Medical Assistance Systems

TRR 318 Research Presented at the “Eingeloggt!” Week at Wissenswerkstadt Bielefeld

Medical Assistance Systems — Thu, 16 Apr 2026 14:55:34 +0200

On March 16, Prof. Dr. Britta Wrede, head of the Medical Assistive Systems research group and principal investigator in the Collaborative Research Centre (TRR) 318 “Constructing Explainability”, contributed to the theme week “Eingeloggt!” at the Wissenswerkstadt Bielefeld.
Together with Prof. Dr. Katharina Rohlfing, psycholinguist at Paderborn University and spokesperson of TRR 318, she gave a talk titled “It Takes at Least Two to Explain – Why AI Needs You to Explain!”

The two researchers provided insights into current research on explainable AI. They demonstrated that successful explanations require an interplay between humans and machines. Their presentation was based on findings from Projects A01 “Adaptive Explaining” and A05 “Contextualized Scaffolding in Human–Robot Explanatory Dialogue.” They illustrated how explanations can be adapted to users and how robots can support learning through tailored assistance strategies that respond to individual needs.

The event was part of the digital theme week “Eingeloggt!”, which was primarily aimed at people over 50 and sought to facilitate access to digital technologies and AI through workshops and talks.

TRR 318 entered its second funding phase!

Medical Assistance Systems — Mon, 16 Mar 2026 13:52:29 +0100

With a kick-off event on March 3 at the CITEC building of Bielefeld University, the Collaborative Research Center / Transregio TRR 318 “Constructing Explainability” officially entered its second funding phase. The next phase of joint research was launched with presentations as well as several exchange formats for members and associates.

During the first funding phase, the researchers demonstrated that explanations are only effective when the perspective of those receiving the explanation is taken into account.
Building on these insights, the second funding phase will focus in particular on the context of explanations – including different situations, settings, individuals, and the shared knowledge that emerges through dialogue.

The aim of the upcoming research phase is to investigate how explanations need to adapt to these contextual conditions and how AI systems can respond to them. In the future, AI systems should be able to generate explanations more flexibly and continue the dialogue with users in a way that is appropriate to the situation.

More than 60 researchers from seven disciplines are involved in TRR 318 across a total of 20 subprojects.
The Medical Assistance Systems group participates in three of these projects: A03, A05, and WIKO.

Deep Dive into Multimodal HRI at SoRAIM 2026!

Medical Assistance Systems — Fri, 20 Feb 2026 15:01:42 +0100

Last week, Julian Leichert and Manuel Scheibl had the pleasure of attending the SoRAIM 2026 Winterschool in the beautiful snowy setting of Autrans, France.

It was an intensive week filled with insightful sessions on multimodality in Human-Robot Interaction (HRI). A particular highlight was the talk by Dr. Maribel Pino, who shared perspectives on the real-world applications and hurdles of deploying robotics in healthcare.

A huge thank you to Thomas Hueber and Xavier Alameda-Pineda for the seamless organization of this event!
We also want to give a special shoutout to Lorenzo Ferrini from PAL Robotics for an ambitious and hands-on workshop with the TIAGo Robot!

New article published in Frontiers in Robotics and AI

Medical Assistance Systems — Mon, 19 Jan 2026 13:01:38 +0100

We are delighted to announce that the article "Everything robots need to know about cooking actions: creating actionable knowledge graphs to support robotic meal preparation" has been published in “Frontiers in Robotics and AI”!

The article explores the extent to which an AI-supported knowledge graph is sufficient to enable a robot to understand online recipes. To this end, millions of recipes are analyzed and the cooking activities mentioned in them are clustered.

The work was carried out in collaboration with Bremen University and the Faculty of Technology at Bielefeld University.

M. Kümpel, M. Scheibl, J. Töberg, V. Hassouna, P. Cimiano, B. Wrede, M. Beetz, "Everything robots need to know about cooking actions: creating actionable knowledge graphs to support robotic meal preparation", Front. Robot. AI, Volume 12, 29th October 2025

Link to the article: https://www.frontiersin.org/journals/robotics-and-ai/articles/10.3389/frobt.2025.1682031/full

Two AG MAS Publications Featured in the New Frontiers eBook

Medical Assistance Systems — Wed, 17 Dec 2025 18:14:43 +0100

Two contributions from the MAS research group are included in the newly published Frontiers eBook on the Research Topic “Dialogue with Robots: Constructive Approaches for Understanding Communication.”

The following publications are featured:

RISE: An Open-Source Architecture for Interdisciplinary and Reproducible Human–Robot Interaction Research (A. Groß, C. Schütze, M. Brandt, B. Wrede, B. Richter)
→ Presentation of an open and reproducible architecture designed to support interdisciplinary HRI research.
Scaffolding the Human Partner by Contrastive Guidance in an Explanatory Human–Robot Dialogue (A. Groß, A. Singh, N. C. Banh, B. Richter, I. Scharlau, K. J. Rohlfing, B. Wrede)
→ Joint publication with collaboration partners from TRR 318 Project A05, investigating how contrastive cues can be used in explanatory human–robot dialogues to specifically support human understanding.

The complete eBook and all individual articles are now available online via the Frontiers website and the Research Topic homepage.

We are delighted about this double contribution and the visibility of our research in the field of explainable human–robot interaction.

Invited Talk by Claudia Weymann

Medical Assistance Systems — Wed, 17 Dec 2025 16:53:29 +0100

We had the pleasure of welcoming sociologist Claudia Weymann for an invited talk.

In her presentation, she shared insights into her research on disruptions in human–robot interaction, with a particular focus on social action and the importance of mutual perception—a topic that is central to the real-world deployment of social and assistive robotics. During the subsequent discussion, we identified numerous points of connection to the research questions and ongoing work of the MAS research group.

Thank you very much for the valuable input and the inspiring impulses!

Invited Talk at the Annual Cooperative Meeting of Freie Scholle: Britta Wrede on AI and Smart Homes

Medical Assistance Systems — Wed, 17 Dec 2025 15:46:51 +0100

At this year’s annual cooperative meeting of Freie Scholle, Prof. Dr. Britta Wrede was invited as a guest speaker.

In her talk, she provided an accessible overview of the current state of artificial intelligence in the smart home domain—ranging from new assistive systems and intelligent everyday support to future developments in human–technology interaction.

She was accompanied by Marian Heger, a doctoral researcher at CITEC (Center for Cognitive Interaction Technology), who contributed valuable insights from hands-on research and ongoing projects in the smart home field. Together, they demonstrated how AI-based technologies are already making everyday living easier and highlighted the potential of future innovations.

We would like to thank Freie Scholle for the invitation and for the engaging and successful exchange!

28–13.10.25: Visit by Prof. Dr. Matthias Rehm

Medical Assistance Systems — Wed, 26 Nov 2025 13:53:45 +0100

The Medical Assistance Systems research group at Bielefeld University welcomed Prof. Dr. Matthias Rehm from Aalborg University for a multi-day academic exchange. The visit focused on current developments in human–robot interaction and provided insights into the ongoing research activities of the group.

Prof. Dr. Rehm gave a talk titled “Interdisciplinary HRI Research at Aalborg University: From Social Practice to Responsible Robotics in (Health)Care.” Afterwards, the research group presented several projects, including a study system, a project on trust in robotic systems, current student research projects, and additional technical demonstrations.

André attended the ICDL 2025 in Prague from September 16 to 19.

Medical Assistance Systems — Thu, 20 Nov 2025 20:44:39 +0100

At the IEEE International Conference on Development and Learning (ICDL) 2025, he presented a model that enables the robot Nao to flexibly adapt its explanation strategies to the users behavior and presumed cognitive states. Using gaze data, Nao decides when negations—such as “don’t tilt, but shake”—are helpful. In a study, this adaptive communication reduced the error rate by 23%.

The code is available as open source.

Contributors: André Groß, Dr. Birte Richter, Prof. Dr. Britta Wrede Application in the context of medical tasks on a touchscreen

Julian at MAI-XAI/ECAI

Medical Assistance Systems — Mon, 17 Nov 2025 15:58:35 +0100

Julian Leichert presented the paper “Influence of Prior and Task-Generated Emotions on XAI Explanation Retention and Understanding” at the MAI-XAI Workshop (2nd Workshop on Multimodal, Affective and Interactive eXplainable Artificial Intelligence) and attended the ECAI Conference in Bologna (28th European Conference on Artificial Intelligence, October 25–30, 2025).

The workshop focuses on exploring innovative methods for making data and models explainable while addressing the challenges of real-world applications, particularly in the context of multimodal affective interaction. It emphasizes not only the development of new XAI (Explainable Artificial Intelligence) approaches but also the creation of open resources, corpora, and benchmark datasets. These resources are essential for training models, evaluating their explanations in real decision-making processes, and ultimately developing powerful AI systems that are both human-centered and environmentally conscious.

The paper investigates how pre-existing emotions and task-induced arousal influence the understanding and retention of explanations provided by an explainable decision support system (DSS). The findings show that emotions such as anxiety can impair comprehension—particularly when they coincide with arousal generated by the task itself.

Contributors: Birte Richter, Christian Schütze, Anna Aksonova, Julian Leichert und Britta Wrede

Britta Wrede showcased the focus area AI*IM at the EAMHID Congress 2025

Medical Assistance Systems — Mon, 17 Nov 2025 15:48:35 +0100

From September 18 to 20, 2025, the 15th Congress of the European Association for Mental Health in Intellectual Disability (EAMHID) took place in Ghent, Belgium. Prof. Britta Wrede, together with other researchers from the focus area AI*IM, participated with a solicited symposium – an excellent opportunity to present research on Inclusive Artificial Intelligence on an international stage.

The symposium, titled “Artificial Intelligence for Inclusive Medicine (AIIM): Innovations in Assistive Technology for People with Intellectual Disabilities”, brought together contributions from Antonia von Reden, Mareike Müller-Cleve, Britta Wrede, Rebecca Lätzsch, Peer Keller, Sarah Krieg, and Tanja Sappok. The focus was on innovative approaches showing how AI and digital assistive systems – such as eye tracking, augmented reality, or participatorily developed apps – can support and empower people with intellectual disabilities in their everyday lives, education, and healthcare.

The EAMHID Congress gathered international experts from research, practice, and policy, providing an inspiring platform for exchange on current developments in the field of mental health and disability. The AI*IM symposium offered important impulses for inclusive technological innovation and demonstrated how research, application, and real-life experience can be effectively connected.

Robot Nao as an Attentive Explainer

Medical Assistance Systems — Thu, 9 Oct 2025 12:52:02 +0200

How can a robot best support us linguistically in solving tasks?

Researchers from TRR 318 Constructing Explainability at Bielefeld University and Paderborn University have investigated this question. In subproject A05, they developed a model that enables the robot Nao to choose appropriate verbal explanation strategies depending on how the human has previously behaved and what cognitive state they are likely to be in.

You want to learn more about this project? Read the full article here!

Paper accepted at MAI-XAI 🎉

Medical Assistance Systems — Mon, 29 Sep 2025 15:36:28 +0200

We are excited to announce that our paper has been accepted at the MAI-XAI Conference!

In the paper we investigate how emotions influence the understanding of AI explanations. Our study shows: Pre-induced emotions such as joy or fear do not initially affect comprehension. However, when arousal occurs during the explanation – for example, through personally relevant content or perceived errors – understanding can be impaired.

The paper was carried out within Project A03 of the TRR 318 “Constructing Explainability” and thus contributes to a better understanding of socio-emotional factors in the use of explainable AI.

B. Richter, C. Schütze, A. Aksonova, J. Leichert, and B. Wrede (2025), “Influence of prior and task-generated emotions on XAI explanation retention and understanding”, Multimodal, Affective and Interactive eXplainable AI (MAI-XAI 2025)

Birte Richter at the MZEB Congress in Leipzig

Medical Assistance Systems — Mon, 29 Sep 2025 15:02:00 +0200

At this year’s MZEB Congress in Leipzig, held under the motto “Breaking down barriers – Strengthening participation”, Dr.-Ing. Birte Richter presented the projects IDWorkSupport and GAZE-AID.

Both projects focus on developing digital assistance systems that foster attention and support ADHD diagnostics in people with intellectual disabilities (ID). A key element is the agile and participatory development approach, which actively involves users in the process – perfectly reflecting the spirit of the congress.

Kick-off for X-DeePedMYO

Medical Assistance Systems — Mon, 22 Sep 2025 16:37:12 +0200

The new interdisciplinary research project X-DeePedMYO has been launched.

At the kick-off meeting on September 1st, participants included, among others, Atousa Amadi, Prof. Dr.-Ing. Britta Wrede and Dr.-Ing. Birte Richter. The project aims to improve the diagnosis of myocarditis in children using MRI images and Artificial Intelligence (AI). A particular focus is on integrating cardiac functional parameters and applying explainable AI (XAI) to ensure transparent and trustworthy diagnoses.

Manuel Scheibl at the RO-MAN 2025 conference

Medical Assistance Systems — Mon, 22 Sep 2025 15:44:02 +0200

Manuel Scheibl has been given the opportunity to present his paper, "Towards a cognitive architecture to enable natural language interaction in co-constructive task learning," at the RO-MAN 2025 conference.

The paper, which delves into the critical aspects of cognitive architectures for facilitating natural language interaction in human-robot collaboration, marks a step towards more intuitive and effective partnerships.

Successful ITL4HRI Workshop!

Medical Assistance Systems — Mon, 22 Sep 2025 15:40:11 +0200

In a significant step forward for collaborative robotics, the "Human-Robot Interaction for Co-Constructive Task Learning (ITL4HRI)" workshop at the RO-MAN 2025 conference in Eindhoven was a resounding success. The event brought together leading researchers to explore innovative methods for robots to learn and adapt alongside humans in real-time, paving the way for more intuitive and effective human-robot partnerships. The keynote speech by Prof. Dr. Stefan Kopp gave inspiring impulses for future research.

New Release: Edited Volume on Sociotechnical Transformations Featuring Contribution from Our Research Group

Medical Assistance Systems — Mon, 28 Jul 2025 16:02:57 +0200

The edited volume “Sociotechnical Transformations in Social and Healthcare Systems: Collaborative, Diverse, Barrier-Free, and Place-Based” was published in June!

Birte Richter, together with her collaboration partner Janna Landwehr, contributes a chapter on health promotion for children. They present their participatory cooperative project Mission Baumheide — a gamification app designed to foster health-related competencies in elementary school children living in a socially disadvantaged neighborhood. Their contribution is part of the volume’s special focus Brennglas 3: Reaching Target Groups and Overcoming Barriers.

About the volume: The focus is on needs- and demand-oriented, sustainable sociotechnical transformations in social and healthcare sectors. These transformations arise from new human-technology relationships that enable plural perspectives, critically reflect norms and values, and embrace diversity. Embedded in regional and social spatial networks, they rely on the participation of all relevant target groups to address societal challenges in a participatory and inclusive way.

Poster Presentation at HCI International 2025

Medical Assistance Systems — Mon, 28 Jul 2025 15:52:33 +0200

At the 27th International Conference on Human-Computer Interaction, Dennis Dübeler, student research assistant of the Medical Assistance Systems group, presented his short paper "Humans Follow AI-Advice by (Un-)Trustworthy Virtual Agents in Ethical Healthcare Decisions" as a poster.

The paper presents the results of a study conducted as part of Dennis Dübeler's bachelor's thesis: Disclosing the training data of AI advisors has no significant impact on how these advisors are perceived or on the extent to which they influence human decision-making—even when the AI agents appear untrustworthy. In particular, there are no significant differences in the perception of the different Floka agents (trustworthy, untrustworthy, neutral). The only factors influencing human decision-making are the perceived likability and intelligence of the agents (measured using the Godspeed questionnaire). These findings have important implications for the robustness of human-in-the-loop systems.

Dübeler, D., Schütze, C., Müller, A., Richter, B., Wrede, B. (2025). Humans Follow AI-Advice by (un-)trustworthy Virtual Agents in Ethical Healthcare Decisions. In: Stephanidis, C., Antona, M., Ntoa, S., Salvendy, G. (eds) HCI International 2025 Posters. HCII 2025. Communications in Computer and Information Science, vol 2529. Springer, Cham. https://doi.org/10.1007/978-3-031-94171-9_24

Paper on SHIFT Accepted at IEEE ICDL 2025

Medical Assistance Systems — Mon, 28 Jul 2025 15:40:32 +0200

We are very pleased to announce that our paper titled "SHIFT: An Interdisciplinary Framework for Scaffolding Human Attention and Understanding in Explanatory Tasks" has been accepted for presentation at the IEEE International Conference on Development and Learning (ICDL) 2025.

André Groß will present the paper at the conference, which will take place in Prague from September 16 to 19, 2025. In this work, we introduce the computational model SHIFT, which uses monitoring of the human interaction partner to determine the need for negation-based scaffolding explanations.

We look forward to valuable feedback and engaging discussions on site!

Successful Kickoff for New AI*IM Focus Area at Bielefeld University

Medical Assistance Systems — Mon, 28 Jul 2025 15:34:55 +0200

On May 9, 2025, the kickoff event for the new AI*IM focus area took place at Bielefeld University!

Researchers from a wide range of disciplines came together to present their projects and initiate the first steps toward interdisciplinary collaboration. Among the speakers were Britta Wrede from the Medical Assistance Systems group and Anna-Lisa Vollmer from the Interactive Robotics in Medicine and Care group.

The event marks the starting point for future cooperation within the focus area, which aims to set new standards in the development of human-centered AI through a strong connection between research and practice!

IDWorkSupport – What’s Next? Participatory Exchange at the proWerk Brokstraße Workshop

Medical Assistance Systems — Mon, 28 Jul 2025 15:20:18 +0200

In the research project IDWorkSupport, we are developing a digital system to support concentration in people with cognitive impairments. During a visit to the proWerk workshop Brokstraße, a key goal was in focus: to reflect together with all participants on the current status of the project – and how it can be developed further in a truly participatory way.

The meeting brought together four members of the university team (Britta Wrede, Monique Koke, Julian Leichert, Birte Richter), four representatives from the workshop management, seven employees who participated in the data collection in 2024, and a representative of the workshop council.

The first part of the meeting focused on building a shared knowledge base:

What happened with the collected data?
What initial insights have been gained?
How are the data used in research?

Based on this, an open and participatory discussion about the project’s future took place:

How is the system currently perceived?
What (technical) improvements do users wish for?
How should the project move forward?

The feedback from the employees provides valuable impulses for a practical, participatory further development of the system. We sincerely thank all participants for their trust, commitment, and active contribution to shaping the project.

Guest Lecture on AI in Medical Imaging by Dr.-Ing. Tamino Huxohl

Medical Assistance Systems — Mon, 28 Jul 2025 15:07:41 +0200

As part of the medical teaching module “Introduction to Technological Transformation in Medicine,” we had the pleasure of welcoming Dr.-Ing. Tamino Huxohl, Data Analyst at the Heart and Diabetes Center NRW, for a guest lecture. The focus of the talk was on current developments in medical imaging—particularly the use of artificial intelligence to analyze imaging techniques such as SPECT, CT, and MRI. Using concrete examples from clinical practice, Dr. Huxohl demonstrated how data-driven systems can support physicians in diagnosis and what opportunities arise from the intersection of computer science and medicine.

We are thankfull for the fascinating lecture and the inspiring discussion!

Funding for GAZE-AID: Technology-Based ADHD Diagnosis for Individuals with Intellectual Disabilities

Medical Assistance Systems — Wed, 16 Jul 2025 14:00:11 +0200

We are pleased to announce that the GAZE-AID research project is being funded by the Medical Research Seed Fund (AMF).

The aim of the project is to improve ADHD diagnosis in individuals with intellectual disabilities through the use of eye-tracking technology – objective, non-invasive, and independent of verbal abilities or third-party assessments. Traditional diagnostic methods often reach their limits within this target group. GAZE-AID seeks to address this with an innovative approach that enables reliable diagnoses, helps avoid overmedication, and ultimately improves the quality of life for those affected.

Project Lead: Dr.-Ing. Birte Richter

Cooperation Partner: Annika Gerdtommarkotten, University Clinic for Inclusive Medicine

Start: July 2025

Funded by: Medical Research Seed Fund (AMF)

Workshop at the RO-MAN Conference 2025

Medical Assistance Systems — Wed, 16 Jul 2025 13:55:47 +0200

For the first time, the “Workshop on Interactive Task Learning in Human-Robot Co-construction” will take place at the RO-MAN Conference 2025.

The workshop committee is composed of Michaela Kümpel and Michael Beetz (AICOR, University of Bremen), Omar Eldardeer and Alessandra Sciutti (IIT, Italy), as well as Manuel Scheibl and Britta Wrede (MAS, Bielefeld University). With a special focus on the possibilities and implementation of co-construction in task learning, the workshop offers an excellent platform for interdisciplinary exchange among researchers in the field of human-robot interaction.