MUST is an ecosystem that provides high-performance access to telemetry, telecommand history, events and ancillary mission data and tools to interact with this data. MUST Ecosystem features several clients such as: WebMUST, MUSE (the MUST Scripting Engine), Reporting Tool to automatically create reports, DrMUST, Novelty Detection, etc.
The Mission Utilities & Support Tools
Anomaly investigation and characterization
MUST client providing data-driven support for anomaly investigation and characterization. It features pattern matching in time series to understand if and when the same anomaly happened in the past, and it automatically identify which telemetry parameters were involved in an anomaly.
Early detection of unusual behaviour
Novel behaviour is often the signature of an anomaly in the way to happen. Novelty Detection performs early detection of unusual behaviour in telemetry data. This allows control engineers to take corrective action before the anomaly develops.
Thermal Power Consumption prediction
Increase science return
Machine Learning is used to automatically predict how much power will be needed by the thermal subsystem. Accurately predicting the thermal power consumption allows to increase science return while keeping spacecrafts safe.
Data dump plans
The MEXAR2 tool generates data dump plans for the MarsExpress mission, RAXEM schedules the uplink of telecommands using artificial intelligence technologies.
Advanced Planning & Scheduling Initiative
An AI experimental Java platform which allows rapid development of AI based tools for planning, scheduling, optimization processes and autonomy. Available for download on the European Space Software Repository (ESSR).
Goal Oriented Autonomous Controller
A study to design and test robust onboard goal-oriented autonomous software. The Goal Oriented Autonomous Controller (GOAC) is designed to generate plans in-situ, to dispatch activities for execution and to recover from off-nominal conditions.
Innovative Planning Operations
Preparing ESA for future robotics missions operations through the Investigation and Prototyping of Innovative Planning Operations Concepts for Rovers equipped with Autonomy Capabilities.
Tool for Intelligent Allocation of Ground Operations
TIAGO applies AI to planning and scheduling of routine ground station passes to dump the most recent scientific and housekeeping data for the Cluster-II mission.
The Advanced Planning and Scheduling Technology Research
The Advanced Planning and Scheduling Technology Research, a study to analyse, design, prototype and evaluate an integration approach between AI framework, APSI, and the consolidated mission planning and scheduling framework MPSF.
Fully automatic generation of conflict-free operation plans
TECO provides fully automatic generation of conflict-free operation plans for week-long ESA experimental communication payload operations, onboard Aplhasat. The plans are generated, based on activity requests received by each payload manager.
Machine learning tool
TRAC is a machine learning tool to automatically check if requirement documents are compliant to the ECSS‐E‐ST‐10‐06C standard. TRAC features easy to use web interface that will enable service provision to Quality Assurance experts across ESA.
KITE is a knowledge management tool powered by state-of-the-art text mining and machine learning. KITE can discover network of expertise across ESA colleagues based on available textual documents (e.g. technical notes, reports, papers, etc.). KITE can also support the identification of which ESA colleagues has competence on specific domain of expertise.