Abstract
We propose a model for learning robot task constrained movements from a finite number of observed human demonstrations. The model uses the variation between demonstrations to extract important parts of the movements and reproduce trajectories accordingly. Regions with low variability are reproduced in a constrained manner, while regions with higher variability are approximated more loosely to achieve shorter trajectories. The demonstrations are sampled into states and an initial state sequence is chosen by a minimum distance criterion. Then, a method for state variation analysis is proposed that weights the states according to its similarity to all the other states. A custom function is constructed based on the state-variability information. The time function is then coupled with a state driven dynamical system to reproduce the trajectories. We test the approach on typical two-dimensional task constrained trajectories with constrains on the beginning, in the middle and the end of the movement. The approach is further compared with the case of using a standard exponentially decayed time function.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Calinon, S., Li, Z., Alizadeh, T., Tsagarakis, G.N., Caldwell, G.D.: Statistical dynamical system for skill acquisition in humanoids. In: 12th IEEE-RAS International Conference on Humanoid Robots, pp. 323–329. IEEE, Osaka (2012)
Mülling, K., Kober, J., Kroemer, O., Peters, J.: Learning to select and generalize striking movements in robot table tennis. Int. J. Robot. Res. 32(3), 263–279 (2013)
Theodorou, E., Buchli, J., Schaal, S.: Learning policy improvements with path integrals. In: PMLR, Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, Sardinia, Italy, vol. 9, pp. 828–835 (2010)
Nair, A., McGrew, B., Andrychowicz, M., Zaremba, W., Abbeel, P.: Overcoming exploration in reinforcement learning with demonstrations. In: 2018 IEEE International Conference on Robotics and Automation (ICRA), Brisbane, Australia (2018). https://doi.org/10.1109/icra.2018.8463162
Švaco, M., Jerbić, B., Polančec, M., Šuligoj, F.: A reinforcement learning based algorithm for robot action planning. In: Proceedings of the 27th International Conference on Robotics in Alpe-Adria Danube Region, RAAD (2018)
Calinon, S., Guenter, F., Billard, A.: On learning, representing, and generalizing a task in a humanoid robot. IEEE Trans. Syst. Man Cybern. Part B (Cybernetics) 37(2), 286–298 (2007)
Hewitt, A., Yang, C., Li, Y., Cui, R.: DMP and GMR based teaching by demonstration for a KUKA LBR robot. In: 2017 23rd International Conference on Automation and Computing (ICAC), pp. 1–6. IEEE, Huddersfield (2017)
Calinon, S., Sardellitti, I., Caldwell, D.G.: Learning-based control strategy for safe human-robot interaction exploiting task and robot redundancies. In: IEEE/RSJ International Conference on Intelligent Robots and Systems, Taipei (2010)
Stulp, F., Raiola, G., Hoarau, A., Ivaldi, S., Sigaud, O.: Learning compact parameterized skills with a single regression. In: 13th IEEE-RAS International Conference on Humanoid Robots (Humanoids), pp. 417–422. IEEE, Atlanta (2013)
Forte, D., Gams, A., Morimoto, J., Ude, A.: On-line motion synthesis and adaptation using a trajectory database. Robot. Auton. Syst. 60(10), 1327–1339 (2012)
Figueroa, N., Pais Ureche, A.L., Billard, A.: Learning complex sequential tasks from demonstration: A pizza dough rolling case study. In: The Eleventh ACM/IEEE International Conference on Human Robot Interaction, pp. 611–612. IEEE, Christchurch (2016)
Pervez, A., Lee, D.: Learning task-parameterized dynamic movement primitives using mixture of GMMs. Intel. Serv. Robot. 11(1), 61–78 (2018)
Ijspeert, J.A., Nakanishi, J., Schaal, S.G.: Trajectory formation for imitation with nonlinear dynamical systems. In: International Conference on Intelligent Robots and Systems (IROS), pp. 752–757. IEEE, Maui (2001)
Schaal, S., Mohajerian, P., Ijspeert, J.: Dynamics systems vs. optimal control a unifying view. Prog. Brain Res. 165, 425–445 (2007)
Ijspeert, A., Nakanishi, J., Hoffmann, H., Pastor, P., Schaal, S.: Dynamical movement primitives: learning attractor models for motor behaviors. Neural Comput. 25(2), 328–373 (2013)
Acknowledgments
Authors would like to acknowledge the Croatian Scientific Foundation through the “Young researchers’ career development project – training of new doctoral students”.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Vidaković, J., Jerbić, B., Šekoranja, B., Švaco, M., Šuligoj, F. (2020). Task Dependent Trajectory Learning from Multiple Demonstrations Using Movement Primitives. In: Berns, K., Görges, D. (eds) Advances in Service and Industrial Robotics. RAAD 2019. Advances in Intelligent Systems and Computing, vol 980. Springer, Cham. https://doi.org/10.1007/978-3-030-19648-6_32
Download citation
DOI: https://doi.org/10.1007/978-3-030-19648-6_32
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-19647-9
Online ISBN: 978-3-030-19648-6
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)