Abstract
Supervised machine learning techniques have proven very effective to solve the problems arising from model learning in robotics. A significant limitation of such approaches is that internal models learned for a specific robot are likely to fail when transferred to a robot with a different morphology. One of the challenges to relate the morphology and the internal model is the difference in the number of parameters that define them. We propose three neural network architectures for solving this problem, along with a case study to evaluate their performance, namely saccadic movements in a robotic head. We generate a huge dataset to test the performance of the proposed architectures. Our results suggest that the best solution is provided by the parallel neural network, due to the fact that the trained weights are independent of one another.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
The same number and kind of morphological parameters but different values.
- 2.
The parameters of the network were calculated previously using cross validation.
References
Sigaud, O., Salan, C., Padois, V.: On-line regression algorithms for learning mechanical models of robots: a survey. Robot. Auton. Syst. 59(12), 1115–1129 (2011)
Siciliano, B., et al.: Robotics: Modelling, Planning and Control. Advanced Textbooks in Control and Signal Processing. Springer, London (2008)
Nguyen-Tuong, D., Peters, J.: Model learning for robot control: a survey. Cogn. Process. 12(4), 319–340 (2011)
Hornik, K.: Approximation capabilities of multilayer feedforward networks. Neural Networks 4(2), 251–257 (1991)
Gupta, M.M., Homma, N., Jin, L., Homma, N.: Static and Dynamic Neural Networks: From Fundamentals to Advanced Theory (2003)
Kikuchi, K., Kobayashi, H.: A study on functional characteristics of robotic system with morphology and intelligence. In: Proceedings of the 2000 IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 733–738 (2000)
Antonelli, M., Duran, A.J., Chinellato, E., del Pobil, A.P.: Learning the visual-oculomotor transformation: effects on saccade control and space representation. Robot. Auton. Syst. 71, 13–22 (2015)
Kawato, M.: Feedback-error-learning neural network for supervised motor learning. In: Eckmiller, R. (ed.) Advanced Neural Computers, pp. 365–372. North-Holland, Amsterdam (1990)
Rahimi, A., Recht, B.: Random features for large-scale kernel machines. In: Advances in neural information processing systems, pp. 1177–1184 (2007)
Gijsberts, A., Metta, G.: Real-time model learning using Incremental Sparse Spectrum Gaussian Process Regression. Neural Networks 41, 59–69 (2013)
Møller, M.F.: A scaled conjugate gradient algorithm for fast supervised learning supervised learning. Neural Networks 6, 525–533 (1993)
Baldi, P.: Autoencoders, Unsupervised Learning, and Deep Architectures. ICML Unsupervised and Transfer Learning, pp. 37–50 (2012)
Rifai, S., Muller, X.: Contractive auto-encoders : explicit invariance during feature extraction. icml 85(1), 833–840 (2011)
Ng, A.: Sparse autoencoder. CS294A Lecture Notes 72, 1–19 (2011)
Acknowledgements
This paper describes research done at the UJI Robotic Intelligence Laboratory. Support for this laboratory is provided in part by Ministerio de Economía y Competitividad (DPI2015-69041-R), by Generalitat Valenciana (PROMETEOII/2014/028) and by Universitat Jaume I (P1-1B2014-52, PREDOC/ 2013/06).
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Duran, A.J., del Pobil, A.P. (2017). Discovering the Relationship Between the Morphology and the Internal Model in a Robot System by Means of Neural Networks. In: Chen, W., Hosoda, K., Menegatti, E., Shimizu, M., Wang, H. (eds) Intelligent Autonomous Systems 14. IAS 2016. Advances in Intelligent Systems and Computing, vol 531. Springer, Cham. https://doi.org/10.1007/978-3-319-48036-7_61
Download citation
DOI: https://doi.org/10.1007/978-3-319-48036-7_61
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-48035-0
Online ISBN: 978-3-319-48036-7
eBook Packages: EngineeringEngineering (R0)