mlsanityData to 14 Oct 2026

Model-free tracking control of complex dynamical trajectories with machine learning

arXiv 2309.11470 ↗First posted 20 Sep 2023cs.RO cs.LG math.DScited by 13

Not on the map. Why?

Abstract (arXiv)

Nonlinear tracking control enabling a dynamical system to track a desired trajectory is fundamental to robotics, serving a wide range of civil and defense applications. In control engineering, designing tracking control requires complete knowledge of the system model and equations. We develop a model-free, machine-learning framework to control a two-arm robotic manipulator using only partially observed states, where the controller is realized by reservoir computing. Stochastic input is exploited for training, which consists of the observed partial state vector as the first and its immediate future as the second component so that the neural machine regards the latter as the future state of the former. In the testing (deployment) phase, the immediate-future component is replaced by the desired observational vector from the reference trajectory. We demonstrate the effectiveness of the control framework using a variety of periodic and chaotic signals, and establish its robustness against measurement noise, disturbances, and uncertainties.

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Builds on 11 of its 77 references that are in the map. First posted on arXiv 20 Sep 2023.

Builds on

11 of 77 references.

References · 11

  1. 2021Next Generation Reservoir Computingcited by 160
  2. 2018A Tour of Reinforcement Learning: The View from Continuous Controlcited by 151
  3. 2020Machine learning prediction of critical transition and system collapsecited by 54
  4. 2019Machine Learning from a Continuous Viewpointcited by 50
  5. 2019Model-free prediction of spatiotemporal dynamical systems with recurrent neural networks: Role of network spectral radiuscited by 34
  6. 2021Anticipating synchronization with machine learningcited by 22
  7. 2020Model-Free Control of Dynamical Systems with Deep Reservoir Computingcited by 12
  8. 2016Structure-based control of complex networks with nonlinear dynamicscited by 2
  9. 2019Irrelevance of linear controllability to nonlinear dynamical networkscited by 2
  10. 2020Machine Learning and Control Theorycited by 2
  11. 2017Locally Optimal Control of Complex Networkscited by 1

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 9; 2025: 3.

13 papers.

Sort:

  1. 2024Controlling Chaos Using Edge Computing Hardwarecited by 11
  2. 2024Data-driven model discovery with Kolmogorov-Arnold networkscited by 9
  3. 2024Kolmogorov-Arnold Network Autoencoderscited by 8
  4. 2023Machine-learning parameter tracking with partial state observationcited by 4
  5. 2024Conservation-informed Graph Learning for Spatiotemporal Dynamics Predictioncited by 4
  6. 2025Unsupervised learning for anticipating critical transitionscited by 4
  7. 2025Confabulation dynamics in a reservoir computer: Filling in the gaps with untrained attractorscited by 4
  8. 2024Learning to learn ecosystems from limited data -- a meta-learning approachcited by 2
  9. 2024Reconstructing dynamics from sparse observations with no training on target systemcited by 2
  10. 2024Temporal Convolution Derived Multi-Layered Reservoir Computingcited by 1
  11. 2024Machine learning approach to detect dynamical states from recurrence measurescited by 0
  12. 2024Tree-based Learning for High-Fidelity Prediction of Chaoscited by 0
1 more
  1. 2025Deficiency of equation-finding approach to data-driven modeling of dynamical systemscited by 0