SciELO - Scientific Electronic Library Online

 
vol.14 issue27Application of neuro-fuzzy ANFIS model vs neural network, to the predictive monthly mean flow problem in the Bogotá river in Villapinzón author indexsubject indexarticles search
Home Pagealphabetic serial listing  

Services on Demand

Journal

Article

Indicators

Related links

  • On index processCited by Google
  • Have no similar articlesSimilars in SciELO
  • On index processSimilars in Google

Share


Tecnura

Print version ISSN 0123-921X

Abstract

MARTINEZ SARMIENTO, Fredy Hernán  and  CASTIBLANCO ORTIZ, Mariela. Projection, design and construction of robotic platform for artificial intelligence research. Tecnura [online]. 2010, vol.14, n.27, pp.7-17. ISSN 0123-921X.

In order to consolidate research about artificial intelligence-based tools, the design and construction of an autonomous robotic platform with simple mathematical model and high processing capacity is considered. The final prototype objective is to evaluate autonomous control strategies, artificial vision, route planning and collective intelligence. For this reason, the system was equipped with a FPGA as central control unit. In order to facilitate the development of a theoretical model, and provide the system with high mobility, the prototype was structured on a differential platform with two independent motors coupled with scroll wheels, and one third omni directional wheel of support. The mechanical structure was designed in acrylic (methacrylate), looking for mechanical strength, low weight, visualization of components and esthetic presentation. For primary space location, the prototype was equipped with encoded position ultrasonic sensors for wide range of vision. In addition, the system counts with ports to increase robot peripherals. The prototype was evaluated in laboratory, observing an excellent performance according to plan in design.

Keywords : Intelligent control; FPGA; Development platform; Robot.

        · abstract in Spanish     · text in Spanish     · Spanish ( pdf )

 

Creative Commons License All the contents of this journal, except where otherwise noted, is licensed under a Creative Commons Attribution License