Learning a visual task by genetic programming
P. Chongistitvatana, Jumpol Polvichai · 2002
This work describes a hand-eye system that can learn from its experience. The task is to visually guide the hand to reach a target while avoiding obstacles. The motion planning problem is solved by genetic programming. The system learns the forward kinematics by building a lookup table and uses it in the simulation run to generate robot programs that perform the task. The genetically created programs are validated by the actual runs on the robot.