Homing Using Combinations of Model Views

Abstract

A method for homing in an indoor environment is presented. Homing is the process by which an autonomous system guides itself to a particular location on the basis of sensory input [8) . The proposed method proceeds in two steps. In the first step the robot attempts to recognize the environment, and in the second step the robot navigates within the recognized environment toward the target location. A system for Localization (recognizing the environment) and positioning (computing the exact coordinates of a robot in the environment) is used. The system represents scenes as sets of 2D views and predicts the appearance of novel views by linear combinations of the model views. Two methods for directing the robot to the target position are proposed. The first approach is based on recovering the exact coordinates of the robot in the environment. Homing is carried out as a direct result of this recovery. The second approach uses a predetermined homing pattern to execute a simpler algorithm for the process. At each stage the direction to the target is computed directly from the image. Knowledge of the transformation between the model views is not required in this approach.