Francisco G. Rossomando

Sliding Mode Neuro Adaptive Control in Trajectory Tracking for Mobile Robots

In this work a neural indirect sliding mode control method for mobile robots is proposed. Due to the nonholonomic property and restricted mobility, the trajectory tracking of this system has been one of the research topics for the last ten years. The proposed control structure combines a feedback linearization model, based on a kinematics nominal model, and a practical design that combines an indirect neural adaptation technique with sliding mode control to compensate the dynamics of the robot. Using an online adaptation scheme, a neural sliding mode controller is used to approximate the equivalent control in the neighbourhood of the sliding manifold. A sliding control is appended to ensure that the neural sliding mode control can achieve a stable closed-loop system for the trajectory-tracking control of a mobile robot with unknown nonlinear dynamics. The proposed design simultaneously guarantees the stability of the adaptation of the neural nets and obtains suitable equivalent control when the parameters of the robot model are unknown in advance. The robust adaptive scheme is applied to a mobile robot and shown to be able to guarantee that the output tracking error will converge to zero.

Identification and control of nonlinear dynamics of a mobile robot in discrete time using an adaptive technique based on neural PID

In this work, original results, concerning the application of a discrete-time adaptive PID neural controller in mobile robots for trajectory tracking control, are reported. In this control strategy, the exact dynamical model of the robot does not need to be known, but a neural network is used to identify the dynamic model. To implement this strategy, two controllers are implemented separately: a kinematic controller and an adaptive neural PID controller. The uncertainty and variations in the robot dynamics are compensated by an adaptive neural PID controller. It is efficient and robust in order to achieve a good tracking performance. The stability of the proposed technique, based on the discrete-time Lyapunovs theory, is proven. Finally, experiments on the mobile robot have been developed to show the performance of the proposed technique, including the comparison with a classical PID.

Adaptive neural sliding mode compensator for a class of nonlinear systems with unmodeled uncertainties

This paper addresses the problem of adaptive neural sliding mode control for a class of multi-input multi-output nonlinear system. The control strategy is an inverse nonlinear controller combined with an adaptive neural network with sliding mode control using an on-line learning algorithm. The adaptive neural network with sliding mode control acts as a compensator for a conventional inverse controller in order to improve the control performance when the system is affected by variations in its entire structure (kinematics and dynamics). The controllers are obtained by using Lyapunovs stability theory. Experimental results of a case study show that the proposed method is effective in controlling dynamic systems with unexpected large uncertainties.

Adaptive Neural Dynamic Compensator for Mobile Robots in Trajectory tracking control

In the present paper, it will be reported original results concerning the application of Neural Networks (NN) in mobile robot in trajectory tracking control. This work combines a feedback linearization based on a nominal model and an NN adaptive dynamic compensation. In mobile robot with uncertain dynamic parameters, two controllers are implemented separately: a kinematic controller and an inverse dynamic controller. The uncertainty in the nominal dynamic model is compensated by a neural adaptive feedback controller. The resulting adaptive controller is efficient and robust in the sense that it succeeds to achieve a good tracking performance with a small computational effort. The learning laws were deduced by Lyapunovs stability analysis. Finally, the performance of the control system is verified through experiments.

Design and Implementation of Adaptive Neural PID for Non Linear Dynamics in Mobile Robots

In this work, it will be reported original results concerning the application of PID Adaptive Neural controller in mobile robot in trajectory tracking control. In this control strategy the exact dynamical model of the robot will not need to be known and identified. To implement this strategy, two controllers are implemented separately: a kinematic controller and an adaptive neural PID controller. The uncertainty and dynamics variations in the robot dynamic are compensated by an adaptive neural PID controller. The resulting adaptive neural PID controller is efficient and robust in the sense that it succeeds to achieve a good tracking performance. The stability of the proposed technique (based on Lyapunovs theory) was demonstrated. Finally, experiments on a mobile robot have been developed to show the performance of the proposed technique, including the comparison with other controllers.

Control de Robots Móviles con Incertidumbres Dinámicas usando Redes de Base Radial

This paper presents an adaptive trajectory tracking control for mobile robots for which stability conditions and performance evaluation are given. The proposed control structure combines a feedback linearization model, based on a kinematics nominal model, and a direct neural network-based adaptive dynamics control. The control system design is done considering uncertain dynamic parameters in the dynamic model of the robot. The uncertainty in the dynamics model is learned by a RBF neural network in an adaptive feedback loop, adjusting the weight and the radial basis functions. The proposed RBF-NN scheme is computationally more efficient than the case of using the learning capabilities of the neural network to be adapted, as that used in feedback architectures that need to back propagate the control errors through the model (or network model) to adjust the neurocontroller. The resulting adaptive controller is efficient and robust in the sense that it succeeds to achieve a good tracking performance with a small computational effort. Stability result for the adaptive neuro-control system is given. It is proved that control errors are ultimately bounded as a function of the approximation error of the RBF-NN. Experimental results show the practical feasibility and performance of the proposed approach to mobile robots.

Adaptive Neural Sliding Mode Control in Discrete Time for a SCARA robot arm

This work presents a neuro-adaptive control method in sliding mode control designed in discrete time for SCARA robot arm. The proposed control structure is based on neuro-adaptive sliding mode control to adjust dynamics variations of the SCARA robot. The sliding control is included to ensure that the discrete-time neural control can improve the stable closed loop system to be immune to the parameters variations. The proposed technique simultaneously ensures the stability of the adaptation of neural networks and can obtain adequate control when the robots parameters are inexactly or unknown. This adaptive neural system was applied on a SCARA type robot arm where the trajectory tracking error converges to zero. Finally, experiments have been developed on SCARA robot arm to demonstrate the efficiency of the proposed technique, including comparison with a classical controller.

Neural Network-Based State Estimation for a Closed-Loop Control Strategy Applied to a Fed-Batch Bioreactor

The lack of online information on some bioprocess variables and the presence of model and parametric uncertainties pose significant challenges to the design of efficient closed-loop control strategies. To address this issue, this work proposes an online state estimator based on a Radial Basis Function (RBF) neural network that operates in closed loop together with a control law derived on a linear algebra-based design strategy. The proposed methodology is applied to a class of nonlinear systems with three types of uncertainties: (i) time-varying parameters, (ii) uncertain nonlinearities, and (iii) unmodeled dynamics. To reduce the effect of uncertainties on the bioreactor, some integrators of the tracking error are introduced, which in turn allow the derivation of the proper control actions. This new control scheme guarantees that all signals are uniformly and ultimately bounded, and the tracking error converges to small values. The effectiveness of the proposed approach is illustrated on the basis of simulated experiments on a fed-batch bioreactor, and its performance is compared with two controllers available in the literature.

ADVANCED MODEL BASED PROCESS SUPERVISION IN HOT STEEL MILLING

Abstract This paper presents the principles, as well as a prototype implementation, of a model-based supervisory system for the hot steel milling process. Here, a set of simulation models builds the core of the system and possess updated processes information. A model-based setup calculation and tendency prediction, as well as an online fault detection and equipment diagnostics, enhance the performance of the facility control procedure. Concepts of hierarchical modeling, distributed control and decentralized process data acquisition are studied in order to design a methodology for low-cost development of advanced supervision and control systems in industry. Copyright

Adaptive dynamic control of a quadrotor for trajectory tracking

This work presents an adaptive trajectory tracking controller for an unmanned aerial vehicle (UAV) which combines a feedback linearization controller based on a nominal model of a quadrotor and a Neuro Adaptive Compensation (NAC). The NAC is introduced in order to minimize the control errors caused by uncertainties in the nominal parameters. The uncertain parameters of the nominal model are balanced by a Neuro Adaptive Compensator. The proposed adaptive control scheme is robust and efficient to achieve a good trajectory following performance for outdoor and indoor applications. The analysis of the neural approximation error on the control errors is included. Finally, the effectiveness of the control system is proved through numerical simulation.