Abstract
We present a full variational treatment of the Coupled Gaussian Process Dynamical Model (CGPDM) with non-marginalized coupling mappings. The CGPDM generates high-dimensional trajectories from coupled low-dimensional latent dynamical models. The deterministic variational treatment obviates the need for sampling and facilitates the use of the CGPDM on larger data sets. The non-marginalized coupling mappings allow for a flexible exchange of the constituent dynamics models at run time. This exchange possibility is crucial for the construction of modular movement primitive models. We test the model against the marginalized CGPDM, dynamic movement primitives and temporal movement primitives, finding that the CGPDM generally outperforms the other models. Human observers can hardly distinguish CGPDM-generated movements from real human movements.
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
Similar content being viewed by others
Notes
- 1.
Available at http://uni-marburg.de/wk8Vf or from the authors.
References
Bastien, F., Lamblin, P., Pascanu, R., Bergstra, J., Goodfellow, I.J., Bergeron, A., Bouchard, N., Bengio, Y.: Theano: new features and speed improvements. In: Deep Learning and Unsupervised Feature Learning NIPS Workshop (2012)
Bauer, M., van der Wilk, M., Rasmussen, C.: Understanding probabilistic sparse Gaussian process approximations. Technical report, arXiv:1606.04820 (2016)
Bishop, C.M.: Pattern Recognition and Machine Learning (Information Science and Statistics). Springer, New York (2006)
Bizzi, E., Cheung, V., d’Avella, A., Saltiel, P., Tresch, M.: Combining modules for movement. Brain Res. Rev. 57(1), 125–133 (2008)
Clever, D., Harant, M., Koch, K.H., Mombaur, K., Endres, D.M.: A novel approach for the generation of complex humanoid walking sequences based on a combination of optimal control and learning of movement primitives. Rob. Aut. Sys. 83, 287–298 (2016). doi:10.1016/j.robot.2016.06.001
Frigola, R., Chen, Y., Rasmussen, C.: Variational Gaussian process state-space models. In: Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N., Weinberger, K. (eds.) Advances in NIPS, vol. 27, pp. 3680–3688 (2014)
Giese, M.A., Mukovskiy, A., Park, A.-N., Omlor, L., Slotine, J.-J.E.: Real-time synthesis of body movements based on learned primitives. In: Cremers, D., Rosenhahn, B., Yuille, A.L., Schmidt, F.R. (eds.) Statistical and Geometrical Approaches to Visual Motion Analysis. LNCS, vol. 5604, pp. 107–127. Springer, Heidelberg (2009). doi:10.1007/978-3-642-03061-1_6
Hinton, G.E.: Products of experts. In: Proceedings of ICANN 1999, vol. 1, pp. 1–6 (1999)
Ijspeert, A.J., Nakanishi, J., Hoffmann, H., Pastor, P., Schaal, S.: Dynamical movement primitives: learning attractor models for motor behaviors. Neu. Comp. 25(2), 328–373 (2013)
Jones, E., Oliphant, T., Peterson, P., et al.: SciPy: Open source scientific tools for Python (2001). http://www.scipy.org/. Accessed 9 Oct 2015
Mattos, C.L.C., Dai, Z., Damianou, A., Forth, J., Barreto, G.A., Lawrence, N.D.: Recurrent Gaussian processes. Technical report, arXiv:1511.06644 (2016)
Paraschos, A., Daniel, C., Peters, J., Neumann, G.: Probabilistic movement primitives. In: Burges, C., Bottou, L., Welling, M., Ghahramani, Z., Weinberger, K. (eds.) Advances in NIPS, vol. 26, pp. 2616–2624 (2013)
Pastor, P., Kalakrishnan, M., Righetti, L., Schaal, S.: Towards associative skill memories. In: IEEE-RAS International Conference on Humanoid Robots, pp. 309–315 (2012)
Sakoe, H., Chiba, S.: Dynamic programming algorithm optimization for spoken word recognition. IEEE Trans. Acoust. Speech Sig. Proc. 26(1), 43–49 (1978)
Taubert, N., Christensen, A., Endres, D., Giese, M.: Online simulation of emotional interactive behaviors with hierarchical Gaussian process dynamical models. In: Proceedings of the ACM SAP, pp. 25–32. ACM (2012)
Titsias, M.K., Lawrence, N.D.: Bayesian Gaussian process latent variable model. In: Proceedings of the 13th AISTATS, pp. 844–851 (2010)
Velychko, D., Endres, D., Taubert, N., Giese, M.A.: Coupling Gaussian process dynamical models with product-of-experts kernels. In: Wermter, S., Weber, C., Duch, W., Honkela, T., Koprinkova-Hristova, P., Magg, S., Palm, G., Villa, A.E.P. (eds.) ICANN 2014. LNCS, vol. 8681, pp. 603–610. Springer, Cham (2014). doi:10.1007/978-3-319-11179-7_76
Wang, J.M., Fleet, D.J., Hertzmann, A.: Gaussian process dynamical models for human motion. IEEE Trans. Pattern Anal. Mach. Intell. 30(2), 283–298 (2008)
Acknowledgements
DFG-IRTG 1901 ‘The Brain in Action’, DFG-SFB-TRR 135 project C06. We thank Olaf Haag for help with rendering the movies, and Björn Büdenbender for assistance with MoCap.
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
Velychko, D., Knopp, B., Endres, D. (2017). The Variational Coupled Gaussian Process Dynamical Model. In: Lintas, A., Rovetta, S., Verschure, P., Villa, A. (eds) Artificial Neural Networks and Machine Learning – ICANN 2017. ICANN 2017. Lecture Notes in Computer Science(), vol 10613. Springer, Cham. https://doi.org/10.1007/978-3-319-68600-4_34
Download citation
DOI: https://doi.org/10.1007/978-3-319-68600-4_34
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-68599-1
Online ISBN: 978-3-319-68600-4
eBook Packages: Computer ScienceComputer Science (R0)