arXiv subjects

Julian Rasch

Publications and source records attributed to Julian Rasch.

16 recordsLinked to original sources

arXiv2025

Designing Intent Communication for Agent-Human Collaboration

As autonomous agents, from self-driving cars to virtual assistants, become increasingly present in everyday life, safe and effective collaboration depends on human understanding of agents' intentions. Current intent communication approaches are often rigid, agent-specific, and narrowly scoped, limiting their adaptability across tasks, environments, and user preferences. A key gap remains: existing models of what to communicate are rarely linked to systematic choices of how and when to communicate, preventing the development of generalizable, multi-modal strategies. In this paper, we introduce a multidimensional design space for intent communication structured along three dimensions: Transparency (what is communicated), Abstraction (when), and Modality (how). We apply this design space to three distinct human-agent collaboration scenarios: (a) bystander interaction, (b) cooperative tasks, and (c) shared control, demonstrating its capacity to generate adaptable, scalable, and cross-domain communication strategies. By bridging the gap between intent content and communication implementation, our design space provides a foundation for designing safer, more intuitive, and more transferable agent-human interactions.

cs.HC↗

arXiv2025

Through the Expert's Eyes: Exploring Asynchronous Expert Perspectives and Gaze Visualizations in XR

Transferring knowledge across generations is fundamental to human civilization, yet the challenge of passing on complex practical skills persists. Methods without a physically present instructor, such as videos, often fail to explain complex manual tasks, where spatial and social factors are critical. Technologies such as eXtended Reality and Artificial Intelligence hold the potential to retain expert knowledge and facilitate the creation of tailored, contextualized, and asynchronous explanations regardless of time and place. In contrast to videos, the learner's perspective can be different from the recorded perspective in XR. This paper investigates the impact of asynchronous first- and third-person perspectives and gaze visualizations on efficiency, feeling of embodiment, and connectedness during manual tasks. The empirical results of our study (N=36) show that the first-person perspective is better in quantitative measures and preferred by users. We identify best practices for presenting preserved knowledge and provide guidelines for designing future systems.

cs.HC↗

arXiv2025

Designing Intent: A Multimodal Framework for Human-Robot Cooperation in Industrial Workspaces

As robots enter collaborative workspaces, ensuring mutual understanding between human workers and robotic systems becomes a prerequisite for trust, safety, and efficiency. In this position paper, we draw on the cooperation scenario of the AIMotive project in which a human and a cobot jointly perform assembly tasks to argue for a structured approach to intent communication. Building on the Situation Awareness-based Agent Transparency (SAT) framework and the notion of task abstraction levels, we propose a multidimensional design space that maps intent content (SAT1, SAT3), planning horizon (operational to strategic), and modality (visual, auditory, haptic). We illustrate how this space can guide the design of multimodal communication strategies tailored to dynamic collaborative work contexts. With this paper, we lay the conceptual foundation for a future design toolkit aimed at supporting transparent human-robot interaction in the workplace. We highlight key open questions and design challenges, and propose a shared agenda for multimodal, adaptive, and trustworthy robotic collaboration in hybrid work environments.

cs.HC↗

arXiv2025

A Vision for AI-Driven Adaptation of Dynamic AR Content to Users and Environments

Augmented Reality (AR) is transforming the way we interact with virtual information in the physical world. By overlaying digital content in real-world environments, AR enables new forms of immersive and engaging experiences. However, existing AR systems often struggle to effectively manage the many interactive possibilities that AR presents. This vision paper speculates on AI-driven approaches for adaptive AR content placement, dynamically adjusting to user movement and environmental changes. By leveraging machine learning methods, such a system would intelligently manage content distribution between AR projections integrated into the external environment and fixed static content, enabling seamless UI layout and potentially reducing users' cognitive load. By exploring the possibilities of AI-driven dynamic AR content placement, we aim to envision new opportunities for innovation and improvement in various industries, from urban navigation and workplace productivity to immersive learning and beyond. This paper outlines a vision for the development of more intuitive, engaging, and effective AI-powered AR experiences.

cs.HC↗

arXiv2025

AR You on Track? Investigating Effects of Augmented Reality Anchoring on Dual-Task Performance While Walking

With the increasing spread of AR head-mounted displays suitable for everyday use, interaction with information becomes ubiquitous, even while walking. However, this requires constant shifts of our attention between walking and interacting with virtual information to fulfill both tasks adequately. Accordingly, we as a community need a thorough understanding of the mutual influences of walking and interacting with digital information to design safe yet effective interactions. Thus, we systematically investigate the effects of different AR anchors (hand, head, torso) and task difficulties on user experience and performance. We engage participants (n=26) in a dual-task paradigm involving a visual working memory task while walking. We assess the impact of dual-tasking on both virtual and walking performance, and subjective evaluations of mental and physical load. Our results show that head-anchored AR content least affected walking while allowing for fast and accurate virtual task interaction, while hand-anchored content increased reaction times and workload.

cs.HC↗

arXiv2025

CreepyCoCreator? Investigating AI Representation Modes for 3D Object Co-Creation in Virtual Reality

Generative AI in Virtual Reality offers the potential for collaborative object-building, yet challenges remain in aligning AI contributions with user expectations. In particular, users often struggle to understand and collaborate with AI when its actions are not transparently represented. This paper thus explores the co-creative object-building process through a Wizard-of-Oz study, focusing on how AI can effectively convey its intent to users during object customization in Virtual Reality. Inspired by human-to-human collaboration, we focus on three representation modes: the presence of an embodied avatar, whether the AI's contributions are visualized immediately or incrementally, and whether the areas modified are highlighted in advance. The findings provide insights into how these factors affect user perception and interaction with object-generating AI tools in Virtual Reality as well as satisfaction and ownership of the created objects. The results offer design implications for co-creative world-building systems, aiming to foster more effective and satisfying collaborations between humans and AI in Virtual Reality.

cs.HC↗

arXiv2024

Mind Mansion: Exploring Metaphorical Interactions to Engage with Negative Thoughts in Virtual Reality

Recurrent negative thoughts can significantly disrupt daily life and contribute to negative emotional states. Facing, confronting, and noticing such thoughts without support can be challenging. To provide a playful setting and leverage the technical maturation of Virtual Reality (VR), our VR experience, Mind Mansion, places the user in an initially cluttered virtual apartment. Here we utilize established concepts from traditional therapy and metaphors identified in prior works to let users engage metaphorically with representations of thoughts, gradually sorting the space, fostering awareness of thoughts, and supporting mental self-care. The results of our user study (n = 30) reveal that Mind Mansion encourages the exploration of alternative perspectives, fosters acceptance, and potentially offers new coping mechanisms. Our findings suggest that this VR intervention can reduce negative affect and improve overall emotional awareness.

cs.HC↗

arXiv2024

Just Undo It: Exploring Undo Mechanics in Multi-User Virtual Reality

With the proliferation of VR and a metaverse on the horizon, many multi-user activities are migrating to the VR world, calling for effective collaboration support. As one key feature, traditional collaborative systems provide users with undo mechanics to reverse errors and other unwanted changes. While undo has been extensively researched in this domain and is now considered industry standard, it is strikingly absent for VR systems in research and industry. This work addresses this research gap by exploring different undo techniques for basic object manipulation in different collaboration modes in VR. We conducted a study involving 32 participants organized in teams of two. Here, we studied users' performance and preferences in a tower stacking task, varying the available undo techniques and their mode of collaboration. The results suggest that users desire and use undo in VR and that the choice of the undo technique impacts users' performance and social connection.

cs.HC↗

arXiv2023

UndoPort: Exploring the Influence of Undo-Actions for Locomotion in Virtual Reality on the Efficiency, Spatial Understanding and User Experience

When we get lost in Virtual Reality (VR) or want to return to a previous location, we use the same methods of locomotion for the way back as for the way forward. This is time-consuming and requires additional physical orientation changes, increasing the risk of getting tangled in the headsets' cables. In this paper, we propose the use of undo actions to revert locomotion steps in VR. We explore eight different variations of undo actions as extensions of point\&teleport, based on the possibility to undo position and orientation changes together with two different visualizations of the undo step (discrete and continuous). We contribute the results of a controlled experiment with 24 participants investigating the efficiency and orientation of the undo techniques in a radial maze task. We found that the combination of position and orientation undo together with a discrete visualization resulted in the highest efficiency without increasing orientation errors.

cs.HC↗

arXiv2022

Supporting Electronics Learning through Augmented Reality

Understanding electronics is a critical area in the maker scene. Many of the makers' projects require electronics knowledge to connect microcontrollers with sensors and actuators. Yet, learning electronics is challenging, as internal component processes remain invisible, and students often fear personal harm or component damage. Augmented Reality (AR) applications are developed to support electronics learning and visualize complex processes. This paper reflects on related work around AR and electronics that characterize open research challenges around the four characteristics functionality, fidelity, feedback type, and interactivity.

cs.HC↗

arXiv2021

Knowledge State Networks for Effective Skill Assessment in Atomic Learning

The goal of this paper is to introduce a new framework for fast and effective knowledge state assessments in the context of personalized, skill-based online learning. We use knowledge state networks - specific neural networks trained on assessment data of previous learners - to predict the full knowledge state of other learners from only partial information about their skills. In combination with a matching assessment strategy for asking discriminative questions we demonstrate that our approach leads to a significant speed-up of the assessment process - in terms of the necessary number of assessment questions - in comparison to standard assessment designs. In practice, the presented methods enable personalized, skill-based online learning also for skill ontologies of very fine granularity without deteriorating the associated learning experience by a lengthy assessment process.

cs.LG↗

arXiv2020

Inexact First-Order Primal-Dual Algorithms

In this paper we investigate the convergence of a recently popular class of first-order primal-dual algorithms for saddle point problems under the presence of errors occurring in the proximal maps and gradients. We study several types of errors and show that, provided a sufficient decay of these errors, the same convergence rates as for the error-free algorithm can be established. More precisely, we prove the (optimal) $O(1/N)$ convergence to a saddle point in finite dimensions for the class of non-smooth problems considered in this paper, and prove a $O(1/N^2)$ or even linear $O(θ^N)$ convergence rate if either the primal or dual objective respectively both are strongly convex. Moreover we show that also under a slower decay of errors we can establish rates, however slower and directly depending on the decay of the errors. We demonstrate the performance and practical use of the algorithms on the example of nested algorithms and show how they can be used to split the global objective more efficiently.

math.OC↗

arXiv2018

Convergence rates and structure of solutions of inverse problems with imperfect forward models

The goal of this paper is to further develop an approach to inverse problems with imperfect forward operators that is based on partially ordered spaces. Studying the dual problem yields useful insights into the convergence of the regularised solutions and allow us to obtain convergence rates in terms of Bregman distances - as usual in inverse problems, under an additional assumption on the exact solution called the source condition. These results are obtained for general absolutely one-homogeneous functionals. In the special case of TV-based regularisation we also study the structure of regularised solutions and prove convergence of their level sets to those of an exact solution. Finally, using the developed theory, we adapt the concept of debiasing to inverse problems with imperfect operators and propose an approach to pointwise error estimation in TV-based regularisation.

math.NA↗

arXiv2017

Dynamic MRI Reconstruction from Undersampled Data with an Anatomical Prescan

The goal of dynamic magnetic resonance imaging (dynamic MRI) is to visualize tissue properties and their local changes over time that are traceable in the MR signal. We propose a new variational approach for the reconstruction of subsampled dynamic MR data, which combines smooth, temporal regularization with spatial total variation regularization. In particular, it furthermore uses the infimal convolution of two total variation Bregman distances to incorporate structural a-priori information from an anatomical MRI prescan into the reconstruction of the dynamic image sequence. The method promotes the reconstructed image sequence to have a high structural similarity to the anatomical prior, while still allowing for local intensity changes which are smooth in time. The approach is evaluated using artificial data simulating functional magnetic resonance imaging (fMRI), and experimental dynamic contrast-enhanced magnetic resonance data from small animal imaging using radial golden angle sampling of the k-space.

math.NA↗

arXiv2017

Joint Reconstruction via Coupled Bregman Iterations with Applications to PET-MR Imaging

Joint reconstruction has recently attracted a lot of attention, especially in the field of medical multi-modality imaging such as PET-MRI. Most of the developed methods rely on the comparison of image gradients, or more precisely their location, direction and magnitude, to make use of structural similarities between the images. A challenge and still an open issue for most of the methods is to handle images in entirely different scales, i.e. different magnitudes of gradients that cannot be dealt with by a global scaling of the data. We propose the use of generalized Bregman distances and infimal convolutions thereof with regard to the well-known total variation functional. The use of a total variation subgradient respectively the involved vector field rather than an image gradient naturally excludes the magnitudes of gradients, which in particular solves the scaling behavior. Additionally, the presented method features a weighting that allows to control the amount of interaction between channels. We give insights into the general behavior of the method, before we further tailor it to a particular application, namely PET-MRI joint reconstruction. To do so, we compute joint reconstruction results from blurry Poisson data for PET and undersampled Fourier data from MRI and show that we can gain a mutual benefit for both modalities. In particular, the results are superior to the respective separate reconstructions and other joint reconstruction methods.

math.NA↗

arXiv2016

Bias-Reduction in Variational Regularization

The aim of this paper is to introduce and study a two-step debiasing method for variational regularization. After solving the standard variational problem, the key idea is to add a consecutive debiasing step minimizing the data fidelity on an appropriate set, the so-called model manifold. The latter is defined by Bregman distances or infimal convolutions thereof, using the (uniquely defined) subgradient appearing in the optimality condition of the variational method. For particular settings, such as anisotropic $\ell^1$ and TV-type regularization, previously used debiasing techniques are shown to be special cases. The proposed approach is however easily applicable to a wider range of regularizations. The two-step debiasing is shown to be well-defined and to optimally reduce bias in a certain setting. In addition to visual and PSNR-based evaluations, different notions of bias and variance decompositions are investigated in numerical studies. The improvements offered by the proposed scheme are demonstrated and its performance is shown to be comparable to optimal results obtained with Bregman iterations.

math.NA↗