Hamid Boubertakh

A new mobile robot navigation method using fuzzy logic and a modified Q-learning algorithm

This paper proposes a new fuzzy logic-based navigation method for a mobile robot moving in an unknown environment. This method endows the robot with the capabilities of obstacles avoidance and goal seeking without being stuck in local minima. A simple Fuzzy controller is constructed based on the human sense and a reinforcement learning algorithm is used to fine tune the fuzzy rule base parameters. The advantages of the proposed method are its simplicity, its easy implementation for industrial applications, and the robot joins its objective despite the environment complexity. Some simulation results of the proposed method and a comparison with some previous works are provided.

Tuning fuzzy PID controllers using ant colony optimization

Ant colony optimization (ACO) is one of the swarm intelligence (SI) techniques. It is a bio-inspired optimization method that has proven its success through various combinatorial optimization problems. This paper proposes an ant colony optimization algorithm for tuning fuzzy PID controllers. First, the design of typical Takagi-Sugeno (TS) fuzzy PID controllers is investigated. The tuning parameters of these controllers have physical meaning which makes its tuning task easier than conventional PID controllers. Simulation examples are provided to illustrate the efficiency of the proposed method.

PSO to design decentralized fuzzy PI controllers application for a helicopter

In this paper, we propose the use of a Particle Swarm Optimization (PSO) for tuning decentralized typical fuzzy PI (FPI) controllers applied for the stabilization of a helicopter model. The method is used such as to minimize a square error (SE) fitness function which quantifies the performance of the whole control system. The proposed PSO method exploits all the available knowledge about the system under control since, the considered typical FPI controllers are characterized by simple and interpretable structure, which can reduces the tuning time.

A Simple Goal Seeking Navigation Method for a Mobile Robot Using Human Sense, Fuzzy Logic and Reinforcement Learning

This paper proposes a new fuzzy logic-based navigation method for a mobile robot moving in an unknown environment. This method endows the robot the capabilities of obstacles avoidance and goal seeking without being stuck in local minima. A simple Fuzzy controller is constructed based on the human sense and a fuzzy reinforcement learning algorithm is used to fine tune the fuzzy rule base parameters. The advantages of the proposed method are its simplicity, its easy implementation for industrial applications, and the robot joins its objective despite the environment complexity. Some simulation results of the proposed method and a comparison with previous works are provided.

Indirect Adaptive Fuzzy Control for a Class of Uncertain Nonlinear Systems with Unknown Control Direction

In this paper, the authors propose two indirect adaptive fuzzy control schemes for a class of uncertain continuous-time single-input single-output SISO nonlinear dynamic systems with known and unknown control direction. Within these schemes, fuzzy systems are used to approximate unknown nonlinear functions and the Nussbaum gain technique is used to deal with the unknown control direction. This paper first presents a singularity-free indirect adaptive control algorithm for nonlinear systems with known control direction, and then this control algorithm is generalized for the case of unknown control direction. The proposed adaptive controllers are free from singularity, allow initialization to zero of all adjustable parameters of the used fuzzy systems, and guarantee asymptotic convergence of the tracking error to zero. Simulations performed on a nonlinear system are given to show the feasibility of the proposed adaptive control schemes.

Optimal tuning of a PD control by bat algorithm to stabilize a quadrotor

In In this work, we propose a new design approach based on bat algorithm for optimal design of proportional derivative controller for the stabilization of a Quadrotor. To stabilize the angles (roll, pitch and yaw) and heights of the Quadrotor a decentralized control structure is adopted where four proportional derivative (PD) controllers are used. Their parameters are given simultaneously by BAT algorithm. The performance of the system from its desired behavior is quantified by an objective function (SE). Some simulation results are presented to show the efficiency of the method.

Synchronization of chaotic systems using genetic and particle swarms algorithms

This work focus on the application of Genetic Algorithms (GA) and Particle Swarm Optimization (PSO) applied for the synchronization of two chaotic systems. Therefore, the synchronization problem is considered as an optimization problem. The GA and PSO approaches are used to minimize the synchronization error between the master and the slave chaotic systems. A comparative study between the GA and the PSO is carried out through a simulation example to show the best solution in terms of convergence speed and efficiency.

An adaptive fuzzy PID control for a class of uncertain nonlinear underactuated systems

In this work an adaptive PID control law is used to approximate a model-based robust sliding mode control law to deal with a class of uncertain underactuated nonlinear systems. Therefore, a fuzzy system is used to learn online the ideal PID control gains regarding the desired performances. So, the fuzzy system parameters are adjusted online by a robust adaptation law in order to minimize the error between the unknown ideal controller and the PID controller. The stability of the closed-loop system is proven analytically based on the Lyapunov approach. A simulation example is presented to illustrate the efficiency of the proposed approach.

Human pose recognition and tracking using RGB-D camera

Accidents caused by heavy vehicles, are a serious worldwide safety problem. Preventing these accidents demands thorough knowledge about vehicle dynamic state as well as other vehicle parameters. For this purpose, High-Order Sliding-Mode Observer (HOSMO) is employed to estimate the dynamic states and parameters of the heavy vehicles to evaluate the rollover threat and warning signals are issued sufficiently in advance of rollover, then the rollover accidents can be prevented by the drivers corrective actions. The proposed method proved efficient by simulation.

Adaptive fuzzy actuator failure compensation for a class of nonlinear systems

This paper proposes a direct adaptive fuzzy control scheme for actuator failure compensation of a class of multi-input single-output (MISO) nonlinear systems. The proposed controller assumes a proportional actuation scheme which allows transforming the MISO system with uncertain actuator failures to an uncertain SISO system for which a fuzzy logic system is used for designing the control input signal to be distributed among redundant actuators. The parameter update laws for the fuzzy controller are derived using a gradient descent type algorithm that minimizes a quadratic cost function of the control error. Closed-loop system stability and tracking requirements are proved using Lyapunov stability theory and a piecewise analysis to deal with parameter jumps due to abrupt failures. A simulation study is carried out to show the effectiveness of the proposed control scheme.