Outdoor navigation using natural landmarks by teaching-playback scheme

The outdoor navigation of an autonomous and self-contained mobile robot using a perceived route map (PRM) generated through human-assisted route teaching is discussed. PRM includes the path from the start to the goal taught by operator and landmark information automatically generated by robot-self. The robot generates the route map which is perceived by own sensors. Navigation is performed by playback of the generated PRM. The robot navigates to the goal by feedback control of the estimated position by dead reckoning while playing back the path to follow, which is recorded in the PRM. Then, the robot occasionally corrects its position by fusion of the positional information obtained from landmark recognition.