Motivation

With the commercialization of space travel, the journey into space is becoming accessible to a wider audience. In the future, not only highly educated and highly trained space travelers will go into space. This will also change the demands on space suits and the health requirements.

In order to be medically and technically prepared for this situation, new technologies and measurement methods will be tested and adapted to the new conditions.

Approach & Goals

Protective suits for space travelers serve to safeguard vital functions during launch and landing as well as during missions in a vacuum. Today's suits are already equipped with various sensors, especially for temperature and oxygen concentration monitoring. The recording of vital parameters ranges from punctual measurements at specific points in time to continuous measurements. The sensor data is collected in the spacecraft and then sent to the ground station.

The goal of the overall AI-Suit project is to continuously record the stress level with the help of artificial intelligence (AI). In the future, critical health conditions will be detected at an early stage and selective feedback will be given to the space travelers. Since critical incidents are detected locally, contact to the base station and the amount of data transmitted will be reduced.

Concepts for a design of miniaturized, AI-based, yet energy-efficient sensing patches and their implementation/evaluation will be explored. The application is intended to realize optimized, digital health monitoring of the spacefarer:s and to provide preventive warning of immediate overload. For use in space, (e.g., blood pressure) as a vital parameter enables important statements about the effects of microgravity on the human blood circulation and, in combination with heart rate, is essential for determining the state of stress. The novel research approach of artificial intelligence is used for fast and efficient calculation of the data. The integration of expert knowledge ensures that the machine learning algorithms used are not a black box.

In parallel, we are investigating how the knowledge and tools gained can also be used in the medical field. One obvious example is the use of sensor technology for continuous monitoring in the clinical field.