A5068893550- Social Robot Interaction and HRI
- Human Motion and Animation
- Speech and dialogue systems
- Artificial Intelligence in Games
- Virtual Reality Applications and Impacts
- Emotion and Mood Recognition
- Emotions and Moral Behavior
- AI in Service Interactions
- Digital Mental Health Interventions
- Human Pose and Action Recognition
- Robotics and Automated Systems
- Psychiatry, Mental Health, Neuroscience
- Mind wandering and attention
- Multi-Agent Systems and Negotiation
- Human-Automation Interaction and Safety
- Video Analysis and Summarization
- Hand Gesture Recognition Systems
- Consumer Retail Behavior Studies
- Personality Traits and Psychology
- Gaze Tracking and Assistive Technology
- Mental Health Research Topics
- Educational Games and Gamification
- Sentiment Analysis and Opinion Mining
- Data Visualization and Analytics
- Action Observation and Synchronization
German Research Centre for Artificial Intelligence
2015-2025
Deutsches Forschungsnetz
2016
Saarland University
2010
In this paper we introduce ALMA - A Layered Model of Affect. It integrates three major affective characteristics: emotions, moods and personality that cover short, medium, long term affect. The use model consists two phases: the preparation phase appraisal rules profiles for characters must be specified with help AffectML our XML based affect modeling language. runtime phase, are used to compute real-time emotions as results a subjective relevant input. computed characteristics represented...
Grounding is an important process that underlies all human interaction. Hence, it crucial for building social robots are expected to collaborate effectively with humans. Gaze behavior plays versatile roles in establishing, maintaining and repairing the common ground. Integrating these a computational dialog model complex task since gaze generally combined multiple parallel information modalities involved processes generation recognition of behavior. Going beyond related work, we present...
Expanding research on employment interview training, this study introduces virtual (VI) training with focus nonverbal behavior. In VI participants took part in a simulated character. Simultaneously, the computer analyzed participants’ behavior and provided real‐time feedback for it. The control group received parallel training. Following mock interviews, where interviewers rated behavior, performance. Analyses revealed (a) that of showed better performance, (b) effect was mediated by (c) has...
This paper presents an approach that makes use of a virtual character and social signal processing techniques to create immersive job interview simulation environment. In this environment, the plays role recruiter which reacts adapts user's behavior thanks component for automatic recognition cues (conscious or unconscious behavioral patterns). The pertinent interviews have been identified using knowledge elicitation study with real seekers. Finally, we present two user studies investigate...
This article presents the development of a socially interactive industrial robot. An Avatar is used to embody cobot for collaborative assembly tasks. The embodied covatar (cobot plus its avatar) introduced support Flow experiences through co-regulation, emotion regulation guidance. A real-time continuous emotional modeling method and an aligned transparent behavioral model, BASSF (Boredom, Anxiety, Self-efficacy, Self-compassion, Flow) developed. model anticipates co-regulates...
In this paper, we introduce a toolkit called SceneMaker for authoring scenes adaptive, interactive performances. These performances are based on automatically generated and pre-scripted which can be authored with the in two-step approach: step one, scene flow is defined using cascaded finite state machines. second step, content of each must provided. This done either manually by simple scripting language, or integrating at runtime domain dialogue model. Both types interweaved our plan-based,...
Job interviews come with a number of challenges, especially for young people who are out employment, education, or training (NEETs). This paper presents an approach to job simulation environment that employs two virtual characters and social cue recognition techniques create immersive interactive interview. The created different behavior profiles, understanding demanding, which consequently influ- ences the level difficulty as well impact on user. In this context we present user study...
The outcome of interpersonal interactions depends not only on the contents that we communicate verbally, but also nonverbal social signals. Because a lack skills is common problem for significant number people, serious games and other training environments have recently become focus research. In this work, present NovA ( No n v erbal behavior A nalyzer), system analyzes facilitates interpretation signals automatically in bidirectional interaction with conversational agent. It records data...
In this paper, we focus on experience-based role play with virtual agents to provide young adults at the risk of exclusion social skill training. We present a scenario-based serious game simulation platform. It comes signal interpretation component, scripted and autonomous agent dialog interaction behavior model, an engine for 3-D rendering lifelike in environment. show how two training systems developed basis platform can be used educate people showing appropriate socioemotive reactions job...
Artificial mediators are promising to support human group conversations but at present their abilities limited by insufficient progress in behaviour analysis. The MultiMediate challenge addresses, for the first time, two fundamental analysis tasks well-defined conditions: eye contact detection and next speaker prediction. For training evaluation, makes use of MPIIGroup Interaction dataset consisting 22 three- four-person discussions as well an unpublished test set six additional discussions....
Natural multimodal interaction with realistic virtual characters provides rich opportunities for entertainment and education. In this paper we present the current VIRTUALHUMAN demonstrator system. It a knowledge-based framework to create interactive applications in multi-user, multi-agent setting. The behavior of humans objects 3D environment is controlled by interacting affective conversational dialogue engines. An elaborate model adds natural emotional reactions presence humans. Actions...
This paper presents a study that examines whether social agents can elicit the emotion shame as humans do. For that, we use job interviews, which are highly evaluative situations per se. We vary interview style (shame-eliciting vs. neutral) and interviewer (human agent). Our dependent variables include observational data regarding signals of regulation well self-assessment questionnaires felt uneasiness discomfort in situation. results indicate to same amount humans. gives insights about...