Abstract
Generating trajectories autonomously through generalization requires an extensive database of motion, which is usually time-consuming and difficult to obtain. Recently approaches for autonomous database expansion for the generation of compliant and accurate motion were proposed, all showing that autonomous generation of the database of motion can be significantly speed up. However, no extensive analysis was performed to show what would be the optimal sequence of learning. In this paper we analyze different strategies to further speed up the learning process of autonomous database expansion for compliant movement primitives (CMPs). An extensive analysis was performed for finding an optimal learning sequence in a simulated environment for a peg-in-hole task with a Kuka LWR-4 robot. The obtained results were then confirmed on a real Kuka LWR-4 robot set up performing a peg-in-hole task.
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
Albu-Schaffer, A., Eiberger, O., Grebenstein, M., Haddadin, S., Ott, C., Wimbock, T., Wolf, S., Hirzinger, G.: Soft robotics. IEEE Robot. Autom. Mag. 15(3), 20–30 (2008)
Bristow, D.A., Tharayil, M., Alleyne, A.G.: A survey of iterative learning control. IEEE Control Syst. 26(3), 96–114 (2006)
Denisa, M., Petrič, T., Asfour, T., Ude, A.: Synthesizing compliant reaching movements by searching a database of example trajectories. In: International Conference on Humanoid Robots, pp. 540–546 (2013)
Deniša, M., Gams, A., Ude, A., Petrič, T.: Learning compliant movement primitives through demonstration and statistical generalization. IEEE/ASME Trans. Mechatron. 21(5), 2581–2594 (2016)
Ijspeert, A.J., Nakanishi, J., Hoffmann, H., Pastor, P., Schaal, S.: Dynamical movement primitives: learning attractor models for motor behaviors. Neural Comput. 25(2), 328–373 (2013)
Kawato, M.: Feedback-errror-learning neural network for supervised motor learning. In: Eckmiller, R. (ed.) Advanced Neural Computers, pp. 365–372. Elsevier, North-Holland (1990)
Kober, J., Wilhelm, A., Oztop, E., Peters, J.: Reinforcement learning to adjust parametrized motor primitives to new situations. Auton. Robots 33(4), 361–379 (2012)
Petrič, T., Colasanto, L., Gams, A., Ude, A., Ijspeert, A.: Bio-inspired learning and database expansion of compliant movement primitives. In: IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids), pp. 346–351, November 2015
Schaal, S., Mohajerian, P., Ijspeert, A.: Dynamics systems vs. optimal control-a unifying view. Prog. Brain Res. 165, 425–445 (2007)
Ude, A., Gams, A., Asfour, T., Morimoto, J.: Task-specific generalization of discrete and periodic dynamic movement primitives. IEEE Trans. Robot. 26(5), 800–815 (2010)
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
Petrič, T., Gams, A. (2017). Effect of Sequence Order on Autonomous Robotic Database Expansion. In: Rodić, A., Borangiu, T. (eds) Advances in Robot Design and Intelligent Control. RAAD 2016. Advances in Intelligent Systems and Computing, vol 540. Springer, Cham. https://doi.org/10.1007/978-3-319-49058-8_44
Download citation
DOI: https://doi.org/10.1007/978-3-319-49058-8_44
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-49057-1
Online ISBN: 978-3-319-49058-8
eBook Packages: EngineeringEngineering (R0)