Logo do repositório

Percorrer por autor "Haddad, Diego"

A mostrar 1 - 2 de 2
  • A Practical Approach to Teaching Differential Robot Control Using a Goal-to-Goal Interface
    Publication . Amorim, Johann S.J. C. C.; Moraes, Camile A.; Neto, Accacio F. dos; Amorim, Josef G. J. C. C.; Santos, Patricia S.; Haddad, Diego; Pinto, Milena F.; Lima, José
    This paper presents an interface to assist students in performing robot controllers. This application is designed to stabilize the movement of a goal-to-goal robot. The primary objective is to enhance the learning experience by offering an easy application that showcases the robot’s behavior based on its kinematic model. The paper outlines the various stages involved in developing and testing this simple interface, including a study of the kinematics of differential robots. It discusses the discrete- time equations for goal-to-goal behavior, the data required to obtain the controller, the application of the controller in a discrete microcontroller, and the development of code to simulate the robot’s behavior. The results show the developed interface and the possible outcomes through the use of this application in control classes.
    2024Comunicação em conferência Acesso restrito Ver mais
  • Long-term person reidentification: challenges and outlook
    Publication . Manhães, Anderson; Matos, Gabriel; Cardoso, Douglas O.; Pinto, Milena F.; Colares, Jeferson; Leitão, Paulo; Brandão, Diego; Haddad, Diego
    Person reidentification, i.e., retrieving a person of interest across several non-overlapping cameras, is a task that is far from trivial. Despite its great commercial value and wide range of applications (e.g., surveillance, intelligent environments, forensics, service robotics, marketing), it remains unsolved, even when the individuals do not change clothes during the recognition period. This paper provides an outlook on long-term person reidentification, an emerging research topic regarding when consecutive acquisitions of an individual can be found apart for days or even months, making such a task even more challenging. A long-term reidentification system using face recognition is presented to emphasize current techniques’ limitations.
    2022Comunicação em conferência Acesso restrito Ver mais