Hippocampal neural network model performing navigation by homing vector field adhesion to sensor map

We propose an artificial neural network model for autonomous agents, i.e., mobile robots, to learn maps of environments and acquire the ability to perform home-navigation autonomously. The networks consists of two subnetworks, each of which has a similar structure with hippocampal lamellar neuronal circuits. Hebbian learning procedures self-organize the first subnetwork to output the distributed sinusoidal activity of the cells by accumulating motor information generated during movement, and the second subnetwork to output localized activity by prototyping sensory information. These patterns represent a homing vector providing the relative coordinates of the agent from a starting point, and a place code corresponding uniquely to a point of the environment. By attaching homing vectors to the sensor map, the homing vector is associated with the sensory stimuli. Then the agents can perform home-navigation autonomously by this association. This work was presented, in part, at the Second International Symposium on Artificial Life and Robotics, Oita, Japan, February 18–20, 1997