Abstract
We present a method for learning a general regrasping behavior by using supervised policy learning. First, we use reinforcement learning to learn linear regrasping policies, with a small number of parameters, for single objects. Next, a general high-dimensional regrasping policy is learned in a supervised manner by using the outputs of the individual policies. In our experiments with multiple objects, we show that learning low-dimensional policies makes the reinforcement learning feasible with a small amount of data. Our experiments indicate that the general high-dimensional policy learned using our method is able to outperform the respective linear policies on each of the single objects that they were trained on. Moreover, the general policy is able to generalize to a novel object that was not present during training.
Y. Chebotar and K. Hausman contributed equally to this work.
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
Notes
References
Bohg, J., Morales, A., Asfour, T., Kragic, D.: Data-driven grasp synthesis a survey. IEEE Trans. Robot. 30(2), 289–309 (2014)
Chebotar, Y., Hausman, K., Su, Z., Sukhatme, G.S., Stefan, S.: Self-supervised regrasping using spatio-temporal tactile features and reinforcement learning. In: 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE (2016)
Levine, S., Koltun, V.: Guided policy search. In: Proceedings of the 30th International Conference on Machine Learning, pp. 1–9 (2013)
Deisenroth, M.P., Neumann, G., Peters, J.: A survey on policy search for robotics. Found. Trends Robot. 2(1–2), 1–142 (2013)
Dang, H., Allen, P.K.: Stable grasping under pose uncertainty using tactile feedback. Auton. Robot. 36(4), 309–330 (2014)
Li, M., Bekiroglu, Y., Kragic, D., Billard, A.: Learning of grasp adaptation through experience and tactile sensing. In: 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2014), pp. 3339–3346. IEEE (2014)
Levine, S., Wagener, N., Abbeel, P.: Learning contact-rich manipulation skills with guided policy search. In: 2015 IEEE International Conference on Robotics and Automation (ICRA), pp. 156–163. IEEE (2015)
Finn, C., Tan, X.Y., Duan, Y., Darrell, T., Levine, S., Abbeel, P.: Deep spatial autoencoders for visuomotor learning. CoRR 117(117), 240 (2015)
Madry, M., Bo, L., Kragic, D., Fox, D.: St-hmp: unsupervised spatio-temporal feature learning for tactile data. In: 2014 IEEE International Conference on Robotics and Automation (ICRA), pp. 2262–2269, May 2014
Bo, L., Ren, X., Fox, D.: Hierarchical matching pursuit for image classification: architecture and fast algorithms. In: NIPS, pp. 2115–2123 (2011)
Aharon, M., Elad, M., Bruckstein, A.: k-svd: an algorithm for designing overcomplete dictionaries for sparse representation. IEEE Trans. Signal Process. 54(11), 4311–4322 (2006)
Jolliffe, I.T.: Principal Component Analysis. Springer, New York (1986)
Peters, J., Mülling, K., Altun, Y.: Relative entropy policy search. In: AAAI. AAAI Press (2010)
Hagan, M.T., Menhaj, M.B.: Training feedforward networks with the marquardt algorithm. IEEE Trans. Neural Netw. 5(6), 989–993 (1994)
Yao, Y., Rosasco, L., Caponnetto, A.: On early stopping in gradient descent learning. Constr. Approximation 26(2), 289–315 (2007)
Wettels, N., Santos, V.J., Johansson, R.S., Loeb, G.E.: Biomimetic tactile sensor array. Adv. Robot. 22(8), 829–849 (2008)
Su, Z., Hausman, K., Chebotar, Y., Molchanov, A., Loeb, G.E., Sukhatme, G.S., Schaal, S.: Force estimation and slip detection/classification for grip control using a biomimetic tactile sensor. In: 2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids), pp. 297–303 (2015)
Chebotar, Y., Hausman, K., Su, Z., Molchanov, A., Kroemer, O., Sukhatme, G., Schaal, S.: Bigs: biotac grasp stability dataset. In: ICRA 2016 Workshop on Grasping and Manipulation Datasets (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
Chebotar, Y., Hausman, K., Kroemer, O., Sukhatme, G.S., Schaal, S. (2017). Generalizing Regrasping with Supervised Policy Learning. In: Kulić, D., Nakamura, Y., Khatib, O., Venture, G. (eds) 2016 International Symposium on Experimental Robotics. ISER 2016. Springer Proceedings in Advanced Robotics, vol 1. Springer, Cham. https://doi.org/10.1007/978-3-319-50115-4_54
Download citation
DOI: https://doi.org/10.1007/978-3-319-50115-4_54
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-50114-7
Online ISBN: 978-3-319-50115-4
eBook Packages: EngineeringEngineering (R0)