Hierarchical HMM-based Failure Isolation for Cognitive Robots

Dogan Altan, Sanem Sariel-Talay

Abstract

Robots execute their planned actions in the physical world to accomplish their goals. However, since the real world is partially observable and dynamic, failures may occur during the execution of their actions. These failures should be detected immediately, and the underlying reasons of these failures should be isolated to ensure robustness. In this paper, we propose a probabilistic and temporal model-based failure isolation method that maintains Hierarchical Hidden Markov Models (HHMMs) in order to represent and reason about different failure types. The underlying reason of a failure can be isolated efficiently by multi-hypothesis tracking.

References

  1. Baum, L. E. and Petrie, T. (1966). Statistical inference for probabilistic functions of finite state markov chains. The Annals of Mathematical Statistics, 37(6):pp. 1554-1563.
  2. Bouguerra, A., Karlsson, L., and Saffiotti, A. (2007). Handling uncertainty in semantic-knowledge based execution monitoring. In Intelligent Robots and Systems, 2007. IROS 2007. IEEE/RSJ International Conference on, pages 437-443.
  3. Bouguerra, A., Karlsson, L., and Saffiotti, A. (2008). Monitoring the execution of robot plans using semantic knowledge. Robotics and Autonomous Systems, 56(11):942-954.
  4. Camci, F. and Chinnam, R. (2010). Health-state estimation and prognostics in machining processes. Automation Science and Engineering, IEEE Transactions on, 7(3):581-597.
  5. Chittaro, L. and Ranon, R. (2004). Hierarchical modelbased diagnosis based on structural abstraction. Artificial Intelligence, 155(12):147 - 182.
  6. Ersen, M., Sariel-Talay, S., and Yalcin, H. (2013). Extracting spatial relations among objects for failure detection. In Proceedings of the KI 2013 Workshop on Visual and Spatial Cognition.
  7. Fine, S., Singer, Y., and Tishby, N. (1998). The hierarchical hidden markov model: Analysis and applications. Machine Learning, 32(1):41-62.
  8. Flores-Quintanilla, J., Morales-Menendez, R., RamirezMendoza, R., Garza-Castanon, L., and Cantu-Ortiz, F. (2005). Towards a new fault diagnosis system for electric machines based on dynamic probabilistic models. In American Control Conference, 2005. Proceedings of the 2005.
  9. Frank, P. M., Ding, S. X., and Marcu, T. (2000). Modelbased fault diagnosis in technical processes. Transactions of the Institute of Measurement and Control, 22(1):57-101.
  10. Fritz, C. (2005). Execution monitoring - a survey. Technical report, University of Toronto.
  11. Ge, M., Du, R., and Xu, Y. (2004). Hidden markov model based fault diagnosis for stamping processes. Mechanical Systems and Signal Processing, 18(2):391 - 408.
  12. Gspandl, S., Podesser, S., Reip, M., Steinbauer, G., and Wolfram, M. (2012). A dependable perceptiondecision-execution cycle for autonomous robots. In Robotics and Automation (ICRA), 2012 IEEE International Conference on, pages 2992-2998.
  13. Hovland, G. and McCarragher, B. J. (1998). Hidden markov models as a process monitor in robotic assembly. I. J. Robotic Res., 17(2):153-168.
  14. Karapinar, S., Altan, D., and Sariel-Talay, S. (2012). A robust planning framework for cognitive robots. In Proceedings of the AAAI-12 Workshop on Cognitive Robotics (CogRob).
  15. Karapinar, S., Sariel-Talay, S., Yildiz, P., and Ersen, M. (2013). Learning guided planning for robust task execution in cognitive robotics. In The AAAI-13 Workshop on Intelligent Robotic Systems, Bellevue, USA.
  16. Kwon, K.-C. and Kim, J.-H. (1999). Accident identification in nuclear power plants using hidden markov models. Engineering Applications of Artificial Intelligence, 12(4):491 - 501.
  17. Lee, J. M., Kim, S.-J., Hwang, Y., and Song, C.-S. (2004). Diagnosis of mechanical fault signals using continuous hidden markov model. Journal of Sound and Vibration, 276(35):1065 - 1080.
  18. Li, Z., Wu, Z., He, Y., and Fulei, C. (2005). Hidden markov model-based fault diagnostics method in speed-up and speed-down process for rotating machinery. Mechanical Systems and Signal Processing, 19(2):329 - 339.
  19. Nan, C., Khan, F., and Iqbal, M. T. (2008). Real-time fault diagnosis using knowledge-based expert system. Process Safety and Environmental Protection, 86(1):55 - 71.
  20. Ocak, H. and Loparo, K. (2001). A new bearing fault detection and diagnosis scheme based on hidden markov modeling of vibration signals. In Acoustics, Speech, and Signal Processing, 2001. Proceedings. (ICASSP 7801). 2001 IEEE International Conference on, volume 5, pages 3141-3144 vol.5.
  21. Ozturk, M. D., Ersen, M., Kapotoglu, M., Koc, C., SarielTalay, S., and Yalcin, H. (2014). Scene interpretation for self-aware cognitive robots. In AAAI-14 Spring Symposium on Qualitative Representations for Robots.
  22. Pettersson, O. (2005). Execution monitoring in robotics: A survey. Robotics and Autonomous Systems, 53:73-88.
  23. Steinbauer, G. and Wotawa, F. (2009). Robust plan execution using model-based reasoning. Advanced Robotics, 23(10):1315-1326.
  24. Usug, U. C., Altan, D., and Sariel-Talay, S. (2012). Robots that create alternative plans against failures. In 10th IFAC Symposium on Robot Control.
  25. Verma, V., Fernandez, J., Simmons, R., and Chatila, R. (2002a). Probabilistic models for monitoring and fault diagnosis. In The Second IARP and IEEE/RAS Joint Workshop on Technical Challenges for Dependable Robots in Human Environments.
  26. Verma, V., Gordon, G., Simmons, R., and Thrun, S. (2004). Real-time fault diagnosis [robot fault diagnosis]. Robotics Automation Magazine, IEEE, 11(2):56- 66.
  27. Verma, V., Simmons, R., and Fernndez, J. (2002b). Probabilistic models for monitoring and fault diagnosis. In The Second IARP and IEEE/RAS Joint Workshop on Technical Challanges for Dependable Robots in Human, pages 43-67.
  28. Viterbi, A. (1967). Error bounds for convolutional codes and an asymptotically optimum decoding algorithm. Information Theory, IEEE Transactions on, 13(2):260-269.
  29. Ying, J., Kirubarajan, T., Pattipati, K., and Patterson-Hine, A. (2000). A hidden markov model-based algorithm for fault diagnosis with partial and imperfect tests. Systems, Man, and Cybernetics, Part C: Applications and Reviews, IEEE Transactions on, 30(4):463-473.
Download


Paper Citation


in Harvard Style

Altan D. and Sariel-Talay S. (2014). Hierarchical HMM-based Failure Isolation for Cognitive Robots . In Proceedings of the 6th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, ISBN 978-989-758-016-1, pages 299-304. DOI: 10.5220/0004921502990304


in Bibtex Style

@conference{icaart14,
author={Dogan Altan and Sanem Sariel-Talay},
title={Hierarchical HMM-based Failure Isolation for Cognitive Robots},
booktitle={Proceedings of the 6th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,},
year={2014},
pages={299-304},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004921502990304},
isbn={978-989-758-016-1},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 6th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,
TI - Hierarchical HMM-based Failure Isolation for Cognitive Robots
SN - 978-989-758-016-1
AU - Altan D.
AU - Sariel-Talay S.
PY - 2014
SP - 299
EP - 304
DO - 10.5220/0004921502990304