Thesis DESARROLLO DE ALGORITMO DE CONTROL BASADO EN ESTEREOVISIÓN PARA SIMULACIÓN DE AGARRE DE UN OBJETO MEDIANTE UN BRAZO ROBÓTICO
Date
2019-12
Authors
ARAVENA PACHECO, ALVARO JAVIER
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Este trabajo consiste en el desarrollo de un algoritmo capaz de generar las instrucciones de movimiento para un brazo robótico de cinco grados de libertad para simular el agarre de un objeto mediante visión artificial, específicamente, a través de estereovisión, es decir, de la recolección de información a partir del análisis de pares de imágenes con el uso de dos cámaras. El desarrollo del algoritmo se divide en dos grandes bloques: el primero consiste en la aplicación del método de Denavit-Hartenberg (cinemática directa), resolución del problema de cinemática inversa y comunicación con servomotores para la generación del movimiento y el segundo, en la calibración de los sistemas coordenados de las cámaras y del brazo robótico y la detección del punto de agarre del objeto que debe alcanzar el brazo para realizar la simulación.
This work consists in the development of an algorithm able to generate movement instructions for a five degree of freedom robotic arm to simulate the grabbing of an object through computer vision, specifically, through stereovision, that is, collecting information from the analysis of image pairs using two cameras. The algorithm development is divided in two main blocks: the first one consists in the application of the Denavit-Hartenberg method (forward kinematics), inverse kinematics problem solving and stablishing communication with the servomotors to generate movement and the second one consists in the cameras and robotic arm coordinate systems calibration and the detection of the object grabbing point to be reached by the arm in order to accomplish the simulation.
This work consists in the development of an algorithm able to generate movement instructions for a five degree of freedom robotic arm to simulate the grabbing of an object through computer vision, specifically, through stereovision, that is, collecting information from the analysis of image pairs using two cameras. The algorithm development is divided in two main blocks: the first one consists in the application of the Denavit-Hartenberg method (forward kinematics), inverse kinematics problem solving and stablishing communication with the servomotors to generate movement and the second one consists in the cameras and robotic arm coordinate systems calibration and the detection of the object grabbing point to be reached by the arm in order to accomplish the simulation.
Description
Keywords
ROBOTICA , ROBOTS INDUSTRIAL , INTELIGENCIA ARTIFICIAL
