Behavior-based map representation for a sonar-based mobile robot by statistical methods

Abstract

Many conventional methods for map generation by mobile robots have tried to reconstruct a 3D geometric representation of the environment, which is time-consuming, error-prone and necessary to transform the map into the information available for the given task. This paper proposes a method to acquire a statistical map representation robust to sensor noise and directly usable for a navigation task. The robot is equipped with a ring of ultrasonic ranging sensors and a collision avoidance behavior is embedded in it. First, the mobile robot explores the environment in order to store a set of sequences of sonar data and principle component analysis is applied to reduce the dimensionality of the sonar data. As a result, each sequence of sonar data can be described as a score pattern of principal components. Next, these patterns are classified into typical local structures of the environment in order for the robot to discriminate them. Finally, a graph representation of the environment is constructed in which the nodes and arcs correspond to these local structures and the transition probabilities between them, respectively. The validity of the method is shown by computer simulations and real robot experiments.