The research work aims at real anomaly identification and its root cause AI/ML techniques. For spacecraft, this is essential for detecting off-nominal situations and responding accordingly. The software should
able to classify the parameters to identify the anomaly in real time. A distinction is made between point anomalies, contextual anomalies and collective anomalies. For autonomous systems and anomaly
detection, however, a consistent storage all mission data is essential to have a board database for state estimation, pattern recognition and decision-making.
Achievements
The project being undertaken by ISRO in collaboration with academia is directly or indirectly beneficial to the society.