Analyse der Nutzung von KI für AENEAS (ANUKI)

Monitoring and controlling software and system development projects involves a great deal of effort due to the complexity of the projects. Following a ‘perceived’ project status in decision-making processes is inappropriate and, given the nature of software projects in the aerospace industry, grossly negligent. The systematic and risk-driven project management required for this must be based on objective and clearly measurable quality indicators, so-called metrics. Fact-based decision-making is only possible on the basis of reliable figures.

Due to the size and complexity of space projects, which are usually carried out in international cooperation, the selection, recording and interpretation of the metrics relevant to a project is not easy, as they must be clear, objective, appropriate and meaningful, among other things. Even here, difficulties can arise in both internal and cross-project coordination, for example between the client and contractor. Are the same metrics used by all parties? Is the data collection comparable - and therefore also the data analysis? Are all the metrics used understood and interpreted in the same way by the parties involved?

The solution approach of the ANuKI project essentially consists of three parts:

1. acquisition of measurement data: Building on the structure of the predecessor project AENEAS, relevant artefact types (code, requirements, etc.) are to be identified. Relevant metrics are to be identified for these artefact types and recorded in a standardised metrics catalogue. For the identified metrics, the extent to which AI can be used to capture these metrics will be analysed. A particular focus here is on the handling of requirements in natural language.
2. utilisation of measurement data: Relevant use cases are to be identified for the utilisation of the captured data. In particular, relevant (sub)processes should be identified and modelled so that suitable AI techniques can be applied to the measurement data.
3. linking measurement data and project controlling: The potential applications arising from the use of measurement data for project controlling are to be investigated. This potential is to be analysed using the previously identified, selected (sub)processes.

The specific task for the ANuKI project is therefore to To analyse the possibilities offered by AI in automated data acquisition and use of the acquired data.