Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
162 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 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

Learning Control-Oriented Dynamical Structure from Data (2302.02529v2)

Published 6 Feb 2023 in eess.SY, cs.LG, cs.RO, and cs.SY

Abstract: Even for known nonlinear dynamical systems, feedback controller synthesis is a difficult problem that often requires leveraging the particular structure of the dynamics to induce a stable closed-loop system. For general nonlinear models, including those fit to data, there may not be enough known structure to reliably synthesize a stabilizing feedback controller. In this paper, we discuss a state-dependent nonlinear tracking controller formulation based on a state-dependent Riccati equation for general nonlinear control-affine systems. This formulation depends on a nonlinear factorization of the system of vector fields defining the control-affine dynamics, which always exists under mild smoothness assumptions. We propose a method for learning this factorization from a finite set of data. On a variety of simulated nonlinear dynamical systems, we empirically demonstrate the efficacy of learned versions of this controller in stable trajectory tracking. Alongside our learning method, we evaluate recent ideas in jointly learning a controller and stabilizability certificate for known dynamical systems; we show experimentally that such methods can be frail in comparison.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (42)
  1. Formal synthesis of Lyapunov neural networks. IEEE Control Systems Letters, 5(3):773–778, 2021. doi: 10.1109/LCSYS.2020.3005328.
  2. Acarman, T. Nonlinear optimal integrated vehicle control using individual braking torque and steering angle with on-line control allocation by using state-dependent Riccati equation technique. Vehicle System Dynamics, 47(2):157–177, 2009. doi: 10.1080/00423110801932670.
  3. Ailon, A. Simple tracking controllers for autonomous VTOL aircraft with bounded inputs. IEEE Transactions on Automatic Control, 55(3):737–743, 2010.
  4. CasADi: A software framework for nonlinear optimization and optimal control. Mathematical Programming Computation, 11(1):1–36, 2019.
  5. Reduced order modeling and control of thin film growth in an HPCVD reactor. SIAM Journal on Applied Mathematics, 62(4):1251–1280, 2002.
  6. Learning stability certificates from data. In Conf. on Robot Learning, 2020.
  7. JAX: Composable transformations of Python+NumPy programs, 2018. Available at http://github.com/google/jax.
  8. Çimen, T. Systematic and effective design of nonlinear feedback controllers via the state-dependent Riccati equation (SDRE) method. Annual Reviews in Control, 34(1):32–51, 2010. doi: 10.1016/j.arcontrol.2010.03.001.
  9. Çimen, T. Survey of state-dependent Riccati equation in nonlinear optimal feedback control synthesis. AIAA Journal of Guidance, Control, and Dynamics, 35(4):1025–1047, 2012. doi: 10.2514/1.55821.
  10. Stabilizing neural control using self-learned almost Lyapunov critics. In Proc. IEEE Conf. on Robotics and Automation, 2021.
  11. Neural Lyapunov control. In Conf. on Neural Information Processing Systems, 2019.
  12. Cloutier, J. R. State-dependent Riccati equation techniques: An overview. In American Control Conference, 1997.
  13. Hypersonic guidance via the state-dependent Riccati equation control method. In IEEE Conf. on Control Applications, 1999.
  14. Safe nonlinear control using robust neural Lyapunov-barrier functions. In Conf. on Robot Learning, 2021.
  15. Safe control with learned certificates: A survey of neural Lyapunov, barrier, and contraction methods. Available at https://arxiv.org/abs/2202.11762, 2022.
  16. Neural networks with physics-informed architectures and constraints for dynamical systems modeling. In Learning for Dynamics & Control, 2022.
  17. Structured mechanical models for robot learning and control. In Learning for Dynamics & Control, 2020.
  18. Nonlinear control design for slightly non-minimum phase systems: Application to V/STOL aircraft. Automatica, 28(4):665–679, 1992.
  19. Adam: A method for stochastic optimization. In Int. Conf. on Learning Representations, 2015.
  20. Safe active dynamics learning and control: A sequential exploration-exploitation framework. IEEE Transactions on Robotics, 38(5):2888–2907, 2022.
  21. Safe autonomous navigation for systems with learned SE(3) Hamiltonian dynamics. In Learning for Dynamics & Control, 2022.
  22. On contraction analysis for non-linear systems. Automatica, 34(6):683–696, 1998.
  23. Control contraction metrics: Convex and intrinsic criteria for nonlinear feedback design. IEEE Transactions on Automatic Control, 62(6):3046–3053, 2017.
  24. Learning stable deep dynamics models. In Conf. on Neural Information Processing Systems, 2019.
  25. A Mathematical Introduction to Robotic Manipulation. CRC Press, 1 edition, 1994.
  26. Recurrent equilibrium networks: Unconstrained learning of stable and robust dynamical models. In Proc. IEEE Conf. on Decision and Control, 2021. doi: 10.1109/CDC45484.2021.9683054.
  27. The Lyapunov neural network: Adaptive stability certification for safe learning of dynamical systems. In Conf. on Robot Learning, 2018.
  28. Adaptive-control-oriented meta-learning for nonlinear systems. In Robotics: Science and Systems, 2021.
  29. Control-oriented meta-learning. Int. Journal of Robotics Research, 2023. In press.
  30. Learning contracting vector fields for stable imitation learning. Available at https://arxiv.org/abs/1804.04878, 2018.
  31. Robust feedback motion planning via contraction theory. Int. Journal of Robotics Research, 2019. Submitted.
  32. Learning stabilizable nonlinear dynamics with contraction-based regularization. Int. Journal of Robotics Research, 40(10–11):1123–1150, 2021.
  33. On the adaptive control of robot manipulators. Int. Journal of Robotics Research, 6(3):49–59, 1987.
  34. Applied Nonlinear Control. Prentice Hall, 1991.
  35. Learning certified control using contraction metric. In Conf. on Robot Learning, 2020.
  36. Neural stochastic contraction metrics for learning-based control and estimation. IEEE Control Systems Letters, 5(5):1825–1830, 2021a.
  37. Contraction theory for nonlinear stability analysis and learning-based control: A tutorial overview. Annual Reviews in Control, 52:135–169, 2021b.
  38. On the implementation of an interior-point filter line-search algorithm for large-scale nonlinear programming. Mathematical Programming, 106:25–57, 2006.
  39. Control strategy for a snake-like robot based on constraint force and verification by experiment. In IEEE/RSJ Int. Conf. on Intelligent Robots & Systems, 2008.
  40. A new exchange method for convex semi-infinite programming. SIAM Journal on Optimization, 20(6):2959–2977, 2010.
  41. Symplectic ODE-Net: Learning Hamiltonian dynamics with control. In Int. Conf. on Learning Representations, 2020.
  42. Neural Lyapunov control of unknown nonlinear systems with stability guarantees. In Conf. on Neural Information Processing Systems, 2022.
Citations (5)
View on Semantic Scholar

Summary

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

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