Metalearning-Based Fault-Tolerant Control for Skid Steering Vehicles under Actuator Fault Conditions

Dai, Huatong; Chen, Pengzhan; Yang, Hui

doi:10.3390/s22030845

Cited by 8 publications

(7 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, in the real world, most systems are not linear in nature and are indeed very complex. Although the work in [15] addresses non-linear FTC, it still requires training the meta-model using different types of faulty data during the training phase, which is not viable in many real-world cases. Moreover, the methods presented in [18,19] need a separate FDI unit as a prerequisite to perform FTC.…”

Section: Introductionmentioning

confidence: 99%

“…In [15], the study presents an FTC approach based on meta‐reinforcement learning to enhance the tracking accuracy of vehicles when faced with actuator faults. An FTC tracking controller for discrete‐time linear parameter varying systems with single‐input single‐output subjected to both abrupt and gradual actuator faults is presented in [16], using a data‐driven approach.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Koopman fault‐tolerant model predictive control

Bakhtiaridoust,

Yadegar,

Jahangiri

2024

IET Control Theory & Appl

View full text Add to dashboard Cite

This paper introduces a novel data‐driven approach to develop a fault‐tolerant model predictive controller (MPC) for non‐linear systems. By adopting a Koopman operator‐theoretic perspective, the proposed method leverages historical data from the system to construct a data‐driven model that captures the non‐linear behaviour and fault characteristics. The fault influence is addressed through an online estimation of a time‐varying Koopman predictor, which allows for adjusting the MPC control law to counteract the fault effects. This estimation is performed in a higher dimensional Koopman feature space, where the dynamics behave linearly. As a result, the non‐linear fault‐tolerant MPC optimization problem can be replaced with a more practical and feasible linear time‐varying one using the approximated Koopman predictor. Moreover, by incorporating the online update procedure, the time‐varying Koopman predictor can represent the dynamics of the faulty system. Hence, the controller can adapt and compensate for the faults in real‐time, integrating the fault diagnosis module in the MPC framework and eliminating the need for a separate fault detection unit. Finally, the efficacy of the proposed approach is demonstrated through case study results, which highlight the ability of the controller to mitigate faults and maintain desired system behaviour.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Koopman fault‐tolerant model predictive control

Bakhtiaridoust,

Yadegar,

Jahangiri

2024

IET Control Theory & Appl

View full text Add to dashboard Cite

show abstract

“…Te faulttolerant sliding mode controller is designed considering that the fault coefcient is constant [24]. A meta-RLbasedfault-tolerant control (FTC) method is proposed to improve the tracking performance of vehicles in the case of actuator faults [25]. In reference [26], antisaturation faulttolerant controllers in presence of model parametric uncertainties and actuator faults are designed.…”

Section: Introductionmentioning

confidence: 99%

“…In reference [26], antisaturation faulttolerant controllers in presence of model parametric uncertainties and actuator faults are designed. However, the considered actuator faults must be continuously diferentiable [18], and the boundedness of fault coefcient estimates cannot be guaranteed [22,23,25,26].…”

Section: Introductionmentioning

confidence: 99%

Adaptive Fault‐Tolerate Lateral Control for Autonomous Electric Vehicles with Unknown Parameters and Actuator Faults

Liu

Wang

2023

Mathematical Problems in Engineering

View full text Add to dashboard Cite

In this paper, the fault-tolerant lateral control problem is considered for autonomous electric vehicles with unknown parameters and actuator faults. In the real world, the physical characteristics of vehicles are time-varying, causing that the parameters are unknown and even piecewise. Besides, the actuators may encounter with intermittent actuator faults, which can destroy the system’s performance. To deal with the piecewise unknown parameters and actuator faults, quadratic damping terms are designed in the controller and estimators are introduced to estimate those uncertainties. Then, by utilizing the backstepping technique, a novel adaptive fault-tolerant lateral control scheme is proposed, which guarantees that the tracking errors converge into a compact set. Simulation results are provided to validate the effectiveness and robustness of the proposed control scheme.

show abstract

“…The existing control approaches for the SSAV are quite different from the regular wheeled MR model. 5,6 The principal reason is the specific wheel's action along the vehicle path tracking. If the evaluated SSAV follows a non-straight path, SSAV wheels must skid over a lateral coordinate and not be tangent to the reference trajectory.…”

Section: Introductionmentioning

confidence: 99%

Output feedback adaptive controller of a autonomous skid-steering mobile vehicle based on sequential super-twisting differentiators

Fuentes-Alvarez

Chairez

Adams

et al. 2022

Proceedings of the Institution of Mechanical Engineers, Part I:

View full text Add to dashboard Cite

The main purpose of this work is to develop an output state-dependent controller that solves the path-tracking deviation error for a skid-steering autonomous vehicle. The controller takes advantage of a nonlinear diffeomorphism that transforms skid-steering autonomous vehicle into a multi-input multi-output chain of integrators. This research assumes that available skid-steering autonomous vehicle variables are its position and its orientation. This in fact motivates the development of a modified super-twisting algorithm operating as a sequential step-by-step differentiator that estimates traslational velocity and acceleration of the studied autonomous vehicle in a finite time, which were used as part of the controller implementation. Based on the estimated states by the step-by-step multi-variable differentiator, an adaptive control design enforces the asymptotic convergence of the tracking trajectories for the skid-steering autonomous vehicle to the origin. The explicit form of the controller gains is derived using a class of control Lyapunov function including the deviation corresponding to the tracking error and a term that defines a matrix norm associated with control gains. Numerical results confirm the workability of the proposed controller considering the reduced norm of tracking error obtained with the proposed controller. Experimental evaluations compared the adaptive control introduced in this study and a state-feedback form justifying the control proposal. The adaptive form enforced smaller tracking errors using the estimated states forced by the step-by-step differentiator and the information obtained from a multi-camera video high-frequency acquisition system.

show abstract

Metalearning-Based Fault-Tolerant Control for Skid Steering Vehicles under Actuator Fault Conditions

Cited by 8 publications

References 36 publications

Koopman fault‐tolerant model predictive control

Koopman fault‐tolerant model predictive control

Adaptive Fault‐Tolerate Lateral Control for Autonomous Electric Vehicles with Unknown Parameters and Actuator Faults

Output feedback adaptive controller of a autonomous skid-steering mobile vehicle based on sequential super-twisting differentiators

Contact Info

Product

Resources

About