A Fast Genetic SLAM Approach for Mobile Robots

Abstract

This paper presents a new SLAM (simultaneous localization and mapping) method using genetic algorithm (GA) for mobile robots. A laser range finder (LRF) is installed on a mobile robot for collecting point-distance information about the surroundings. From the LRF points, several important ones are extracted for describing the main features of the surroundings. A new form of chromosomes for representing the changes of feature LRF points that are caused by the robot's movement is designed. The matching of current LRF features and the robot's possible movement is done by a fast genetic algorithm. A restart mechanism that re-initializes all chromosomes for increasing the diversity of solutions is developed and works with the matching process. Some constrains are developed for filtering out irrational chromosomes after the operation of crossover and mutation. With these mechanisms and constrains, our proposed method generates feasible solutions in several hundreds of GA iterations. Experiments are conducted on a real mobile robot. The experimental results show that our proposed method is efficient and effective for SLAM.