Evolutionary navigator for a mobile robot

Abstract

An Evolutionary Navigator (EN) is presented for mobile robot navigation through an environment with unknown obstacles. Based on the concept of genetic algorithms, the EN can search paths of different user-defined levels of near-optimization in the entire, continuous free space using only a simple data structure. It unifies off-line and online planning processes and provides the flexibility to solve the conflict between efficiency and optimality. It also provides high safety measures without requiring complete information about the obstacles sensed.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>