ADMOST: UAV Flight Data Anomaly Detection and Mitigation via Online Subspace Tracking

Since the control laws require sensor feedback to set the current dynamic state of the unmanned aerial vehicle (UAV), incorrect readings may lead to potentially catastrophic conditions. Thus, automated detection and mitigation of UAV flight data anomaly is an important problem in the aviation domain. However, the conventional anomaly detection algorithms simply detect the outlier points and cannot provide estimated values. To address this challenge, anomaly detection and mitigation algorithm based on online subspace tracking, an online algorithm for flight data anomaly detection and mitigation is proposed. At every time instant, data subspace matrix is used as a meaningful data representation of raw multivariate heterogeneous flight data. Besides, in terms of outlier points, the subspace matrix is tracked with incomplete partial observation. Anomaly score is calculated based on the identification of a change in the underlying subspace. Utilizing the tracked subspace matrix, the detected outlier points are replaced with reasonable recovered estimations, which will help mitigate the influence of anomaly to UAV system control. Experimental results on real UAV flight data demonstrate its ability to maintain high accuracy for anomaly detection and low error for data recovery.

[1]  Roland Badeau,et al.  Fast and Stable YAST Algorithm for Principal and Minor Subspace Tracking , 2008, IEEE Transactions on Signal Processing.

[2]  Ole J. Mengshoel,et al.  Towards Real-Time, On-Board, Hardware-Supported Sensor and Software Health Management for Unmanned Aerial Systems , 2015 .

[3]  Jaideep Srivastava,et al.  Detection of Precursors to Aviation Safety Incidents Due to Human Factors , 2013, 2013 IEEE 13th International Conference on Data Mining Workshops.

[4]  Constantine Caramanis,et al.  Fast Algorithms for Robust PCA via Gradient Descent , 2016, NIPS.

[5]  Demoz Gebre-Egziabher,et al.  Design for graceful degradation and recovery from GNSS interruptions , 2017, IEEE Aerospace and Electronic Systems Magazine.

[6]  Dacheng Tao,et al.  Shifted Subspaces Tracking on Sparse Outlier for Motion Segmentation , 2013, IJCAI.

[7]  Tianguang Chu,et al.  Structure Regularized Traffic Monitoring for Traffic Matrix Estimation and Anomaly Detection by Link-Load Measurements , 2016, IEEE Transactions on Instrumentation and Measurement.

[8]  Gary J. Balas,et al.  Model-Based and Data-Driven Fault Detection Performance for a Small UAV , 2013, IEEE/ASME Transactions on Mechatronics.

[9]  Roland Siegwart,et al.  Strategies for sensor-fault compensation on UAVs: Review, discussions & additions , 2014, 2014 European Control Conference (ECC).

[10]  Johann Schumann,et al.  R2U2: monitoring and diagnosis of security threats for unmanned aerial systems , 2017, Formal Methods in System Design.

[11]  Peter J Seiler,et al.  Air data system fault modeling and detection , 2013 .

[12]  Yu Peng,et al.  A Structured Sparse Subspace Learning Algorithm for Anomaly Detection in UAV Flight Data , 2018, IEEE Transactions on Instrumentation and Measurement.

[13]  Bin Yang,et al.  Projection approximation subspace tracking , 1995, IEEE Trans. Signal Process..

[14]  Muhammad Ali Imran,et al.  Distributed Anomaly Detection Using Minimum Volume Elliptical Principal Component Analysis , 2016, IEEE Transactions on Knowledge and Data Engineering.

[15]  Yuh-Jye Lee,et al.  Anomaly Detection via Online Oversampling Principal Component Analysis , 2013, IEEE Transactions on Knowledge and Data Engineering.

[16]  Gautam Biswas,et al.  Learning Bayesian Network Structures to Augment Aircraft Diagnostic Reference Models , 2017, IEEE Transactions on Automation Science and Engineering.

[17]  Alfredo Paolillo,et al.  Outlier Detection for the Evaluation of the Measurement Uncertainty of Environmental Acoustic Noise , 2016, IEEE Transactions on Instrumentation and Measurement.

[18]  VARUN CHANDOLA,et al.  Anomaly detection: A survey , 2009, CSUR.

[19]  Marcello R. Napolitano,et al.  Performance evaluation of neural network based approaches for airspeed Sensor Failure Accommodation on a small UAV , 2013, 21st Mediterranean Conference on Control and Automation.

[20]  Marcello R. Napolitano,et al.  Aircraft model-independent airspeed estimation without pitot tube measurements , 2015, IEEE Transactions on Aerospace and Electronic Systems.

[21]  Charu C. Aggarwal,et al.  Outlier Detection for Temporal Data: A Survey , 2014, IEEE Transactions on Knowledge and Data Engineering.

[22]  Robert D. Nowak,et al.  Online identification and tracking of subspaces from highly incomplete information , 2010, 2010 48th Annual Allerton Conference on Communication, Control, and Computing (Allerton).

[23]  Stephen J. Wright,et al.  Online algorithms for factorization-based structure from motion , 2013, IEEE Winter Conference on Applications of Computer Vision.

[24]  Jing Liu,et al.  Robust Structured Subspace Learning for Data Representation , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[25]  A. Robert Calderbank,et al.  PETRELS: Parallel Subspace Estimation and Tracking by Recursive Least Squares From Partial Observations , 2012, IEEE Transactions on Signal Processing.

[26]  Yonina C. Eldar,et al.  Subspace Learning with Partial Information , 2014, J. Mach. Learn. Res..

[27]  Meir Kalech,et al.  A hybrid approach for fault detection in autonomous physical agents , 2014, AAMAS.

[28]  Ian Postlethwaite,et al.  Survey and application of sensor fault detection and isolation schemes , 2011 .

[29]  Meir Kalech,et al.  Online data-driven anomaly detection in autonomous robots , 2014, Knowledge and Information Systems.

[30]  Shie Mannor,et al.  Outlier-Robust PCA: The High-Dimensional Case , 2013, IEEE Transactions on Information Theory.

[31]  Shing-Chow Chan,et al.  Robust Recursive Eigendecomposition and Subspace-Based Algorithms With Application to Fault Detection in Wireless Sensor Networks , 2012, IEEE Transactions on Instrumentation and Measurement.

[32]  Martin Meckesheimer,et al.  Automatic outlier detection for time series: an application to sensor data , 2007, Knowledge and Information Systems.

[33]  Ruy Luiz Milidiú,et al.  Data stream anomaly detection through principal subspace tracking , 2010, SAC '10.

[34]  Eric D. Kolaczyk,et al.  A Compressed PCA Subspace Method for Anomaly Detection in High-Dimensional Data , 2011, IEEE Transactions on Information Theory.

[35]  Ashok N. Srivastava,et al.  Analysis of Flight Data Using Clustering Techniques for Detecting Abnormal Operations , 2015, J. Aerosp. Inf. Syst..

[36]  Mogens Blanke,et al.  Diagnosis of Airspeed Measurement Faults for Unmanned Aerial Vehicles , 2014, IEEE Transactions on Aerospace and Electronic Systems.

[37]  Girish Chowdhary,et al.  Frequency Domain Method for Real-Time Detection of Oscillations , 2010 .

[38]  George V. Moustakides,et al.  Fast and Stable Subspace Tracking , 2008, IEEE Transactions on Signal Processing.