Abstract
Most manipulation tasks can be decomposed into sequences of sensorimotor primitives. These primitives often end with characteristic sensory events, e.g., making or breaking contact, which indicate when the sensorimotor goal has been reached. In this manner, the robot can monitor the tactile signals to determine when to switch between primitives. In this paper, we present a framework for automatically segmenting contact-based manipulation tasks into sequences of sensorimotor primitives using multimodal haptic signals. These signals include both the robot’s end-effector position as well as the low- and high-frequency components of its tactile sensors. The resulting segmentation is used to learn to detect when the robot has reached a sensorimotor goal and it should therefore switch to the next primitive. The proposed framework was evaluated on guided peg-in-hole tasks. The experiments show that the framework can extract the subtasks of the manipulations and the sensorimotor goals can be accurately detected.
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
References
Adams, R.P., MacKay, D.J.: Bayesian online changepoint detection. arXiv preprint (2007). arXiv:0710.3742
Aharon, M., Elad, M., Bruckstein, A.: k -svd: An algorithm for designing overcomplete dictionaries for sparse representation. Trans. Sig. Proc. 54(11), 4311–4322 (2006)
Bo, L., Ren, X., Fox, D.: Hierarchical matching pursuit for image classification: architecture and fast algorithms. In: NIPS, pp. 2115–2123 (2011)
Chebotar, Y., Kroemer, O., Peters, J.: Learning robot tactile sensing for object manipulation. In: IROS, pp. 3368–3375. IEEE (2014)
Deiterding, J., Henrich, D.: Automatic adaptation of sensor-based robots. In: IROS, pp. 1828–1833. IEEE (2007)
Flanagan, J.R., Bowman, M.C., Johansson, R.S.: Control strategies in object manipulation tasks. Curr. Opin. Neurobiol. 16(6), 650–659 (2006)
Johansson, R.S., Flanagan, J.R.: Coding and use of tactile signals from the fingertips in object manipulation tasks. Nat. Rev. Neurosci. 10(5), 345–359 (2009)
Kappler, D., Pastor, P., Kalakrishnan, M., Manue, W., Schaal, S.: Data-driven online decision making for autonomous manipulation. In: RSS (2015)
Kroemer, O., van Hoof, H., Neumann, G., Peters, J.: Learning to predict phases of manipulation tasks as hidden states. In: ICRA, pp. 4009–4014. IEEE (2014)
Kulick, J., Otte, S., Toussaint, M.: Active exploration of joint dependency structures. In: ICRA, pp. 2598–2604. IEEE (2015)
Li, Q., Schürmann, C., Haschke, R., Ritter, H.J.: A control framework for tactile servoing. In: Robotics: Science and systems (2013)
Madry, M., Bo, L., Kragic, D., Fox, D.: ST-HMP: Unsupervised spatio-temporal feature learning for tactile data. In: ICRA, pp. 2262–2269. IEEE (2014)
Manschitz, S., Kober, J., Gienger, M., Peters, J.: Learning movement primitive attractor goals and sequential skills from kinesthetic demonstrations. RAS 74, 97–107 (2015)
Matulevich, B., Loeb, G.E., Fishel, J.A.: Utility of contact detection reflexes in prosthetic hand control. In: IROS, pp. 4741–4746. IEEE (2013)
Meier, F., Theodorou, E., Stulp, F., Schaal, S.: Movement segmentation using a primitive library. In: IROS, pp. 3407–3412. IEEE (2011)
Niekum, S., Osentoski, S., Atkeson, C.G., Barto, A.G.: Online bayesian changepoint detection for articulated motion models. In: ICRA, pp. 1468–1475. IEEE (2015)
Niekum, S., Osentoski, S., Konidaris, G.D., Chitta, S., Marthi, B., Barto, A.G.: Learning grounded finite-state representations from unstructured demonstrations. IJRR 34(2), 131–157 (2015)
Pastor, P., Kalakrishnan, M., Righetti, L., Schaal, S.: Towards associative skill memories. In: Humanoids, pp. 309–315. IEEE (2012)
Romano, J.M., Hsiao, K., Niemeyer, G., Chitta, S., Kuchenbecker, K.J.: Human-inspired robotic grasp control with tactile sensing. Trans. Rob. 27(6), 1067–1079 (2011)
Su, Z., Fishel, J., Yamamoto, T., Loeb, G.: Use of tactile feedback to control exploratory movements to characterize object compliance. Front. Neurorob. 6(7), (2012)
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: Humanoids, pp. 297–303. IEEE (2015)
Turner, R., Saatci, Y., Rasmussen, C.E.: Adaptive sequential bayesian change point detection. In: Temporal Segmentation Workshop at NIPS (2009)
Wettels, N., Santos, V., Johansson, R., Loeb, G.: Biomimetic tactile sensor array. Adv. Robot. 22(8), 829–849 (2008)
Acknowledgments
Research supported by the MPI for Intelligent Systems. BioTac sensors were provided by SynTouch LLC. Gerald E. Loeb is an equity partner in SynTouch LLC, manufacturer of the BioTac sensors used in this research. Special thanks to Felix Grimminger for helping design the 3D printed parts.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Su, Z., Kroemer, O., Loeb, G.E., Sukhatme, G.S., Schaal, S. (2016). Learning to Switch Between Sensorimotor Primitives Using Multimodal Haptic Signals. In: Tuci, E., Giagkos, A., Wilson, M., Hallam, J. (eds) From Animals to Animats 14. SAB 2016. Lecture Notes in Computer Science(), vol 9825. Springer, Cham. https://doi.org/10.1007/978-3-319-43488-9_16
Download citation
DOI: https://doi.org/10.1007/978-3-319-43488-9_16
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-43487-2
Online ISBN: 978-3-319-43488-9
eBook Packages: Computer ScienceComputer Science (R0)