Recurrent Neural Networks in a Mobile Robot Navigation Task
Recurrent neural networks are applied to the forward modeling of the sensory-motor flow of a miniature mobile robot. It is shown that the robot is able to predict the sensory flow a few steps ahead, which suffices for simple environments. The proposed method requires mainly topological information (little geometrical information is used), simplifying the problem considerably.
KeywordsMobile Robot Recurrent Neural Network Obstacle Avoidance Sensory Output Sensory Flow
Unable to display preview. Download preview PDF.