Abstract
As there is a growing need for domestic healthcare, multiple projects are aiming to bring domestic robots in our homes. These robots aim to help users in their everyday life through various actions. However, they are subjected to task failure, making them less efficient and, possibly, bothering to the users. In this work, we aim to prevent task failures by understanding their causes through robot’s experience. In order to guarantee high accuracy, our approach uses highly semantic data as well as user validation. Our approach can consolidate its knowledge or discover new possible causes, and uses a multi-armed bandit solution: R-UCB. In order to make it more efficient, R-UCB was improved using causal induction and causal graphs. Experiments show our proposition to achieve a very high rate of correct failure prevention.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Auer, P., Cesa-Bianchi, N., Fischer, P.: Finite-time analysis of the multiarmed bandit problem. Mach. Learn. 47(2–3), 235–256 (2002)
Bareinboim, E., Forney, A., Pearl, J.: Bandits with unobserved confounders: a causal approach. In: Advances in Neural Information Processing Systems, pp. 1342–1350 (2015)
Bouneffouf, D.: DRARS, a dynamic risk-aware recommender system. Ph.D. thesis, Institut National des Télécommunications (2013)
Bouneffouf, D., Bouzeghoub, A., Ganarski, A.L.: Risk-aware recommender systems. In: Lee, M., Hirose, A., Hou, Z.-G., Kil, R.M. (eds.) ICONIP 2013. LNCS, vol. 8226, pp. 57–65. Springer, Heidelberg (2013). doi:10.1007/978-3-642-42054-2_8
Ghezala, M.W.B., Bouzeghoub, A., Leroux, C.: RSAW: a situation awareness system for autonomous robots. In: 2014 13th International Conference on Control Automation Robotics and Vision (ICARCV), pp. 450–455. IEEE (2014)
Gouaillier, D., Hugel, V., Blazevic, P., Kilner, C., Monceaux, J., Lafourcade, P., Marnier, B., Serre, J., Maisonnier, B.: Mechatronic design of Nao humanoid. In: IEEE International Conference on Robotics and Automation, ICRA 2009, pp. 769–774. IEEE (2009)
Hanheide, M., Göbelbecker, M., Horn, G.S., Pronobis, A., Sjöö, K., Aydemir, A., Jensfelt, P., Gretton, C., Dearden, R., Janicek, M., et al.: Robot task planning and explanation in open and uncertain worlds. Artif. Intell. 247, 119–150 (2015)
Jarraya, A., Ramoly, N., Bouzeghoub, A., Arour, K., Borgi, A., Finance, B.: FSCEP: a new model for context perception in smart homes. In: Debruyne, C., et al. (eds.) OTM 2016. LNCS, vol. 10033, pp. 465–484. Springer, Cham (2016). doi:10.1007/978-3-319-48472-3_28
Kapotoglu, M., Koc, C., Sariel, S.: Robots avoid potential failures through experience-based probabilistic planning. In: 2015 12th International Conference on Informatics in Control, Automation and Robotics (ICINCO), vol. 2, pp. 111–120. IEEE (2015)
Lattimore, F., Lattimore, T., Reid, M.D.: Causal bandits: learning good interventions via causal inference. In: Advances in Neural Information Processing Systems, pp. 1181–1189 (2016)
Li, W., Wang, X., Zhang, R., Cui, Y., Mao, J., Jin, R.: Exploitation and exploration in a performance based contextual advertising system. In: Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 27–36. ACM (2010)
Ortega, P.A., Braun, D.A.: Generalized Thompson sampling for sequential decision-making and causal inference. Complex Adapt. Syst. Model. 2(1), 2 (2014)
Pearl, J.: Causality. Cambridge University Press, New York (2009)
Sariel, S., Yildiz, P., Karapinar, S., Altan, D., Kapotoglu, M.: Robust task execution through experience-based guidance for cognitive robots. In: 2015 International Conference on Advanced Robotics (ICAR), pp. 663–668. IEEE (2015)
Sen, R., Shanmugam, K., Kocaoglu, M., Dimakis, A.G., Shakkottai, S.: Contextual bandits with latent confounders: an NMF approach. arXiv preprint arXiv:1606.00119 (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Ramoly, N., Bouzeghoub, A., Finance, B. (2017). A Causal Multi-armed Bandit Approach for Domestic Robots’ Failure Avoidance. In: Liu, D., Xie, S., Li, Y., Zhao, D., El-Alfy, ES. (eds) Neural Information Processing. ICONIP 2017. Lecture Notes in Computer Science(), vol 10639. Springer, Cham. https://doi.org/10.1007/978-3-319-70136-3_10
Download citation
DOI: https://doi.org/10.1007/978-3-319-70136-3_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-70135-6
Online ISBN: 978-3-319-70136-3
eBook Packages: Computer ScienceComputer Science (R0)