Autonomous decision making in local navigation

We present a neural field approach towards local navigation that is capable of endowing a mobile robot with features of autonomy. In particular we refer to the ability (and appetency) of making decisions and keeping them stable in a varying environment. The quality of a decision is represented by the strength of an activation over the neural field. We employ this strength for influencing the robot's behavior. The theoretical framework is validated by an implementation on our mobile service robot called 'ARNOLD'. Since its only sensor is an active stereo camera system we highlight the importance of gaze control and low-level shortterm memory for the stability of the overall behavior.