Summary

The goal of the doctoral program is to improve the autonomy and participation of persons with special needs through the use of assistance systems based on artificial intelligence (AI). Three topics will be addressed in the doctoral program: (i) AI-based methods for text, audio, and multimedia document processing, (ii) AI methods for interactive training and assistance systems, and (iii) investigation of the consequences and ethical, legal, social, and societal implications of AI systems for people with disabilities

The following research projects are running:

I) AI-based methods for text, audio and multimedia document processing

II) AI methods for interactive training and assistance systems

III) investigation of the consequences and ethical, legal, social, and societal implications of AI systems for people with disabilities

Publications

  • Beyerlein, M., Herzog, M., Stetter, B., & Stein, T. (2025, July). Structure of perturbation-based balance training affects coordination of trip perturbations. In Proceedings of the International Society of Bio-mechanics (ISB).
  • Chen, Y., Liu, R., Zheng, J., Wen, D., Peng, K., Zhang, J., & Stiefelhagen, R. (2025, April). GraphDoc: A graph-based document structure analysis. In International Conference on Learning Representations (ICLR).
  • Lee, P. S., & Mombaur, K. (2025). Investigating the human adaptation behaviour to active ankle exoskeleton use: Kinematics and energetics perspective. In J. L. Pons, J. Tornero, & M. Akay (Eds.), Converging clinical and engineering research on neurorehabilitation V. ICNR 2024 (Vol. 31, pp. [page numbers if known]). Springer. https://doi.org/10.1007/978-3-031-77588-8_46
  • Liu, Y., & Waibel, A. (2025). Factorized-VITS: Decoupling prosody and text in end-to-end speech synthesis without external or secondary aligner. In ICASSP 2025 – 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 1–5). IEEE. https://doi.org/10.1109/ICASSP49660.2025.10890003
  • Moeller, T., Beyerlein, M., Herzog, M., Barisch-Fritz, B., Marquardt, C., Dežman, M., Mombaur, K., Asfour, T., Woll, A., Stein, T., & Krell-Rösch, J. (2025). Human motor performance assessment with lower limb exoskeletons as a potential strategy to support healthy aging—A perspective article. Progress in Biomedical Engineering, 7(1), 013001. https://doi.org/10.1088/2516-1091/ada333
  • Moeller, T., Krell-Röesch, J., Gerhards, S., Huttunen-Lenz, M., Bruno, B., Weinberger, N., Krings, B.-J., Maia, M., Woll, A., & Barisch-Fritz, B. (2025). Von Disziplinär zu Interdisziplinär: Vier Perspektiven auf Bewegungsförderung in Pflegeeinrichtungen mit digitalen Technologien – theoretische Betrachtung und Empfehlungen für die Forschungspraxis. Pflege und Gesellschaft, 30(3). (Title translation not required in APA, but you've included it nicely for context.)
  • Zheng, J., Liu, R., Chen, Y., Chen, Z., Yang, K., Zhang, J., & Stiefelhagen, R. (2025). Scene-agnostic pose regression for visual localization. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
  • Anderer, K., Reich, A., & Wölfel, M. (2024). MaViLS, a benchmark dataset for video-to-slide alignment, assessing baseline accuracy with a multimodal alignment algorithm leveraging speech, OCR, and visual features. In Proceedings of Interspeech 2024 (pp. 1375–1379). https://doi.org/10.21437/Interspeech.2024-978
  • Anderer, K., Wölfel, M., & Niehues, J. (2024, September). Identifying the information gap for visually impaired students during lecture talks. In 2024 IEEE Symposium on Visual Languages and Human-Centric Computing (VL/HCC) (pp. 168–173). IEEE.
  • Beyerlein, M., Herzog, M., & Stein, T. (2024). The influence of single-session blocked vs. randomized perturbation-based balance training on dynamic stability in young adults. Gait & Posture, 113, 22–23.
  • Chen, Y., Zhang, J., Peng, K., Zheng, J., Liu, R., Torr, P., & Stiefelhagen, R. (2024, June). RoDLA: Benchmarking the robustness of document layout analysis models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, United States.
  • Schuster, S., Wetzel, J., Zeitvogel, S., & Laubenheimer, A. (2024). Automatic extrinsic multi-sensor network calibration based on time series matching. In 2024 27th International Conference on Information Fusion (FUSION) (pp. 1–8). IEEE. https://doi.org/10.23919/FUSION59988.2024.10706511
  • Zachariae, A., Plahl, F., Tang, Y., Mamaev, I., Hein, B., & Wurll, C. (2024). Human-robot interactions in autonomous hospital transports. Robotics and Autonomous Systems, 179, 104755. https://doi.org/10.1016/j.robot.2024.104755
  • Zachariae, A., Widera, J., Plahl, F., Hein, B., & Wurll, C. (2024). Human emergency detection during autonomous hospital transports. In Intelligent Autonomous Systems 18 (Vol. 794, pp. 233–245). Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-44981-9_21
  • Zheng, J., Liu, R., Chen, Y., Peng, K., Wu, C., Yang, K., Zhang, J., & Stiefelhagen, R. (2024, September). Open panoramic segmentation. In European Conference on Computer Vision (ECCV) (pp. 164–182). Springer Nature Switzerland.
  • Zheng, J., Zhang, J., Yang, K., Peng, K., & Stiefelhagen, R. (2024, May). Materobot: Material recognition in wearable robotics for people with visual impairments. In 2024 IEEE International Conference on Robotics and Automation (ICRA) (pp. 2303–2309). IEEE.
  • Moeller, T., Moehler, F., Krell-Rösch, J., Dežman, M., Marquardt, C., Asfour, T., Stein, T., & Woll, A. (2023). Use of lower limb exoskeletons as an assessment tool for human motor performance: A systematic review. Sensors, 23(6). https://doi.org/10.3390/s23063032