Abstract
Dynamic systems (DS) methods constitute one of the most commonly employed frameworks for Learning from Demonstration (LfD). The field of LfD aims to enable robots or other agents to learn new skills or behaviors by observing human demonstrations, and DS provide a powerful tool for modeling and reproducing such behaviors. Due to their ability to capture complex and nonlinear patterns of movement, DS have been successfully applied in robotics application. This paper presents a new learning from demonstration method by using the DS. The proposed method ensures that the learned systems achieve global asymptotic stability, a valuable property that guarantees the convergence of the system to an equilibrium point from any initial condition. The original trajectory is initially transformed to a higher-dimensional space and then subjected to a diffeomorphism transformation. This transformation maps the transformed trajectory forward to a straight line that converges towards the zero point. By deforming the trajectories in this way, the resulting system ensures global asymptotic stability for all generated trajectories.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ravichandar, H., Polydoros, A.S., Chernova, S.: Recent advances in robot learning from demonstration. Ann. Rev. Control Robot. Auton. Syst. 3(1), 297ā330 (2020)
Zhang, Y., Cheng, L., Li, H., Cao, R.: Learning accurate and stable point-to-point motions: a dynamic system approach. IEEE Robot. Autom. Lett. 7(2), 1510ā1517 (2022)
Liu, N., Lu, T., Y, Cai., Wang, R., Wang, S.: Manipulation skill learning on multi-step complex task based on explicit and implicit curriculum learning. Sci. China Inf. Sci. 65, 114201 (2022)
Rozo, L., Calinon, S., Caldwell, D.G., Jimenez, P., Torras, C.: Learning physical collaborative robot behaviors from human demonstrations. IEEE Trans. Robot. 32(3), 513ā527 (2016)
Zhang, Y., Cheng, L.: Online adaptive and attention-based reference path generation for upper-limb rehabilitation robot. In: China Automation Congress, pp. 5268ā5273, Beijing, China (2021)
Khansari-Zadeh, S.M., Billard, A.: Learning stable nonlinear dynamical systems with Gaussian mixture models. IEEE Trans. Robot. 27(5), 943ā957 (2011)
Kong, L.H., He, W., Chen, W.S., Zhang, H., Wang, Y.: Dynamic movement primitives based robot skills learning. Mach. Intell. Res. 20, 396ā407 (2023)
Ijspeert, A.J., Nakanishi, J., Hoffmann, H., Pastor, P., Schaal, S.: Dynamical movement primitives: learning attractor models for motor behaviors. Neural Comput. 25(2), 328ā373 (2013)
Ginesi, M., Sansonetto, N., Fiorini, P.: Overcoming some drawbacks of dynamic movement primitives. Robot. Auton. Syst. 144, 103844 (2021)
Li, C., Li, Z., Jiang, Z., Cui, S., Liu, H., Cai, H.: Autonomous planning and control strategy for space manipulators with dynamics uncertainty based on learning from demonstrations. Sci. China Technol. Sci. 64, 2662ā2675 (2021)
Neumann, K., Steil, J.J.: Learning robot motions with stable dynamical systems under diffeomorphic transformations. Robot. Auton. Syst. 70, 1ā15 (2015)
Neumann, K., Lemme, A., Steil, J.J.: Neural learning of stable dynamical systems based on data-driven Lyapunov candidates. In: IEEE International Conference on Intelligent Robots and Systems, pp. 1216ā1222, Tokyo, Japan (2013)
Khansari-Zadeh, S.M., Billard, A.: Learning control Lyapunov function to ensure stability of dynamical system-based robot reaching motions. Robot. Auton. Syst. 62(6), 752ā765 (2014)
Rana, M.A., Li, A., Fox, D., Boots, B., Ramos, F., Ratliff, N.: Euclideanizing flows: diffeomorphic reduction for learning stable dynamical systems. In: 2th International Proceedings on the Conference on Learning for Dynamics and Control, pp. 630ā639, Online (2020)
Zhang, Y., Cheng, L., Cao, R., Li, H., Yang, C.: A neural network based framework for variable impedance skills learning from demonstrations. Robot. Auton. Syst. 160, 104312 (2023)
Zhang, H., Cheng, L., Zhang, Y.: Learning robust point-to-point motions adversarially: a stochastic differential equation approach. IEEE Robot. Autom. Lett. 8(4), 2357ā2364 (2023)
Perrin, N., Schlehuber-Caissier, P.: Fast diffeomorphic matching to learn globally asymptotically stable nonlinear dynamical systems. Syst. Control Lett. 96(6), 51ā59 (2016)
Bishop, C.M.: Pattern Recognition and Machine Learning, 5th edn. Information Science and Statistics, Chapter 6, pp. 291ā294. Springer, New York (2006)
Homepage. https://bitbucket.org/khansari/lasahandwritingdataset/. Accessed 25 Mar 2015
Lam, S.K., Pitrou, A., Seibert, S.: Numba: a LLVM-based Python JIT compiler. In: International Proceedings on the Second Workshop on the LLVM Compiler Infrastructure in HPC, pp. 1ā6, New York, USA (2015)
Acknowledgements
This work is supported by National Key Research and Development Program (Grant No. 2022YFB4703204), National Natural Science Foundation of China (Grant No. 62311530097), and Chinese Academy of Sciences Project for Young Scientists in Basic Research (Grant No. YSBR-034).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
Ā© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Zhang, Y., Han, L., Wang, Z., Xia, X., Li, H., Cheng, L. (2024). Learning Stable Nonlinear Dynamical System fromĀ One Demonstration. In: Luo, B., Cheng, L., Wu, ZG., Li, H., Li, C. (eds) Neural Information Processing. ICONIP 2023. Lecture Notes in Computer Science, vol 14450. Springer, Singapore. https://doi.org/10.1007/978-981-99-8070-3_36
Download citation
DOI: https://doi.org/10.1007/978-981-99-8070-3_36
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-8069-7
Online ISBN: 978-981-99-8070-3
eBook Packages: Computer ScienceComputer Science (R0)