TERSY

Stereo Vision Hardware System for
Autonomous Robot Navigation

This research is in cooperation with the
ENEA - Casaccia
Dott. S. Taraglio, Dott. A.Zanela


The TERSYCORE Project headed by Research Center of ENEA by Italian Ministry for the University and the Scientific Research (MURST).
The researches are aimed at the development and test of various approach to the sensing of the environment, through different sensors and algorithms.
Visual information are processed by neural architectures for the reconstruction of the ground maps.
The robotic platforms are the B21 robot of the Real World Interface (RWI) for indoor applications and the ATRV2 model for outdoor experiments.

Autonomous navigation requires the knowledge of the three dimensional information of the environment, in order to avoid collisions with moving objects or with the architectural or natural background.
The developed system is based on a disparity map (third dimension information) extracted from a pair of stereo images by a Cellular Neural Network (Stereo-CNN) algorithm.


B21 Robot

  • 32 Infrared Sensors (on the base)
  • 32 Contact Sensors (on the base)
  • 24 Ultrasonic Sensors (on the enclosure)
  • 24 Contact Sensors (on the enclosure)
  • 24 Infrared Sensors (on the enclosure)
  • 2 PC Pentium 200MHz (inside the enclosure)
  • 1 PC (on the console)
  • 2 Video Cameras (on the console)
  • 1 Radio link Ethernet (10Mbit/s)
  • 4 Batteries 12V / 31Ah
 
B21 robot





References

  1. M. Salerno, F. Sargeni,  V. Bonaiuto, S. Taraglio, A. Zanela
    "A CNN Stereo Vision Hardware System for Autonomous Robot Navigation"
    5thIEEE International Workshop on CNN and their Application (CNNA98), London, United Kingdom, 1998.
     

Return to the top page



Last updated on

For information and comments about this page feel free to contatct the Webmaster