Online anomaly detection in unmanned vehicles

Autonomy requires robustness. The use of unmanned (autonomous) vehicles is appealing for tasks which are dangerous or dull. However, increased reliance on autonomous robots increases reliance on their robustness. Even with validated software, physical faults can cause the controlling software to perceive the environment incorrectly, and thus to make decisions that lead to task failure. We present an online anomaly detection method for robots, that is light-weight, and is able to take into account a large number of monitored sensors and internal measurements, with high precision. We demonstrate a specialization of the familiar Mahalanobis Distance for robot use, and also show how it can be used even with very large dimensions, by online selection of correlated measurements for its use. We empirically evaluate these contributions in different domains: commercial Unmanned Aerial Vehicles (UAVs), a vacuum-cleaning robot, and a high-fidelity flight simulator. We find that the online Mahalanobis distance technique, presented here, is superior to previous methods.

[1]  Sarit Kraus,et al.  Multi-robot perimeter patrol in adversarial settings , 2008, 2008 IEEE International Conference on Robotics and Automation.

[2]  Gaurav S. Sukhatme,et al.  Fault detection and identification in a mobile robot using multiple model estimation and neural network , 2000, Proceedings 2000 ICRA. Millennium Conference. IEEE International Conference on Robotics and Automation. Symposia Proceedings (Cat. No.00CH37065).

[3]  P. Mahalanobis.  On the generalized distance in statistics , 1936 .

[4]  Eric Sorton,et al.  Simulated Flight Testing of an Autonomous Unmanned Aerial Vehicle Using FlightGear , 2005 .

[5]  R. Mackey,et al.  Anomaly detector fusion processing for advanced military aircraft , 2001, 2001 IEEE Aerospace Conference Proceedings (Cat. No.01TH8542).

[6]  Sebastian Thrun,et al.  Robotic mapping: a survey , 2003 .

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

[8]  Aleksandar Lazarevic,et al.  Incremental Local Outlier Detection for Data Streams , 2007, 2007 IEEE Symposium on Computational Intelligence and Data Mining.

[9]  Andreas Christmann,et al.  Support vector machines , 2008, Data Mining and Knowledge Discovery Handbook.

[10]  Patric Jensfelt,et al.  Fault detection for mobile robots using redundant positioning systems , 2006, Proceedings 2006 IEEE International Conference on Robotics and Automation, 2006. ICRA 2006..

[11]  Michael A. Goodrich,et al.  Supporting wilderness search and rescue using a camera‐equipped mini UAV , 2008, J. Field Robotics.

[12]  Doug Fisher,et al.  Learning from Data: Artificial Intelligence and Statistics V , 1996 .

[13]  Martti Juhola,et al.  Informal identification of outliers in medical data , 2000 .

[14]  Brian Goldiez,et al.  A Survey of Commercial & Open Source Unmanned Vehicle Simulators , 2007, Proceedings 2007 IEEE International Conference on Robotics and Automation.

[15]  R. Walker,et al.  Sensor Fault Detection for UAVs using a Nonlinear Dynamic Model and the IMM-UKF Algorithm , 2007, 2007 Information, Decision and Control.

[16]  Paul R. Cohen,et al.  Detecting Complex Dependencies in Categorical Data , 1995, AISTATS.

[17]  Eliahu Khalastchi,et al.  Detecting anomalies in unmanned vehicles using the Mahalanobis distance , 2010, 2010 IEEE International Conference on Robotics and Automation.

[18]  Michael A. Goodrich,et al.  Supporting wilderness search and rescue using a camera-equipped mini UAV: Research Articles , 2008 .

[19]  Andreas Birk,et al.  Rescue robotics — a crucial milestone on the road to autonomous systems , 2006, Adv. Robotics.