Enabling artificial agents to be truly socially interactive and unobtrusive requires them to understand the social context of a situation. As a variety of different social context cues exist, both user studies and methods for context classification systems of agents are required to reliably categorize and recognise social contexts and respond appropriately and autonomously towards users. Compiling datasets from the real world can often be expensive, time-consuming and lack scalability. Thus, virtually simulated social contexts can be used to generate training data for context detection systems, but also stimuli material for user studies in a fast and cost-effective way. As a proof of concept, we introduce virtual social contexts and test their applicability for social context research with objective and subjective measurements. Therefore, we first implement virtual social contexts to compile our own dataset1. With subjective participant ratings, we evaluate the applicability of virtual social contexts as stimuli material for user studies. For this, we replicate a previous study with recordings of real social contexts using recordings of virtual social contexts instead. For our objective measurements, we use the computer vision models of YOLOv8 on object detection and pose estimation to train a classification model on our virtual image dataset and evaluate it on an image dataset of real social contexts. The results of the subjective and objective analyses indicate, that virtually generated social contexts can be used both for training classification systems and as stimuli material in user studies.

Positive contact with authorities can be an important pillar for our society, as it fosters trust and confidence in the legal and governmental systems, helping maintain social order and cooperation. Hence, for instance, the police engages in public relations efforts. However, due to staff shortages, this is only possible to a limited extent. Additionally, the representation of individuals with immigrant backgrounds within the police force is low. Nevertheless, for individuals with immigrant backgrounds, the ingroup effect can be particularly beneficial in facilitating pleasant personal interactions. To investigate the potential positive effect of a pleasant interaction with the police, and the impact of cultural similarity, on the perceived trust in the police, we implemented an interactive scenario containing either a prototypical German police officer, or one with a mixed-cultural background. In a user study with individuals of the same mixed-cultural background, we measured the trust in the police before and after the interaction. In addition, we assessed the perception of the agent in terms of similarity, warmth, competence, empathy, trust towards the agent, as well as the interaction with the agent in general. Our results reveal, that through interaction with a virtual police officer, indeed the trust in the police could be increased. However, we did not find the intended effect of ingroup similarity, showing no increased trust in the mixed-cultural condition compared to the German condition. We consider these results promising in regards to effectively being able to use virtual agents as a tool to provide positive personal interactions with authorities.

Social robots are finding their way into our society and must adapt to the social norms of everyday life. It is often unavoidable for robotic assistants to interrupt humans in their activities. These interruptions must therefore be designed in such a way that they have as little negative impact as possible on the ongoing activity and the perception of the robot. In this study, we investigate whether interruptions regarding health-promoting behavior delivered by a social robot in an office situation should be phrased politely rather than directly. A system was implemented to trigger either politely or directly phrased interruptions in a laboratory user study with participants executing an office task. We examined the perception of the robot, the task, and the interruption, as well as whether the health-promoting behavior was performed by the users. The results show that there were no significant differences in the perception of the robot and the interruptions, while the temporal demand of the task was perceived to be higher in the polite condition. In addition, the intention to follow the polite prompts was significantly higher, but there was no difference in the actual compliance with the prompts in the study itself. Index Terms—social robot, politeness, interruptions

Virtual environments (VEs) can be designed to evoke specific emotions for example by using colored light, not only applicable for games but also for virtual storytelling with a single storyteller. Social robots are perfectly suited as storytellers due to their multimodality. However, there is no research yet on the transferability of robotic storytelling to virtual reality (VR). In addition, the transfer of concepts from VE design such as adaptive room illumination to robotic storytelling has yet not been tested. Thus, we conducted a study comparing the same robotic storytelling with a physically embodied robotic storyteller and in VR to investigate the transferability of robotic storytelling to VR. As a second factor, we manipulated the room light following design guidelines for VEs or kept it constant. Results show that a virtual robotic storyteller is not perceived worse than a physically embodied storyteller, suggesting the applicability of virtual static robotic storytellers. Regarding emotion-driven lighting, no significant effect of colored lights on self-reported emotions was found, but adding colored light increased the social presence of the robot and its’ perceived competence in both VR and reality. As our study was limited by a static robotic storyteller not using bodily expressiveness future work is needed to investigate the interaction between well-researched robot modalities and the rather new modality of colored light based on our results.

The social context of a situation is crucial for people to decide how to behave and interact. For artificial agents to be truly socially interactive and unobtrusive it is equally important to understand the social context of a situation. Training these agents to reliably recognize social context is a difficult task, as big data sets of training data are required and a wide variety of different social context cues exist. In this contribution, we describe the creation of virtually simulated situations using virtual agents that demonstrate different social contexts. With this approach, we provide a fast and cost-effective way to create diverse and adaptable training data, by being able to generate video material of the virtual scenes. A suitable context detection system can then be used to support the classification of social context and decide upon, for example, whether a user is available for an interaction, or not. Further, these virtual social context situations can be also used for virtual reality studies to investigate how users react to interruptions in social contexts.

This paper introduces the Pepper Python Unity Toolkit (PePUT), a toolkit for controlling and using the social robot Pepper via Unity and Python. As toolkit components, we present implementations for the speech- and tablet-control, as well as animation and navigation, which can be directly used within Unity. With it, we provide the opportunity of a virtual testbed for the social robot Pepper. In addition, we highlight potential use cases for the components, in particular in a smart environment, as well as the use of PePUT as a research tool. The toolkit with the presented components and the source files are publicly available as open-source project1under the MIT license via GitLab for usage, replication, and extension.

This paper presents the implementation of a prototype including a virtual environment in which humans are exposed to a seemingly autonomous Intelligent Virtual Agent (IVA) that ostracises them by using its smartphone during a conversation (a phenomenon called phubbing with adverse outcomes in interhuman communication). Based on the temporal need threat model of ostracism, the effects of phubbing were examined in an online experiment with three conditions (no vs. proactive vs. reactive phubbing) using an IVA. The results showed a significant effect on the warmth attributed to the IVA. Consequently, our study provides partial support that the negative effects of phubbing can be transfered to human-agent interaction. It is thereby not only in line with the underlying theory, but also provides a prototype suitable for future research with phubbing in the context of IVAs.

This article introduces the accessory dock, a 3D printed multi-purpose extension for consumer-grade XR controllers that enables flexible mounting of self-made and commercial accessories. The uniform design of our concept opens new opportunities for XR systems being used for more diverse purposes, e.g., researchers and practitioners could use and compare arbitrary XR controllers within their experiments while ensuring access to buttons and battery housing. As a first example, we present a stylus tip accessory to build an XR Stylus, which can be directly used with frameworks for handwriting, sketching, and UI interaction on physically aligned virtual surfaces. For new XR controllers, we provide instructions on how to adjust the accessory dock to the controller’s form factor. A video tutorial for the construction and the source files for 3D printing are publicly available for reuse, replication, and extension (https://go.uniwue.de/hci-otss-accessory-dock).