Abstract
The preprocessing procedure for anomalous behavior of robot system elements is proposed in the paper. It uses a special kind of a neural network called an autoencoder to solve two problems. The first problem is to decrease the dimensionality of the training data using the autoencoder to calculate the Mahalanobis distance, which can be viewed as one of the best metrics to detect the anomalous behavior of robots or sensors in the robot systems. The second problem is to apply the autoencoder to transfer learning. The autoencoder is trained by means of the target data which corresponds to the extreme operational conditions of the robot system. The source data containing the normal and anomalous observations derived from the normal operation conditions is reconstructed to the target data using the trained autoencoder. The reconstructed source data is used to define a optimal threshold for making decision on the anomaly of the observation based on the Mahalanobis distance.
Similar content being viewed by others
References
Navarro, I. and Matia, F., An introduction to swarm robotics, ISRN Rob., 2013, vol. 2013, no. 608164, pp. 1–10.
Tan, Y. and Zheng, Z.-Y., Research advance in swarm robotics, Def. Technol., 2013, vol. 9, pp. 18–39.
Pronobis, A., Mozos, O., and Caputo, B., SVM-based discriminative accumulation scheme for place recognition, Proceedings of the IEEE International Conference on Robotics and Automation, ICRA 2008, 2008, pp. 522–529.
Cowley, A., Hsu, H.-C., and Taylor, C., Distributed sensor databases for multi-robot teams, Proceedings of the 2004 IEEE International Conference on Robotics and Automation, ICRA '04, 2004, vol. 1, pp. 691–696.
Khalastchi, E., Kaminka, G., Kalech, M., and Lin, R., Online anomaly detection in unmanned vehicles, Proc. of 10th Int. Conf. on Autonomous Agents and Multiagent Systems (AAMAS 2011), 2011, vol. 1, pp. 115–122.
Khalastchi, E., Kalech, M., and Rokach, L., Sensor fault detection and diagnosis for autonomous systems, Proceedings of the 12th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2013), 2013, pp. 15–22.
Chandola, V., Banerjee, A., and Kumar, V., Anomaly detection: A survey, ACM Comput. Surv., 2009, vol. 41, no. 3, pp. 15:1–15:58.
Bartkowiak, A., Anomaly, novelty, one-class classification: A comprehensive introduction, Int. J. Comput. Inf. Syst. Ind. Manage. Appl., 2011, vol. 3, pp. 61–71.
Erfani, S., Rajasegarar, S., Karunasekera, S., and Leckie, C., High-dimensional and large-scale anomaly detection using a linear one-class SVM with deep learning, Pattern Recognit., 2016, vol. 58, pp. 121–134.
Khalastchi, E., Kalech, M., Kaminka, G., and Lin, R., Online data-driven anomaly detection in autonomous robots, Knowl. Inf. Syst., 2015, vol. 43, no. 3, pp. 657–688.
Pimentel, M., Clifton, D., Clifton, L., and Tarassenko, L., A review of novelty detection, Signal Process., 2014, vol. 99, pp. 215–249.
Thomaz, C., Gillies, D., and Feitosa, R., A new covariance estimate for Bayesian classifiers in biometric recognition, IEEE Trans. Circuits Syst. Video Technol., 2004, vol. 14, no. 2, pp. 214–223.
Pan, S. and Yang, Q., A survey on transfer learning, IEEE Trans. Knowl. Data Eng., 2010, vol. 22, no. 10, pp. 1345–1359.
Yang, S., Lin, M., Hou, C., Zhang, C., and Wu, Y., A general framework for transfer sparse subspace learning, Neural Comput. Appl., 2012, vol. 21, no. 10, pp. 1801–1817.
Deng, J., Zhang, Z., Marchi, E., and Schuller, B., Sparse autoencoder-based feature transfer learning for speech emotion recognition, Humaine Association Conference on Affective Computing and Intelligent Interaction, ACII-2013, Geneva, 2013, pp. 511–516.
Sakurada, M. and Yairi, T., Anomaly detection using autoencoders with nonlinear dimensionality reduction, Proceedings of the MLSDA 2014 2nd Workshop on Machine Learning for Sensory Data Analysis, Gold Coast, 2014, pp. 4–11.
Tagawa, T., Tadokoro, Y., and Yairi, T., Structured denoising autoencoder for fault detection and analysis, JMLR: Workshop and Conference Proceedings, 2014, vol. 39, pp. 96–111.
Brereton, R., The Mahalanobis distance and its relationship to principal component scores, J. Chemom., 2015, vol. 29, pp. 143–145.
Makhzani, A. and Frey, B., k-Sparse autoencoders, arXiv preprint: 1312.5663, 2013.
Author information
Authors and Affiliations
Corresponding author
Additional information
Original Russian Text © L.V. Utkin, V.S. Zaborovskii, S.G. Popov, 2016, published in Problemy Informatsionnoi Bezopasnosti, Komp’yuternye Sistemy.
About this article
Cite this article
Utkin, L.V., Zaborovskii, V.S. & Popov, S.G. Detection of anomalous behavior in a robot system based on deep learning elements. Aut. Control Comp. Sci. 50, 726–733 (2016). https://doi.org/10.3103/S0146411616080319
Received:
Published:
Issue Date:
DOI: https://doi.org/10.3103/S0146411616080319