 |
    |
Evolving Visual Object Recognition for Legged Robots
Juan Cristóbal Zagal, Javier Ruiz-del-Solar, Pablo Guerrero, and Rodrigo Palma
Department of Electrical Engineering, Universidad de Chile, Chilejzagal@ing.uchile.cl
jruizd@ing.uchile.cl
pguerrer@ing.uchile.cl
ropalma@ing.uchile.cl
Abstract. Recognition of relevant game field objects, such as the ball and landmarks, is usually based upon the application of a set of decision rules over candidate image regions. Rule selection and parameters tuning are often arbitrarily done. We propose a method for evolving the selection of these rules as well as their parameters with basis on real game field images, and a supervised learning approach. The learning approach is implemented using genetic algorithms. Results of the application of our method are presented.
LNAI 3020, p. 181 ff.
lncs@springer.de
© Springer-Verlag Berlin Heidelberg 2004