Deep Neural Network-Based Approximate Optimal Tracking for Unknown Nonlinear Systems

Greene, Max L.; Bell, Zachary I.; Nivison, Scott; Dixon, Warren E.

doi:10.1109/tac.2023.3246761

Cited by 20 publications

(5 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Concurrent learning has been incorporated into other control frameworks beyond the conventional adaptive control to enhance learning and control performance [48], [50], [63]- [76]. In [63], concurrent learning was employed for plant model learning to enhance the performance of model predictive control.…”

Section: Discrete Data-driven Mrementioning

confidence: 99%

“…The extensions of concurrent learning to the neural network (NN) control of nonlinear systems with unstructured uncertainties were done in [48], [50], [66]- [71]. Concurrent learning was incorporated into adaptive dynamic programming and reinforcement learning for developing adaptive optimal control methods in [72]- [76].…”

Section: Discrete Data-driven Mrementioning

confidence: 99%

“…The way of exploiting online data memory gives rise to four different data memory-driven parameter estimation schemes in adaptive systems, including forgetting-data MRE [19]- [38], fulldata MRE [39]- [45], discrete-data MRE [46]- [76], and intervaldata MRE [77]- [126]. This article overviews the four MRE schemes in adaptive systems from a historical perspective.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Adaptive Estimation and Control With Online Data Memory: A Historical Perspective

Pan,

Shi

2024

IEEE Control Syst. Lett.

View full text Add to dashboard Cite

Online data memory is essential for adaptive estimation and control as it can enhance the performance and robustness of adaptive systems compared to adaptive systems without data memory. We provide an overview of four data memory-driven parameter estimation schemes for adaptive systems from a historical perspective, including forgetting-data memory regression extension (MRE), full-data MRE, discrete-data MRE, and interval-data MRE. For clear presentation and better understanding, a general class of nonlinear systems with linear-in-the-parameter uncertainties is applied as a unifying framework to demonstrate the motivation, synthesis, and characteristics of each MRE scheme for parameter estimation in adaptive control. Intensive comparisons of the four MRE schemes are provided to reveal their technical natures, and real-world applications are discussed to show their practicability. It is concluded that all the MRE schemes can achieve exponential parameter convergence under relaxed excitation conditions rather than the classical condition of persistent excitation which is too stringent to satisfy in practice. The distinctive features of intervaldata MRE termed composite learning are highlighted with respect to computational simplicity, estimation accuracy, robustness against perturbations, and widespread real-world applications to robot learning and control. Possible directions for future research in this area are suggested to conclude this survey.

show abstract

Section: Discrete Data-driven Mrementioning

confidence: 99%

Section: Discrete Data-driven Mrementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Adaptive Estimation and Control With Online Data Memory: A Historical Perspective

Pan,

Shi

2024

IEEE Control Syst. Lett.

View full text Add to dashboard Cite

show abstract

“…15 For a class of nonlinear control-affine systems, a deep NN was updated in real time to approximate the unknown dynamics, which used a multiscale concurrent learning-based weight update policy. 16 For an unmanned surface vehicle with complex unknowns, NNs approach was further used to identify complex unknowns. On this basis, the optimal tracking control was realized.…”

Section: Introductionmentioning

confidence: 99%

“…RL was employed to resolve optimal controller design issue of nonlinear unknown strict‐feedback systems, and a NNs‐based observer was developed to identify unknown dynamics 15 . For a class of nonlinear control‐affine systems, a deep NN was updated in real time to approximate the unknown dynamics, which used a multiscale concurrent learning‐based weight update policy 16 . For an unmanned surface vehicle with complex unknowns, NNs approach was further used to identify complex unknowns.…”

Section: Introductionmentioning

confidence: 99%

Reinforcement learning‐based event‐triggered optimal control for unknown nonlinear systems with input delay

Chen,

Sun,

Gao

et al. 2024

Intl J Robust & Nonlinear

View full text Add to dashboard Cite

The optimal control issue of discrete‐time nonlinear unknown systems with time‐delay control input is the focus of this work. In order to reduce communication costs, a reinforcement learning‐based event‐triggered controller is proposed. By applying the proposed control method, closed‐loop system's asymptotic stability is demonstrated, and a maximum upper bound for the infinite‐horizon performance index can be calculated beforehand. The event‐triggered condition requires the next time state information. In an effort to forecast the next state and achieve optimal control, three neural networks (NNs) are introduced and used to approximate system state, value function, and optimal control. Additionally, a M NN is utilized to cope with the time‐delay term of control input. Moreover, taking the estimation errors of NNs into account, the uniformly ultimately boundedness of state and NNs weight estimation errors can be guaranteed. Ultimately, the validity of proposed approach is illustrated by simulations.

show abstract

Digital Twin Application on System Identification and Control

Pattanaik,

Mohanty

2024

Simulation Techniques of Digital Twin in Real‐Time Applications

View full text Add to dashboard Cite

Deep Neural Network-Based Approximate Optimal Tracking for Unknown Nonlinear Systems

Cited by 20 publications

References 18 publications

Adaptive Estimation and Control With Online Data Memory: A Historical Perspective

Adaptive Estimation and Control With Online Data Memory: A Historical Perspective

Reinforcement learning‐based event‐triggered optimal control for unknown nonlinear systems with input delay

Digital Twin Application on System Identification and Control

Contact Info

Product

Resources

About