Paula Friedrich, M.Sc.

Abstract: We present CECA, a configurable framework for embodied conversational AI agents in Unity-based extended reality (XR) applications. CECA employs a client–server architecture to decouple agent logic from game engine–based embodiment. Built on LiveKit Agents, our approach integrates speech-to-text (STT), large language models (LLMs), and text-to-speech (TTS) into a unified, streaming voice-to-voice pipeline configured via metadata rather than code changes. We outline how this architecture flexibly integrates local and cloud AI providers while mitigating limited provider SDK support in Unity. Finally, we highlight opportunities for future work, including multi-agent scenarios, higher-level templates for XR research, and systematic user studies.

Abstract: The global prevalence of mental health disorders has created a substantial treatment gap. To support clinicians and increase access to care, researchers in the field of Artificial Intelligence (AI) and Virtual Reality (VR) have investigated technology-mediated psychotherapy for years. However, research about stakeholders' concerns and their readiness to use AI in psychotherapy remains scarce. This study focuses on a user-centered approach to accommodate patients' concerns and, based on the results, implement measures to foster self-disclosure and trust towards an embodied AI therapist in VR. First, we conducted an online study with mental health patients ($N = 152$), which identified data autonomy and transparency as their primary ethical concerns. In a subsequent in-person VR study ($N = 90$) we compared effects of increased data autonomy and transparency on self-disclosure and trust towards an embodied AI therapist. Results indicated that higher data autonomy led to greater self-disclosure, while transparency had no significant effect. Manipulating data autonomy and transparency did not affect perceived trust, though exploratory calculations revealed that women reported significantly higher trust levels than men. These findings illuminate patients' priorities and provide implications for technical designs for AI-driven mental health care.

Abstract: The research group on four-dimensional research and communication of urban history (HistStadt4D) investigates and develops methods and technologies to transfer extensive repositories of historical photographs and their contextual information into a three-dimensional spatial model, with an additional temporal component. This will make content accessible to researchers and the public, via a 4D browser as well as a location-dependent augmented reality representation. Against this background, this article highlights users and requirements of both scholarly and touristic usage of digital information about urban history, in particular historical photographs.

Abstract: The availability of digital image repositories of historical photographs offers new possibilities to historians in their research. In addition to representing a large collection of data records themselves, image archives allow for new methods of research, from large-scale statistical analysis, to algorithmic generation of knowledge, such as historical 3D models, directly from these sources. In this paper, we explore methods to work with digital image libraries, from the creation of 3D or in extension time-annotated 4D models, to the eventual dissemination of research findings in teaching/learning scenarios. We review pedagogical approaches to reach different learning objectives, as well as methods that allow for the inclusion of historic city models employing Augmented Reality in mobile learning environments.

Abstract: Archives and museums store vast collections of historical images of urban areas and make them publicly available through online platforms. Many of these images, often containing historic buildings and landscapes, can be oriented spatially using automatic methods such as structure from motion (SfM). Providing spatially and temporally oriented images of urban architecture, in combination with advanced searching and 2D/3D exploration techniques, offers new potentials in supporting historians in their research. We are developing a 3D web environment usable to historians to spatially search online media repositories containing historic photographic images. We combine 3D models of historic buildings with spatially oriented images, replacing text-based searching through meta-data with spatial and temporal browsing with respect to given focus points in historic city models.