Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
133 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Structured Deep Neural Network-Based Backstepping Trajectory Tracking Control for Lagrangian Systems (2403.00381v3)

Published 1 Mar 2024 in cs.RO, cs.LG, cs.SY, and eess.SY

Abstract: Deep neural networks (DNN) are increasingly being used to learn controllers due to their excellent approximation capabilities. However, their black-box nature poses significant challenges to closed-loop stability guarantees and performance analysis. In this paper, we introduce a structured DNN-based controller for the trajectory tracking control of Lagrangian systems using backing techniques. By properly designing neural network structures, the proposed controller can ensure closed-loop stability for any compatible neural network parameters. In addition, improved control performance can be achieved by further optimizing neural network parameters. Besides, we provide explicit upper bounds on tracking errors in terms of controller parameters, which allows us to achieve the desired tracking performance by properly selecting the controller parameters. Furthermore, when system models are unknown, we propose an improved Lagrangian neural network (LNN) structure to learn the system dynamics and design the controller. We show that in the presence of model approximation errors and external disturbances, the closed-loop stability and tracking control performance can still be guaranteed. The effectiveness of the proposed approach is demonstrated through simulations.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (30)
  1. S. N. Kumpati, P. Kannan et al., “Identification and control of dynamical systems using neural networks,” IEEE Transactions on neural networks, vol. 1, no. 1, pp. 4–27, 1990.
  2. D. Rolnick and M. Tegmark, “The power of deeper networks for expressing natural functions,” in International Conference on Learning Representations, 2018.
  3. H. W. Lin, M. Tegmark, and D. Rolnick, “Why does deep and cheap learning work so well?” Journal of Statistical Physics, vol. 168, pp. 1223–1247, 2017.
  4. T. Poggio, H. Mhaskar, L. Rosasco, B. Miranda, and Q. Liao, “Why and when can deep-but not shallow-networks avoid the curse of dimensionality: a review,” International Journal of Automation and Computing, vol. 14, no. 5, pp. 503–519, 2017.
  5. B. Bauer and M. Kohler, “On deep learning as a remedy for the curse of dimensionality in nonparametric regression,” The Annals of Statistics, vol. 47, no. 4, pp. pp. 2261–2285, 2019.
  6. A. Punjani and P. Abbeel, “Deep learning helicopter dynamics models,” in 2015 IEEE International Conference on Robotics and Automation (ICRA), 2015, pp. 3223–3230.
  7. M. Lutter, C. Ritter, and J. Peters, “Deep lagrangian networks: Using physics as model prior for deep learning,” in International Conference on Learning Representations, 2018.
  8. M. Cranmer, S. Greydanus, S. Hoyer, P. Battaglia, D. Spergel, and S. Ho, “Lagrangian neural networks,” in ICLR 2020 Workshop on Integration of Deep Neural Models and Differential Equations, 2020.
  9. N. Takeishi and Y. Kawahara, “Learning dynamics models with stable invariant sets,” in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, no. 11, 2021, pp. 9782–9790.
  10. S. Sanyal and K. Roy, “Ramp-net: A robust adaptive mpc for quadrotors via physics-informed neural network,” in 2023 IEEE International Conference on Robotics and Automation (ICRA).   IEEE, 2023, pp. 1019–1025.
  11. K. Y. Chee, T. Z. Jiahao, and M. A. Hsieh, “Knode-mpc: A knowledge-based data-driven predictive control framework for aerial robots,” IEEE Robotics and Automation Letters, vol. 7, no. 2, pp. 2819–2826, 2022.
  12. L. Bauersfeld, E. Kaufmann, P. Foehn, S. Sun, and D. Scaramuzza, “Neurobem: Hybrid aerodynamic quadrotor model,” Proceedings of Robotics: Science and Systems XVII, p. 42, 2021.
  13. C. Dawson, S. Gao, and C. Fan, “Safe control with learned certificates: A survey of neural lyapunov, barrier, and contraction methods for robotics and control,” IEEE Transactions on Robotics, 2023.
  14. Y.-C. Chang, N. Roohi, and S. Gao, “Neural lyapunov control,” Advances in neural information processing systems, vol. 32, 2019.
  15. N. Gaby, F. Zhang, and X. Ye, “Lyapunov-net: A deep neural network architecture for lyapunov function approximation,” in 2022 IEEE 61st Conference on Decision and Control (CDC).   IEEE, 2022, pp. 2091–2096.
  16. S. M. Richards, F. Berkenkamp, and A. Krause, “The lyapunov neural network: Adaptive stability certification for safe learning of dynamical systems,” in Proceedings of The 2nd Conference on Robot Learning, ser. Proceedings of Machine Learning Research, A. Billard, A. Dragan, J. Peters, and J. Morimoto, Eds., vol. 87.   PMLR, 29–31 Oct 2018, pp. 466–476.
  17. R. Zhou, T. Quartz, H. De Sterck, and J. Liu, “Neural lyapunov control of unknown nonlinear systems with stability guarantees,” Advances in Neural Information Processing Systems, vol. 35, pp. 29 113–29 125, 2022.
  18. H. Dai, B. Landry, L. Yang, M. Pavone, and R. Tedrake, “Lyapunov-stable neural-network control,” in Proceedings of Robotics: Science and Systems, Virtual, July 2021.
  19. W. Jin, Z. Wang, Z. Yang, and S. Mou, “Neural certificates for safe control policies,” arXiv preprint arXiv:2006.08465, 2020.
  20. L. Xu, M. Zakwan, and G. Ferrari-Trecate, “Neural energy casimir control for port-hamiltonian systems,” in 2022 IEEE 61st Conference on Decision and Control (CDC).   IEEE, 2022, pp. 4053–4058.
  21. L. Furieri, C. L. Galimberti, M. Zakwan, and G. Ferrari-Trecate, “Distributed neural network control with dependability guarantees: a compositional port-hamiltonian approach,” in Learning for Dynamics and Control Conference.   PMLR, 2022, pp. 571–583.
  22. S. A. Khader, H. Yin, P. Falco, and D. Kragic, “Learning deep energy shaping policies for stability-guaranteed manipulation,” IEEE Robotics and Automation Letters, vol. 6, no. 4, pp. 8583–8590, 2021.
  23. S. Massaroli, M. Poli, F. Califano, J. Park, A. Yamashita, and H. Asama, “Optimal energy shaping via neural approximators,” SIAM Journal on Applied Dynamical Systems, vol. 21, no. 3, pp. 2126–2147, Sep. 2022.
  24. S. Sánchez-Escalonilla, R. Reyes-Báez, and B. Jayawardhana, “Stabilization of underactuated systems of degree one via neural interconnection and damping assignment – passivity based control,” in 2022 IEEE 61st Conference on Decision and Control (CDC), Dec. 2022, pp. 2463–2468.
  25. Q. Hu, L. Xu, and A. Zhang, “Adaptive backstepping trajectory tracking control of robot manipulator,” Journal of the Franklin Institute, vol. 349, no. 3, pp. 1087–1105, 2012.
  26. B. Amos, L. Xu, and J. Z. Kolter, “Input convex neural networks,” in International Conference on Machine Learning.   PMLR, 2017, pp. 146–155.
  27. A. G. Baydin, B. A. Pearlmutter, A. A. Radul, and J. M. Siskind, “Automatic differentiation in machine learning: a survey,” The Journal of Machine Learning Research, vol. 18, no. 1, pp. 5595–5637, 2017.
  28. J. Z. Kolter and G. Manek, “Learning stable deep dynamics models,” Advances in neural information processing systems, vol. 32, 2019.
  29. E. Todorov, T. Erez, and Y. Tassa, “Mujoco: A physics engine for model-based control,” in 2012 IEEE/RSJ international conference on intelligent robots and systems.   IEEE, 2012, pp. 5026–5033.
  30. D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” in 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings, Y. Bengio and Y. LeCun, Eds., 2015.
Citations (1)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets