robotik, Soziosensitive Systeme, Sprachverstehen, Technik, Virtual Agents SAL 2014
-
(2014): Romeo2 Project: Humanoid Robot Assistant and Companion for Everyday Life. I. Situation Assessment for Social Intelligence. In: Artificial Intelligence and Cognition, S. 140-147. Online verfügbar unter https://hal.archives-ouvertes.fr/hal-01096094
Abstract: For a socially intelligent robot, different levels of situation as-sessment are required, ranging from basic processing of sensor input tohigh-level analysis of semantics and intention. However, the attempt tocombine them all prompts new research challenges and the need of a co-herent framework and architecture.This paper presents the situation assessment aspect of Romeo2, a uniqueproject aiming to bring multi-modal and multi-layered perception on asingle system and targeting for a unified theoretical and functional frame-work for a robot companion for everyday life. It also discusses some of theinnovation potentials, which the combination of these various perceptionabilities adds into the robot’s socio-cognitive capabilities.
-
(2014): Implications of Robot Actions for Human Perception. How Do We Represent Actions of the Observed Robots?. In: International Journal of Social Robotics 6 (3), S. 357-366. DOI: 10.1007/s12369-014-0239-x
DOI: https://doi.org/10.1007/s12369-014-0239-x Abstract: Social robotics aims at developing robots that are to assist humans in their daily lives. To achieve this aim, robots must act in a comprehensible and intuitive manner for humans. That is, humans should be able to cognitively represent robot actions easily, in terms of action goals and means to achieve them. This yields a question of how actions are represented in general. Based on ideomotor theories (Greenwald Psychol Rev 77:73-99, 1970) and accounts postulating common code between action and perception (Hommel et al. Behav Brain Sci 24:849-878, 2001) as well as empirical evidence (Wykowska et al. J Exp Psychol 35:1755-1769, 2009), we argue that action and perception domains are tightly linked in the human brain. The aim of the present study was to examine if robot actions would be represented similarly, and in consequence, elicit similar perceptual effects, as representing human actions. Our results showed that indeed robot actions elicited perceptual effects of the same kind as human actions, arguing in favor of that humans are capable of representing robot actions in a similar manner as human actions. Future research will aim at examining how much these representations depend on physical properties of the robot actor and its behavior.
-
(2014): Designing and Evaluating a Social Gaze-Control System for a Humanoid Robot. In: IEEE Transactions on Human-Machine Systems 44 (2), S. 157-168. DOI: 10.1109/THMS.2014.2303083
Abstract: This paper describes a context-dependent social gaze-control system implemented as part of a humanoid social robot. The system enables the robot to direct its gaze at multiple humans who are interacting with each other and with the robot. The attention mechanism of the gaze-control system is based on features that have been proven to guide human attention: nonverbal and verbal cues, proxemics, the visual field of view, and the habituation effect. Our gaze-control system uses Kinect skeleton tracking together with speech recognition and SHORE-based facial expression recognition to implement the same features. As part of a pilot evaluation, we collected the gaze behavior of 11 participants in an eye-tracking study. We showed participants videos of two-person interactions and tracked their gaze behavior. A comparison of the human gaze behavior with the behavior of our gaze-control system running on the same videos shows that it replicated human gaze behavior 89% of the time.
2013
-
(2013) : Hey! There is someone at your door. A hearing robot using visual communication signals of hearing dogs to communicate intent: 2013 IEEE Symposium on Artificial Life (ALIFE): 16-19 April 2013, Singapore ; [part of the] 2013 IEEE Symposium Series on Computational Intelligence (SSCI): 2013 IEEE Symposium on Artificial Life (ALife): Singapore, Singapore: 4/16/2013 - 4/19/2013. Annual IEEE Computer Conference; IEEE Symposium on Artificial Life; Alife; IEEE Symposium Series on Computational Intelligence; Ssci: Piscataway, NJ: IEEE, S. 90-97
Abstract: This paper presents a study of the readability of dog-inspired visual communication signals in a human-robot interaction scenario. This study was motivated by specially trained hearing dogs which provide assistance to their deaf owners by using visual communication signals to lead them to the sound source. For our human-robot interaction scenario, a robot was used in place of a hearing dog to lead participants to two different sound sources. The robot was preprogrammed with dog-inspired behaviors, controlled by a wizard who directly implemented the dog behavioral strategy on the robot during the trial. By using dog-inspired visual communication signals as a means of communication, the robot was able to lead participants to the sound sources (the microwave door, the front door). Findings indicate that untrained participants could correctly interpret the robot's intentions. Head movements and gaze directions were important for communicating the robot's intention using visual communication signals.
-
(2013) : Feature-Based Prediction of Trajectories for Socially Compliant Navigation In: Roy, Nicholas; Newman, Paul; Srinivasa, Siddhartha (Hg.): Robotics: Science and systems VIII: Cambridge, Massachusetts: The MIT Press
DOI: https://doi.org/10.7551/mitpress/9816.003.0030 Abstract: Mobile robots that operate in a shared environmentwith humans need the ability to predict the movements ofpeople to better plan their navigation actions. In this paper, wepresent a novel approach to predict the movements of pedestrians.Our method reasons about entire trajectories that arise frominteractions between people in navigation tasks. It applies amaximum entropy learning method based on features that capturerelevant aspects of the trajectories to determine the probabilitydistribution that underlies human navigation behavior. Hence, ourapproach can be used by mobile robots to predict forthcominginteractions with pedestrians and thus react in a socially compliantway. In extensive experiments, we evaluate the capability andaccuracy of our approach and demonstrate that our algorithmoutperforms the popular social forces method, a state-of-the-artapproach. Furthermore, we show how our algorithm can be usedfor autonomous robot navigation using a real robot.
-
(2013) : Social Importance Dynamics. A Model for Culturally-Adaptive Agents In: Aylett, Ruth; Krenn, Brigitte; Pelachaud, Catherine; Shimodaira, Hiroshi (Hg.): Intelligent Virtual Agents: 13th International Conference IVA 2013 Proceedings: Berlin; Heidelberg: Springer, S. 325-338
DOI: https://doi.org/10.1007/978-3-642-40415-3_29 Abstract: The unwritten rules of human cultures greatly affect social behaviour and as such should be considered in the development of socially intelligent agents. So far, there has been a large focus on modeling cultural aspects related to non-verbal behaviour such as gaze or body posture. However, culture also dictates how we perceive and treat others from a relational perspective. Namely, what do we expect from others in different social situations and how much are we willing to do for others as well. In this article we present a culturally configurable model of such social dynamics. The aim is to facilitate the creation of agents with distinct cultural behaviour, which emerges from different parametrisations of the proposed model. The practical application of the model was tested in the development of an agent-based application for intercultural training, in which the model is responsible for driving the socio-cultural behaviour of the virtual agents.
Keywords: Adaptive Systeme, Disziplin, doppelter Treffer, Favoriten, Kultur, kulturadaptives System, Kulturspezifizität, Kulturtheorie, Mensch-Technik-Relationen (MTR), Modell, Modelle/Theorien, Modellierung, Realtechnik, social importance dynamics, Soziale Angemessenheit, Soziosensitive Systeme, soziosensitives System, Technik, Volltreffer