Integration of ROS and object detection in an autonomous robot KUKA Youbot for rescuing people


Abstract:

The rescue processes to be carried out in environments that present levels of contamination caused by chemical, radioactive or biological agents are limited by the time of exposure to which the rescuers can be submitted, due to this the use of robotic platforms has been taken as a feasible option since it allows to increase the precision when carrying out the operations and to reduce the time in the decision making. The objective of this work is to present a system that links navigation processes, exploration and detection of people inside the Kuka Youbot mobile platform, which mainly allows to generate a map with the locations of the detected individuals. The work allowed the combination of the mentioned processes through the use of Robot Operating System, OpenCV, Gazebo and the Single Shot Detector algorithm to detect people. This work will allow the development of future platforms to rescue people.

Año de publicación:

2019

Keywords:

  • Single Shot Detector
  • KUKA YouBot
  • Robot Operating System
  • deep learning
  • Open Source Computer Vision Library
  • Autonomous Navigation

Fuente:

scopusscopus

Tipo de documento:

Article

Estado:

Acceso restringido

Áreas de conocimiento:

  • Robótica

Áreas temáticas:

  • Física aplicada
  • Otras ramas de la ingeniería