Engenharia de Robôs

URI Permanente desta comunidade

https://repositorio.fei.edu.br/handle/FEI/339

Navegar

Navegando Engenharia de Robôs por Autor "Flávio Tonidandel"

Agora exibindo 1 - 2 de 2
  • Nenhuma Miniatura disponível
    Artigo de evento
    Hardware and software aspects of the design and assembly of a new humanoid robot for RoboCup soccer
    (2014-10-23) PERICO, D. H.; SILVA, I. J.; VILAO, C. O.; HOMEM, T. P. D.; DESTRO. R. C.; Flávio Tonidandel; Reinaldo Bianchi
    © 2014 IEEE.This paper describes the design and development of a new humanoid robot named Newton, that is intended for applications in research and also to be used in the Robo Cup Kid Size League World Competition. Newton robot has been designed to work without any dedicated sub-controller implemented in low level hardware, often used to control the servomotors of the robot. Newton uses only a standard personal computer to do all processing and control necessary by the robot. To be able to deal with all the tasks involved in the robotic soccer domain, a new software architecture is proposed. This architecture is based on the hybrid paradigm, involving sensing, decision, planning, low level control, localization and communication. Preliminary tests show that the robot can walk properly while it performs tasks like finding the ball in an unknown position or positioning itself at the ball for kicking, exhibiting a very good performance.
  • Nenhuma Miniatura disponível
    Artigo de evento
    Solving the time lapse from vision system in a robot soccer game using kalman filter
    (2019-10-25) PAULI, G.; Flávio Tonidandel
    © 2019 IEEE.This article discusses some effects present in the Small Size League (SSL) category of robot soccer. The dynamic of this category requires a constant update about the state of objects in the field, however, the time to generate an update is smaller than the time between information packets arriving for teams. This latency could have a negative impact in the performance of the software, which could become limited due to the camera's capability. In order to solve this kind of obstacle, a routine was elaborated using a timer to perform the update every 1ms. The update consists of using the dynamic model of the objects combined with the Kalman filter to fill the lack of information while a new package is not available, so the software can have a reliable prediction of the object's position in the field with higher frequency.