Online data-driven anomaly detection in autonomous robots

Abstract

The use of autonomous robots is appealing for tasks, which are dangerous to humans. Autonomous robots might fail to perform their tasks since they are susceptible to varied sorts of faults such as point and contextual faults. Not all faults can be known in advance, and hence, anomaly detection is required. In this paper, we present an online data-driven anomaly detection approach (ODDAD) for autonomous robots. ODDAD is suitable for the dynamic nature of autonomous robots since it declares a fault based only on data collected online. In addition, it is unsupervised, model free and domain independent. ODDAD proceeds in three steps: data filtering, attributes grouping based on dependency between attributes and outliers detection for each group. Above a calculated threshold, an anomaly is declared. We empirically evaluate ODDAD in different domains: commercial unmanned aerial vehicles (UAVs), a vacuum-cleaning robot, a high-fidelity flight simulator and an electrical power system of a spacecraft. We show the significance and impact of each component of ODDAD . By comparing ODDAD to other state-of-the-art competing anomaly detection algorithms, we show its advantages.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18
Fig. 19
Fig. 20
Fig. 21

Notes

  1. 1.

    Note that even a data instance that was determined as anomalous automatically enters the sliding window in the next time step. Otherwise, \(H\) will not reflect changes over time.

References

  1. 1.

    Brotherton T, Mackey R (2001) Anomaly detector fusion processing for advanced military aircraft. In: IEEE proceedings of aerospace conference, vol 6, IEEE, pp 3125–3137

  2. 2.

    Chandola V, Banerjee A, Kumar V (2009) Anomaly detection: a survey, association for computing machinery (ACM) computing surveys 41(3):15:1–15:58. doi:10.1145/1541880.1541882

  3. 3.

    Cork L, Walker R (2007) Sensor fault detection for UAVs using a nonlinear dynamic model and the imm-ukf algorithm. In: Information, decision and control (IDC’07), IEEE, pp 230–235

  4. 4.

    Craighead J, Murphy R, Burke J, Goldiez B (2007) A survey of commercial open source unmanned vehicle simulators. In: Proceedings of the IEEE international conference on robotics and automation, pp 852–857

  5. 5.

    Daigle MJ, Koutsoukos XD, Biswas G (2009) A qualitative event-based approach to continuous systems diagnosis. IEEE Trans Control Syst Technol 17(4):780–793

    Article  Google Scholar 

  6. 6.

    Eski I, Erkaya S, Savas S, Yildirim S (2011) Fault detection on robot manipulators using artificial neural networks. Robot Comput Integr Manuf 27(1):115–123

    Article  Google Scholar 

  7. 7.

    FlightGear (2013) http://www.flightgear.org/.

  8. 8.

    Goel P, Dedeoglu G, Roumeliotis SI, Sukhatme GS (2000) Fault detection and identification in a mobile robot using multiple model estimation and neural network. In: Proceedings of the IEEE international conference on robotics and automation, pp 2302–2309

  9. 9.

    Hido S, Tsuboi Y, Kashima H, Sugiyama M, Kanamori T (2011) Statistical outlier detection using direct density ratio estimation. Knowl Inf Syst 26(2):309–336

    Article  Google Scholar 

  10. 10.

    Hofbaur M, Köb J, Steinbauer G, Wotawa F (2007) Improving robustness of mobile robots using model-based reasoning. J Intell Robot Syst 48(1):37–54. doi:10.1007/s10846-006-9102-0

  11. 11.

    Hwang I, Kim S, Kim Y, Seah CE (2010) A survey of fault detection, isolation, and reconfiguration methods. IEEE Trans Control Syst Technol 18(3):636–653

    Article  Google Scholar 

  12. 12.

    Khalastchi E, Kaminka GA, Kalech M, Lin R (2011) Online anomaly detection in unmanned vehicles. In: Proceedings of the 10th international conference on autonomous agents and multiagent systems, AAMAS ’11, International foundation for Autonomous Agents and Multiagent Systems, pp 115–122. http://dl.acm.org/citation.cfm?id=2030470.2030487

  13. 13.

    lab A (2013). http://c3.nasa.gov/dashlink/projects/3/

  14. 14.

    Laurikkala J, Juhola M, Kentala E, Lavrac N, Miksch S, Kavsek B (2000) Informal identification of outliers in medical data. In: Proceedings of the 5th international workshop on intelligent data analysis in medicine and pharmacology, pp 20–24. http://citeseerx.ist.psu.edu/viewdoc/summary?doi=?doi=10.1.1.36.7407

  15. 15.

    Leveson NG, Turner CS (1993) An investigation of the therac-25 accidents. Computer 26(7):18–41

    Article  Google Scholar 

  16. 16.

    Lin R, Khalastchi E, Kaminka GA (2010) Detecting anomalies in unmanned vehicles using the mahalanobis distance. In: Proceedings of the IEEE international conference on robotics and automation, IEEE, pp 3038–3044

  17. 17.

    Lishuang X, Tao C, Fang D (2011) Sensor fault diagnosis based on least squares support vector machine online prediction. In: IEEE conference on robotics, automation and mechatronics (RAM), IEEE, pp 275–279

  18. 18.

    Mahalanobis PC (1936) On the generalized distance in statistics. In: Proceedings of the National Institute of Sciences, vol 2, ppp 49–55

  19. 19.

    Manevitz LM, Yousef M (2002) One-class svms for document classification. J Mach Learn Res 2, pp 139–154. http://portal.acm.org/citation.cfm?id=944790.944808

  20. 20.

    Masud M, Woolam C, Gao J, Khan L, Han J, Hamlen K, Oza N (2012) Facing the reality of data stream classification: coping with scarcity of labeled data. Knowl Inf Syst 33(1): 213–244. doi:10.1007/s10115-011-0447-8

  21. 21.

    Oates T, Schmill MD, Gregory DE, Cohen PR (1995) Detecting complex dependencies in categorical data. In: Fisher D, Lenz H (eds) Learning from data: artificial intelligence and statistics, Springer, pp 185–195

  22. 22.

    Pearson K (1894) Contributions to the mathematical theory of evolution. Philos Trans R Soc Lond A 185:71–110

    Article  MATH  Google Scholar 

  23. 23.

    Pokrajac D, Lazarevic A, Latecki LJ (2007) Incremental local outlier detection for data streams. In: The symposium on computational intelligence and data mining, CIDM’07, IEEE, pp 504–515

  24. 24.

    Ratsch G, Mika S, Scholkopf B, Muller K-R (2002) Constructing boosting algorithms from SVMs: an application to one-class classification. IEEE Trans Pattern Anal Mach Intell 24(9):1184–1199

    Article  Google Scholar 

  25. 25.

    Ruiz-del Solar J, Chown E, Ploeger PG (2011) RoboCup 2010: robot soccer world cup XIV, vol. 6556, Springer, Berlin

  26. 26.

    Sorton EF, Hammaker S (2005) Simulated flight testing of an autonomous unmanned aerial vehicle using flight-gear. American Institute of Aeronautics and Astronautics 2005–7083, Institute for Scientific Research

  27. 27.

    Steinbauer G (2013) A survey about faults of robots used in robocup. In: RoboCup 2012: robot soccer world cup XVI’, Springer, Berlin, pp 344–355

  28. 28.

    Steinbauer G, Mörth M, Wotawa F (2006) Real-time diagnosis and repair of faults of robot control software. In: Bredenfeld A, Jacoff A, Noda I, Takahashi Y (eds) RoboCup 2005: robot soccer world cup IX’, Springer, pp 13–23. http://dl.acm.org/citation.cfm?id=2124160.2124164

  29. 29.

    Steinwart I, Christmann A (2008) Support vector machines. Springer, Berlin

    MATH  Google Scholar 

  30. 30.

    Sundvall P, Jensfelt P (2006) Fault detection for mobile robots using redundant positioning systems. In: ICRA, pp 3781–3786

  31. 31.

    SVM light (2010). http://svmlight.joachims.org

  32. 32.

    Travé-Massuyès L (2014) Bridging control and artificial intelligence theories for diagnosis: a survey. Eng Appl Artif Intell 27:1–16

    Article  Google Scholar 

  33. 33.

    Zaman S, Steinbauer G, Maurer J, Lepej P, Uran S (2013) An integrated model-based diagnosis and repair architecture for ros-based robot systems In: IEEE international conference on robotics and automation (ICRA), IEEE, pp 482–489

Download references

Acknowledgments

This research was funded in part by ISF Grant #1511/12 and by Kamin program. As always, thanks to K. Ushi and K. Ravit.

Author information

Affiliations

Authors

Corresponding author

Correspondence to Eliahu Khalastchi.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Khalastchi, E., Kalech, M., Kaminka, G.A. et al. Online data-driven anomaly detection in autonomous robots. Knowl Inf Syst 43, 657–688 (2015). https://doi.org/10.1007/s10115-014-0754-y

Download citation

Keywords

  • Anomaly detection
  • Robotics
  • UAV
  • UGV
  • Unmanned vehicles
  • Autonomous agents
  • Unsupervised
  • Model free
  • Online
  • Data driven
  • ODDAD
  • AI
  • Fault detection