Real-Time Model Predictive Control Using a Self-Organizing Neural Network

Han, Honggui; Wu, Xiaolong; Qiao, Junfei

doi:10.1109/tnnls.2013.2261574

Cited by 74 publications

(1 citation statement)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This property not only allows for using very fast training algorithms, but also makes RBF NNs suitable for integration in MPC schemes, as (a) it facilitates the controller design [34], and (b) helps to solve the MPC online optimization problem in shorter computational times [35], thus rendering such schemes applicable to systems with fast dynamics [36]. Another property that makes RBF NNs a popular modeling method in predictive control schemes is related to their increased approximation capabilities [37,38]. Indeed, notwithstanding their simple structure, RBF NNs have proven to be more accurate in modeling various nonlinear systems when compared to other machine learning methods, including MLPs, support vector machines (SVMs), random forests, etc.…”

Section: Radial Basis Function Neural Networkmentioning

confidence: 99%

Multi-Ship Control and Collision Avoidance Using MPC and RBF-Based Trajectory Predictions

Papadimitrakis

Stogiannos

Sarimveis

et al. 2021

Sensors

View full text Add to dashboard Cite

The field of automatic collision avoidance for surface vessels has been an active field of research in recent years, aiming for the decision support of officers in conventional vessels, or for the creation of autonomous vessel controllers. In this paper, the multi-ship control problem is addressed using a model predictive controller (MPC) that makes use of obstacle ship trajectory prediction models built on the RBF framework and is trained on real AIS data sourced from an open-source database. The usage of such sophisticated trajectory prediction models enables the controller to correctly infer the existence of a collision risk and apply evasive control actions in a timely manner, thus accounting for the slow dynamics of a large vessel, such as container ships, and enhancing the cooperation between controlled vessels. The proposed method is evaluated on a real-life case from the Miami port area, and its generated trajectories are assessed in terms of safety, economy, and COLREG compliance by comparison with an identical MPC controller utilizing straight-line predictions for the obstacle vessel.

show abstract

Section: Radial Basis Function Neural Networkmentioning

confidence: 99%

Multi-Ship Control and Collision Avoidance Using MPC and RBF-Based Trajectory Predictions

Papadimitrakis

Stogiannos

Sarimveis

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

Adaptive neuro‐predictive control for redundant robot manipulators in presence of static and dynamic obstacles: A Lyapunov‐based approach

Jasour

Farrokhi

2013

Adaptive Control & Signal

View full text Add to dashboard Cite

SUMMARYThis paper presents a novel approach for online path tracking and obstacle avoidance of redundant robot manipulators. To this end, a nonlinear model predictive control (NMPC) method is designed that can track a desired path or reaches a moving target in the Cartesian space while avoiding static or moving obstacles as well as singular configurations in the workspace of the robot. The finite cost function of the NMPC is optimized at every sampling time, yielding an online optimal approach. In order to avoid collisions with moving obstacles and, at the same time, capturing a moving target, the future positions of the obstacles and the moving target are predicted using artificial neural networks (ANNs). Moreover, ANNs are employed to find a proper nonlinear model for the NMPC. The adaptation laws for the ANNs are obtained using the Lyapunov's direct method. The advantages of the proposed method are fourfold: (i) an adaptive and optimal approach is obtained, which can cope with changes in the system parameters; (ii) no inverse kinematics of the redundant manipulators is required; (iii) no prior knowledge about the obstacles and motion of the moving object is required; and (iv) stability of the closed‐loop system is guaranteed. Numerical simulations, performed on a four degree‐of‐freedom redundant spatial manipulator actuated by DC servomotors, show effectiveness of the proposed method. Copyright © 2013 John Wiley & Sons, Ltd.

show abstract

Machine learning‐based predictive control of nonlinear processes. Part I: Theory

et al. 2019

View full text Add to dashboard Cite

This article focuses on the design of model predictive control (MPC) systems for nonlinear processes that utilize an ensemble of recurrent neural network (RNN) models to predict nonlinear dynamics. Specifically, RNN models are initially developed based on a data set generated from extensive open-loop simulations within a desired process operation region to capture process dynamics with a sufficiently small modeling error between the RNN model and the actual nonlinear process model. Subsequently, Lyapunov-based MPC (LMPC) that utilizes RNN models as the prediction model is developed to achieve closed-loop state boundedness and convergence to the origin. Additionally, machine learning ensemble regression modeling tools are employed in the formulation of LMPC to improve prediction accuracy of RNN models and overall closed-loop performance while parallel computing is utilized to reduce computation time. Computational implementation of the method and application to a chemical reactor example is discussed in the second article of this series.

show abstract

Real-Time Model Predictive Control Using a Self-Organizing Neural Network

Cited by 74 publications

References 49 publications

Multi-Ship Control and Collision Avoidance Using MPC and RBF-Based Trajectory Predictions

Multi-Ship Control and Collision Avoidance Using MPC and RBF-Based Trajectory Predictions

Adaptive neuro‐predictive control for redundant robot manipulators in presence of static and dynamic obstacles: A Lyapunov‐based approach

Machine learning‐based predictive control of nonlinear processes. Part I: Theory

Contact Info

Product

Resources

About