Obstacle avoidance of redundant manipulators using genetic algorithms

Abstract

The authors introduce a novel method for obstacle avoidance with redundant robot manipulators based on genetic algorithms (GAs), GAs are search procedures which duplicate many of the processes of natural genetics. GAs work with a coding of the parameters. The use of a 30-b ternary number to represent the moves associated with a three-degree-of-freedom robot is discussed. A finite number of incremental moves are used to guide the end-effector to the goal point through a collision-free path. Two example runs are described, and advantages and disadvantages of the method are discussed.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>