publication . Other literature type . Article . Preprint . Conference object . 2019

Uncertainty-Aware Imitation Learning using Kernelized Movement Primitives

Silverio, J.; Huang, Y.; Abu-Dakka, F. J.; Rozo, L.; Caldwell, D. G.;
Open Access English
  • Published: 30 Sep 2019
  • Publisher: Zenodo
Abstract
During the past few years, probabilistic approaches to imitation learning have earned a relevant place in the literature. One of their most prominent features, in addition to extracting a mean trajectory from task demonstrations, is that they provide a variance estimation. The intuitive meaning of this variance, however, changes across different techniques, indicating either variability or uncertainty. In this paper we leverage kernelized movement primitives (KMP) to provide a new perspective on imitation learning by predicting variability, correlations and uncertainty about robot actions. This rich set of information is used in combination with optimal controll...
Subjects
free text keywords: 213 Electronic, automation and communications engineering, electronics, 113 Computer and information sciences, Computer Science - Robotics, Computer Science - Machine Learning, Leverage (finance), Single model, Variance estimation, Robotics, Artificial intelligence, business.industry, business, Probabilistic logic, Robot, Computer vision, Trajectory, Imitation learning, Computer science
Funded by
EC| CoLLaboratE
Project
CoLLaboratE
Co-production CeLL performing Human-Robot Collaborative AssEmbly
  • Funder: European Commission (EC)
  • Project Code: 820767
  • Funding stream: H2020 | RIA
Zenodo
Other literature type . 2019
Provider: Datacite
ZENODO
Article . 2019
Provider: ZENODO
Zenodo
Other literature type . 2019
Provider: Datacite
Zenodo
Other literature type . 2019
Provider: Datacite
22 references, page 1 of 2

[1] B. D. Argall, S. Chernova, M. Veloso, and B. Browning, “A survey of robot learning from demonstration,” Robotics and Autonomous Systems, vol. 57, no. 5, pp. 469-483, May 2009.

[2] A. Ijspeert, J. Nakanishi, P. Pastor, H. Hoffmann, and S. Schaal, “Dynamical movement primitives: Learning attractor models for motor behaviors,” Neural Computation, no. 25, pp. 328-373, 2013. [OpenAIRE]

[3] S. Calinon, D. Bruno, and D. G. Caldwell, “A task-parameterized probabilistic model with minimal intervention control,” in Proc. IEEE Intl Conf. on Robotics and Automation (ICRA), Hong Kong, China, May-June 2014, pp. 3339-3344.

[4] A. Paraschos, C. Daniel, J. Peters, and G. Neumann, “Probabilistic movement primitives,” in Advances in Neural Information Processing Systems (NIPS), 2013, pp. 2616-2624.

[5] Y. Huang, L. Rozo, J. Silve´rio, and D. G. Caldwell, “Non-parametric imitation learning of robot motor skills,” in Proc. IEEE Intl Conf. on Robotics and Automation (ICRA), Montreal, Canada, May 2019, (to appear). [OpenAIRE]

[6] Y. Huang, L. Rozo, J. Silve´rio, and D. G. Caldwell, “Kernelized movement primitives,” arXiv:1708.08638v2 [cs.RO], July 2017.

[7] J. Silve´rio, Y. Huang, L. Rozo, S. Calinon, and D. G. Caldwell, “Probabilistic learning of torque controllers from kinematic and force constraints,” in Proc. IEEE/RSJ Intl Conf. on Intelligent Robots and Systems (IROS), Madrid, Spain, October 2018, pp. 6552-6559.

[8] J. Silve´rio, Y. Huang, L. Rozo, and D. G. Caldwell, “An uncertaintyaware minimal intervention control strategy learned from demonstrations,” in Proc. IEEE/RSJ Intl Conf. on Intelligent Robots and Systems (IROS), Madrid, Spain, October 2018, pp. 6065-6071.

[9] C. E. Rasmussen and C. K. I. Williams, Gaussian processes for machine learning. Cambridge, MA, USA: MIT Press, 2006.

[10] J. R. Medina, D. Lee, and S. Hirche, “Risk-sensitive optimal feedback control for haptic assistance,” in Proc. IEEE Intl Conf. on Robotics and Automation (ICRA), May 2012, pp. 1025-1031.

[11] L. Rozo, D. Bruno, S. Calinon, and D. G. Caldwell, “Learning optimal controllers in human-robot cooperative transportation tasks with position and force constraints,” in Proc. IEEE/RSJ Intl Conf. on Intelligent Robots and Systems (IROS), Hamburg, Germany, Sept.-Oct. 2015, pp. 1024-1030. [OpenAIRE]

[12] D. Fox, W. Burgard, F. Dellaert, and S. Thrun, “Monte carlo localization: Efficient position estimation for mobile robots,” in Proc. AAAI Conference on Artificial Intelligence, 1999, pp. 343-349. [OpenAIRE]

[13] J. R. Medina and S. Hirche, “Uncertainty-dependent optimal control for robot control considering high-order cost statistics,” in Proc. IEEE/RSJ Intl Conf. on Intelligent Robots and Systems (IROS), Hamburg, Germany, September-October 2015, pp. 3995-4002.

[14] R. Calandra, A. Seyfarth, J. Peters, and M. P. Deisenroth, “Bayesian optimization for learning gaits under uncertainty,” Annals of Mathematics and Artificial Intelligence, vol. 76, no. 1, pp. 5-23, February 2016.

[15] P. W. Goldberg, C. K. Williams, and C. M. Bishop, “Regression with input-dependent noise: A Gaussian process treatment,” in Advances in Neural Information Processing Systems (NIPS), 1998, pp. 493-499.

22 references, page 1 of 2
Powered by OpenAIRE Open Research Graph
Any information missing or wrong?Report an Issue
publication . Other literature type . Article . Preprint . Conference object . 2019

Uncertainty-Aware Imitation Learning using Kernelized Movement Primitives

Silverio, J.; Huang, Y.; Abu-Dakka, F. J.; Rozo, L.; Caldwell, D. G.;