Browsing by Author "Zaatri, Abdelouahab"

Now showing 1 - 3 of 3
  • No Thumbnail Available
    Item
    Contribution to inverse kinematic modeling of a planar continuum robot using a particle swarm optimization
    (Springer, 2015) Amouri, Ammar; Mahfoudi, Chawki; Zaatri, Abdelouahab
    According to the literature, research on modeling continuum robots is focused on ways to develop the kinematic models, because of the lack of analytical models for these robots and the complexity of the problem which reside in the coupling of operational variables and infinite of possible solutions for a desired configuration. This paper presents a numerical approach for solving the inverse kinematic model of a planar continuum robot (PCR), assuming that each section of the manipulator is curved as a circular arc, with an inextensible central axis of the structure. At first, this paper presents an inverse kinematic model solution for one bending section, whereas the extreme points, of each section, used in calculating the inverse kinematic model for multi-sections is calculated numerically using a particle swarm optimization (PSO) technique. Finally, Simulation examples of this method are carried to validate the proposed approach.
  • No Thumbnail Available
    Item
    New Approach To Modeling A Planar Flexible Continuum Robot Simulating Elephant Trunk
    (Oum-El-Bouaghi University, 2013) Mahfoudi, Chawki; Amouri, Ammar; Zaatri, Abdelouahab
    Research on the modeling of continuum robots is focused on ways to construct the geometric models, while maintaining maximum specificities and mechanical properties of the robot. This paper presents a new approach of geometric modeling of continuum planar multi- sections robots, assuming that each section is curved in a circular arc, while having inextensible central axis of the structure. The direct geometric model is calculated analytically, whereas the extreme points (used in calculating the inverse geometric model) of each section are calculated numerically using a particle swarm optimization (PSO) method. One advantage of this method is to simplify the mathematical calculations and transform the complex problem into a simple numerical function; which allows the knowledge of the form of the central axis of the robot. Simulation examples using this method are carried to validate the proposed approach.
  • No Thumbnail Available
    Item
    Voice Recognition Technology Using Neural Networks
    (Oum-El-Bouaghi University, 2015) Zaatri, Abdelouahab; Azzizi, Norelhouda; Rahmani, Fouad Lazhar
    This paper presents the use of a Multi-Layer Perceptron Neural Nets (MLP-NN) for voice recognition dedicated to generating robot commands. Our main goal concerns the estimation of the minimal number of elements required for the learning process in order to ensure an acceptable success of the neural nets recognition system. As the MLP requires references for the spoken words, we have provided these references by the means of a supervised classifier based on the mean square error. An experimental approach has been followed for the design of experiments enabling to determine the minimal elements in the sample for each voice command. Satisfactory results have been obtained leading to a better understanding of variability of the system functioning. Finally, we have noticed that the success rate of the MLP and the minimal number of elements used for the learning process depend on the spoken word structure and of the variability of the situation (word length, noise, speaker, etc).