Optimized Backstepping Design for Ship Course Following Control Based on Actor-Critic Architecture With Input Saturation

Bai, Yuming; Cao, Yuchi; Li, Tieshan

doi:10.1109/access.2019.2919249

Cited by 19 publications

(8 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure 3. Based on the ideal of backstepping method [33], we transform ADRC into series form with the introduction of the virtual control variable, so the mismatched disturbance can be expanded into state by ESO to estimate and compensate. The control system series formation is as shown in Figure 4.…”

Section: A Control Analysismentioning

confidence: 99%

Series Active Disturbance Rejection Autopilot Design for Hyper Velocity Projectiles

2020

View full text Add to dashboard Cite

This paper presents a series active disturbance rejection controller (ADRC) autopilot design scheme with mini pin actuators for nonlinear hyper velocity projectile (HVP) system. In order to accurately describe the flight dynamics of HVP, a new nonlinear model with mismatched disturbances is established considering the aerodynamic characteristics of mini pin actuators. For compensating mismatched disturbances, series ADRC method is incorporated into double-loop (angle loop and angular loop) autopilot design, i.e., in the angle loop mismatched disturbances are observed and compensated in the virtual control calculation; in the angular loop, the observed matched disturbances are compensated in the mini pin control. In addition, both the mismatched and matched disturbances are considered as lumped ones including external disturbances, model uncertainties, coupling terms, etc. Finally, comparative numerical simulations with some traditional nonlinear control methods indicate that the proposed series ADRC HVP system has good robustness performance. INDEX TERMS HVP, mini pin actuator, attitude autopilot, series ADRC, mismatched disturbances.

show abstract

Section: A Control Analysismentioning

confidence: 99%

Series Active Disturbance Rejection Autopilot Design for Hyper Velocity Projectiles

2020

View full text Add to dashboard Cite

show abstract

“…Adaptive dynamics programming (ADP) [10][11][12][13][14][15][16][17][18] is a mature and mathematical discipline proposed by Werbos [16][17][18] whereby user-defined cost function as the optimization index to determine optimal control policy with self-learning mechanism. In essence, two neural networks (NNs) are deployed to respectively approximate the cost function and control policy such that the optimality principle and optimal performance index function can be met, simultaneously, such that the Hamilton-Jacobi-Bellman (HJB) equation which does not have an analytical form in the nonlinear system can be solved and curse of dimensionality can also be avoided of the dynamics programming (DP).…”

Section: Introductionmentioning

confidence: 99%

Self‐learning‐based optimal tracking control of an unmanned surface vehicle with pose and velocity constraints

Wang

Liu

2022

Intl J Robust & Nonlinear

View full text Add to dashboard Cite

In this article, subject to both pose and velocity constraints within narrow waters, a self-learning-based optimal tracking control (SLOTC) scheme is innovatively created for an unmanned surface vehicle (USV) by deploying actor-critic reinforcement learning (RL) mechanism and backstepping technique. To be specific, the barrier Lyapunov function (BLF) is devised to uniformly limit the states within a predefined region pertaining to a smoothly feasible reference trajectory. By virtue of a constrained Hamilton-Jacobi-Bellman (HJB) function, an actor-critic control structure under backstepping is established by employing adaptive neural network identifiers which recursively updates actor and critic, simultaneously. Eventually, theoretical analysis proves that the entire SLOTC scheme can render all the states remain in the predefined compact set while tracking errors converge to an arbitrarily small neighborhood of the origin. Simulation results on a prototype USV demonstrate remarkable effectiveness and superiority.

show abstract

“…By incorporating the Nussbaum-type gain into adaptive backstepping design, a robust controller was proposed for ship heading nonlinear system in the presence of unknown sign of uncertain control coefficients [24]. Later, this approach was extended to ship heading nonlinear system in the presence of uncertain control coefficients and time-varying characters [25], as well as input saturation [26], [27].…”

Section: Introductionmentioning

confidence: 99%

“…A common feature of the aforementioned studies [3]- [18], [22]- [27], [37]- [43] is that the adaptive controllers are designed based on ship steering linear model of Nomoto [44], and extension nonlinear models of Norrbin [45], Bech [46] and Nomoto [47]. The main reason lies in the fact that these models are said to be in SISO strict-feedback form [48].…”

Section: Introductionmentioning

confidence: 99%

Direct Adaptive Neural Network Control for Ship Manoeuvring Modelling Group Model-Based Uncertain Nonlinear Systems in Non-Affine Pure-Feedback Form

Wang

Soares

2020

IEEE Access

View full text Add to dashboard Cite

In this article, a direct neural network based adaptive backstepping control approach is proposed for a class of uncertain non-affine ship manoeuvring pure-feedback nonlinear systems. To carry out the backstepping design, the high fidelity 3 degrees of freedom Manoeuvring Modelling Group (MMG) model with external disturbances is transformed into the ship manoeuvring systems in non-affine pure-feedback form. Then, by combing the Implicit Function Theorem, Mean Value Theorem and dynamic surface control technique, the proposed approach is able to avoid completely the circularity problem and complexity growing problem exist in the adaptive neural network controller. During the controller design, the uncertain nonlinear functions are approximated by neural networks. Following this control approach, it is worth noting that the direct adaptive backstepping control for the high fidelity MMG model based ship manoeuvring nonlinear systems is achieved firstly, and the controller structure is simpler. Furthermore, it is shown via stability analysis that all signals in the closed-loop system are uniformly ultimately bounded. At last, two reference signals consist of a constant and a realistic performance requirement of ship are applied to simulation studies to illustrate the utility and merits of the proposed control scheme. INDEX TERMS Ship manoeuvring, Manoeuvring Modelling Group (MMG) model, non-affine purefeedback nonlinear system, adaptive neural network control, backstepping design.

show abstract

Optimized Backstepping Design for Ship Course Following Control Based on Actor-Critic Architecture With Input Saturation

Cited by 19 publications

References 33 publications

Series Active Disturbance Rejection Autopilot Design for Hyper Velocity Projectiles

Series Active Disturbance Rejection Autopilot Design for Hyper Velocity Projectiles

Self‐learning‐based optimal tracking control of an unmanned surface vehicle with pose and velocity constraints

Direct Adaptive Neural Network Control for Ship Manoeuvring Modelling Group Model-Based Uncertain Nonlinear Systems in Non-Affine Pure-Feedback Form

Contact Info

Product

Resources

About