Under the direction of AIKO S.r.l. and together with DLR Space Operations and GomSpace Luxembourg, Prof. Dr.-Ing. Roger Förstner has acquired funding from the European Space Agency (ESA) for the DL4Space project.
The project develops deep-learning applications for analyzing the telemetry of spacecraft. The consortium consists of the Italian startup company AIKO, DLR Space Operations, GomSpace Luxembourg, and the Universität der Bundeswehr München (Bundeswehr University Munich). Applications are selected from the research areas of spacecraft ground operations (OPS) and spacecraft assembly, integration and test (AIT), with the focus on the detection of anomalies based on machine learning and deep-learning techniques.
Research in the field of deep learning has gained momentum in the past few years and has contributed to a further increase in the quality and number of applications that benefit from deep-learning solutions. This study focuses on the application of state-of-the-art deep-learning methods to space flight-related problems in the areas Space Flight Operations (OPS) and Assembly, Integration and Test (AIT). Many of these applications focus on time series data (e.g. telemetry, telecommands, etc.). Some examples of applications in both areas are the detection of anomalies, predictions, knowledge management, etc.
Project period: July 2021 to June 2022
Funding by: European Space Agency (ESA)