Publications

A Pattern Collection for Generating Accessible Teaching Materials for Blind and Visually Impaired Students in Computer Science and Electrical Engineering

(2025) - Paper

Diethelm Bienhaus; Michael Kreutzer

This paper addresses the problem that graphical representations such as circuit diagrams, Karnaugh maps, or UML diagrams are often inaccessible for blind and visually impaired students in STEM education. It shows that general guidelines such as WCAG do not provide sufficiently concrete workflows for subject-specific teaching materials. As a contribution, the authors present a collection of five pedagogical design patterns: transformable text-first authoring, textual modeling for diagram generation, tactile and haptic workflows, auditory preparation of time series, and human-in-the-loop explanations. The patterns are derived from teaching practice and are complemented by tool recommendations and implementation examples. The goal is a structured methodology for multimodal teaching materials usable with screen readers, braille displays, tactile printing, and sonification tools. Although developed in computer science and electrical engineering education, the paper describes transferability to other diagram-centered disciplines.

A Framework for Developing Modular Mobility Aids for People with Visual Impairment: An Indoor Navigation Use Case

(2023) - Paper

Florian von Zabiensky; Grigory Fridman; Oguz Ozdemir; Sebastian Reuter; Michael Kreutzer; Diethelm Bienhaus

This paper describes a framework for component-based development of electronic travel aids (ETAs) to reduce repetitive development effort in research projects. The core contribution is a component delimitation model that allows interchangeable combination of subfunctions such as environment sensing, obstacle detection, and output modalities. As practical validation, an indoor navigation system based on ultra-wideband (UWB) is implemented. Implementation uses the ROS2 ecosystem to leverage existing tooling, interfaces, and reuse across teams. The paper concludes with reflections on the development process and an assessment of opportunities and limitations of ROS2 for modular ETA prototypes.

An Electronic Guide Dog for the Blind based on Artificial Neural Networks

(2021) - Paper

S. Lopatin; F. v. Zabiensky; M. Kreutzer; K. Rinn; D. Bienhaus

This paper presents a feasibility study for an electronic assistance system intended to support blind and visually impaired people in orientation and navigation in public space. The core approach is optical detection of walkable sidewalk areas using semantic segmentation with a neural network trained from scratch. In the practical implementation, an NVIDIA Jetson Nano is used as a mobile computing unit for on-device inference. Navigation cues are derived from detected sidewalk structures and output to the user as speech. The work therefore examines technical feasibility of a portable electronic guide dog based on computer vision and CNN.

Ultrasonic Waves to Support Human Echolocation

HCII (2018) - Paper

Florian von Zabiensky; Michael Kreutzer; Diethelm Bienhaus

This paper presents AHRUS, a system that uses parametric ultrasound to make environmental information audible for people with visual impairment or blindness. Through self-demodulation, directional properties of ultrasound are preserved so signals can be perceived with the user's own ears. The contribution describes the technical setup of a prototype and initial usage concepts. In an initial evaluation with four participants, the system was tested in practice. Compared with classic flash-sonar echolocation, the approach shows advantages for small structures and for the stealth issue of smooth surfaces.

Related project: /research/projects/ahrus