Abstract
We propose a novel framework for learning stabilizable nonlinear dynamical systems for continuous control tasks in robotics. The key idea is to develop a new control-theoretic regularizer for dynamics fitting rooted in the notion of stabilizability, which guarantees that the learned system can be accompanied by a robust controller capable of stabilizing any open-loop trajectory that the system may generate. By leveraging tools from contraction theory, statistical learning, and convex optimization, we provide a general and tractable semi-supervised algorithm to learn stabilizable dynamics, which can be applied to complex underactuated systems. We validated the proposed algorithm on a simulated planar quadrotor system and observed notably improved trajectory generation and tracking performance with the control-theoretic regularized model over models learned using traditional regression techniques, especially when using a small number of demonstration examples. The results presented illustrate the need to infuse standard model-based reinforcement learning algorithms with concepts drawn from nonlinear control theory for improved reliability.
M. Pavone—This work was supported by NASA under the Space Technology Research Grants Program, Grant NNX12AQ43G, and by the King Abdulaziz City for Science and Technology (KACST).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Berkenkamp, F., Turchetta, M., Schoellig, A., Krause, A.: Safe model-based reinforcement learning with stability guarantees. In: Conference on Neural Information Processing Systems (2017)
Chua, K., Calandra, R., McAllister, R., Levine, S.: Deep reinforcement learning in a handful of trials using probabilistic dynamics models. arXiv preprint arXiv:1805.12114 (2018)
Crouch, P.E., van der Schaft, A.J.: Variational and Hamiltonian Control Systems. Springer, Heidelberg (1987)
Deisenroth, M.P., Rasmussen, C.E.: PILCO: a model-based and data-efficient approach to policy search. In: International Conference on Machine Learning, pp. 465–472 (2011)
Fahroo, F., Ross, I.M.: Direct trajectory optimization by a chebyshev pseudospectral method. AIAA J. Guidance Control Dyn. 25(1), 160–166 (2002)
Hettich, R., Kortanek, K.O.: Semi-infinite programming: theory, methods, and applications. SIAM Rev. 35(3), 380–429 (1993)
Khansari-Zadeh, S.M., Billard, A.: Learning stable nonlinear dynamical systems with Gaussian mixture models. IEEE Trans. Rob. 27(5), 943–957 (2011)
Khansari-Zadeh, S.M., Khatib, O.: Learning potential functions from human demonstrations with encapsulated dynamic and compliant behaviors. Auton. Robots 41(1), 45–69 (2017)
Lax, P.: Linear Algebra and its Applications, 2nd edn. Wiley, Hoboken (2007)
Lemme, A., Neumann, K., Reinhart, R.F., Steil, J.J.: Neural learning of vector fields for encoding stable dynamical systems. Neurocomputing 141(1), 3–14 (2014)
Liang, T., Rakhlin, A.: Just interpolate: kernel ridgeless regression can generalize. arXiv preprint arXiv:1808.00387v1 (2018)
Lohmiller, W., Slotine, J.J.E.: On contraction analysis for non-linear systems. Automatica 34(6), 683–696 (1998)
Manchester, I.R., Slotine, J.J.E.: Control contraction metrics: convex and intrinsic criteria for nonlinear feedback design. IEEE Trans. Autom. Control 62, 3046–3053 (2017)
Manchester, I.R., Slotine, J.J.E.: Robust control contraction metrics: a convex approach to nonlinear state-feedback \(H-\infty \) control. IEEE Control Syst. Lett. 2(2), 333–338 (2018)
Manchester, I., Tang, J.Z., Slotine, J.J.E.: Unifying classical and optimization-based methods for robot tracking control with control contraction metrics. In: International Symposium on Robotics Research (2015)
Medina, J.R., Billard, A.: Learning stable task sequences from demonstration with linear parameter varying systems and hidden Markov models. In: Conference on Robot Learning, pp. 175–184 (2017)
Nagabandi, A., Kahn, G., Fearing, R.S., Levine, S.: Neural network dynamics for model-based deep reinforcement learning with model-free fine-tuning. arXiv preprint arXiv:1708.02596 (2017)
Ravichandar, H., Salehi, I., Dani, A.: Learning partially contracting dynamical systems from demonstrations. In: Conference on Robot Learning (2017)
Sanner, R.M., Slotine, J.J.E.: Gaussian networks for direct adaptive control. IEEE Trans. Neural Netw. 3(6), 837–863 (1992)
Sindhwani, V., Tu, S., Khansari, M.: Learning contracting vector fields for stable imitation learning. arXiv preprint arXiv:1804.04878 (2018)
Singh, S., Majumdar, A., Slotine, J.J.E., Pavone, M.: Robust online motion planning via contraction theory and convex optimization. In: Proceedings of the IEEE Conference on Robotics and Automation (2017). Extended Version: http://asl.stanford.edu/wp-content/papercite-data/pdf/Singh.Majumdar.Slotine.Pavone.ICRA17.pdf
Singh, S., Sindhwani, V., Slotine, J.J., Pavone, M.: Learning stabilizable dynamical systems via control contraction metrics. In: Workshop on Algorithmic Foundations of Robotics (2018, in Press). https://arxiv.org/abs/1808.00113
Slotine, J.J.E., Li, W.: On the adaptive control of robot manipulators. Int. J. Robot. Res. 6(3), 49–59 (1987)
Venkatraman, A., Capobianco, R., Pinto, L., Hebert, M., Nardi, D., Bagnell, A.: Improved learning of dynamics models for control. In: International Symposium on Experimental Robotics, pp. 703–713. Springer (2016)
Venkatraman, A., Hebert, M., Bagnell, J.A.: Improving multi-step prediction of learned time series models. In: Proceedings of the AAAI Conference on Artificial Intelligence (2015)
Zhang, L., Wu, S.Y., López, M.A.: A new exchange method for convex semi-infinite programming. SIAM J. Optim. 20(6), 2959–2977 (2010)
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
Singh, S., Sindhwani, V., Slotine, JJ.E., Pavone, M. (2020). Learning Stabilizable Dynamical Systems via Control Contraction Metrics. In: Morales, M., Tapia, L., Sánchez-Ante, G., Hutchinson, S. (eds) Algorithmic Foundations of Robotics XIII. WAFR 2018. Springer Proceedings in Advanced Robotics, vol 14. Springer, Cham. https://doi.org/10.1007/978-3-030-44051-0_11
Download citation
DOI: https://doi.org/10.1007/978-3-030-44051-0_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-44050-3
Online ISBN: 978-3-030-44051-0
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)