Small Unmanned Aerial Systems (sUAS) must be monitored closely to identify, diagnose, and potentially mitigate flight problems as they arise. During the flight, the vast amounts of multivariate time series data typically generated by sUAS flight controllers can be complex to understand and analyze. While formal product documentation often provides example data plots with diagnostic suggestions, the sheer diversity of attributes, critical thresholds, and complex data interactions can be overwhelming to non-experts who subsequently seek help from discussion forums to interpret their data logs. Solutions based on deep learning or heuristics can be used to detect anomalies in different time-series data attributes. However, understanding and mitigating the root cause of flight problems based upon the combination of multiple detected data anomalies requires significant domain expertise. To address these challenges, this talk will present approaches that leverage deep learning and heuristic methods to detect anomalies in flight data, both for real-time and post-flight analysis. Additionally, it will explore how the combination of multiple detected anomalies can be utilized to diagnose the root cause of the flight issue. The solutions proposed aim to simplify the anomaly detection process while providing a more systematic approach for diagnosing complex flight behaviors.
Co-sponsored by: Media Partner: Open Research Institute (ORI)
Speaker(s): Md Nafee Al Islam
Agenda:
– Invited talk from Assistant Prof. Md Nafee Al Islam , from the University of San Diego.
– Q/A Session
Virtual: https://events.vtools.ieee.org/m/442925
Detection and Diagnosis of Flight Anomalies in Small Unmanned Aerial Systems
