Daimler and Benz Foundation –
Daimler and Benz Foundation –
Daimler and Benz Foundation –

Ladenburg Research Networks

Funding line

The “Ladenburg Research Networks” funding line offers scientists the opportunity to work on topics within an interdisciplinary research network over an extended period. Under the leadership of a scientific coordinator who acts as spokesperson, a research topic is investigated by several working groups at various scientific institutions in Germany and abroad.

Ladenburger Research Networks 2026

Sensor-based recording of experiential knowledge in nursing care and its conveyance via AI-based humanoid robotics

Due to demographic change, nursing education is faced with a hitherto underestimated challenge. As experienced nursing staff reach retirement age, not only is valuable personnel lost, but in particular experiential knowledge that has been optimized over the course of decades: Day-to-day handling routines, interaction patterns, and intuitive decision-making processes can hardly be recorded or conveyed in textbooks.

This is precisely where the “ROBO.KIWI” research project comes into play. As part of the “Sensor-based recording of experiential knowledge in nursing care and its conveyance via AI-based humanoid robotics” Ladenburg Research Network, the researchers are using a body-fitting sensor network to record real nursing care processes directly on the bodies of experienced nursing staff. The movement data collected are analyzed, processed, and then transferred to a robot via “motion retargeting” and imitative learning.

The humanoid robot plays a dual role here: As a “nursing care professional” it demonstrates curated movement sequences, and as a “care recipient” it simulates realistic resistance. Since it goes beyond the use of reading materials, explanatory videos, and virtual reality, the robot enables low-risk and above all physically experienceable training for the education of future care providers.

At the core of the project is the world’s first multimodal dataset for interactions in nursing care. The data serve as the basis for training embodied artificial intelligence and represent an important resource for the international research community. In the ROBO.KIWI project, an interdisciplinary team of scientists is decoupling nursing education from the limited availability of human experts, thereby bringing about a paradigm shift: Robots are developing from mere tools to physical learning partners. This principle can be transferred to further fields in which experiential knowledge is being systematically lost – for example in industrial production, the skilled trades, or agriculture.