Title :
Using evolved paths for control in robot-soccer
Author :
Thomas, Peter J. ; Stonier, Russel J.
Author_Institution :
Fac. of Eng. & Phys. Syst., Central Queensland Univ, Rockhampton, Qld., Australia
Abstract :
In this paper we use an evolutionary algorithm to evolve paths using robot velocity profiles from an initial configuration to a configuration behind the ball. Physical conditions for wheel lift are incorporated as well as forward and reverse motion of the robot. A fuzzy clustering technique is used to build the fuzzy control knowledge base from optimised paths found for a large grid of initial configurations.
Keywords :
evolutionary computation; fuzzy control; mobile robots; path planning; position control; robot kinematics; evolutionary algorithm; evolved paths; fuzzy clustering technique; fuzzy control knowledge base; initial configuration; optimised paths; robot forward motion; robot reverse motion; robot soccer control; robot velocity profiles; robots kinematics; wheel lift; Control systems; Evolutionary computation; Fuzzy control; Fuzzy logic; Fuzzy sets; Fuzzy systems; Mobile robots; Robot control; Robot kinematics; Wheels;
Conference_Titel :
Computational Intelligence in Robotics and Automation, 2003. Proceedings. 2003 IEEE International Symposium on
Print_ISBN :
0-7803-7866-0
DOI :
10.1109/CIRA.2003.1222272
