Early-Stage Vision of Composite Scenes for Spatial Learning and Navigation

Developmental theories suggest that cognitive agents develop through an initial sensorimotor stage during which they learn sequential and spatial regularities. We implemented these views in a computer simulation. Following its intrinsic motivations, the agent autonomously learns sensorimotor contingencies and discovers permanent landmarks by which to navigate in the environment. Besides illustrating developmental theories, this model suggests new ways to implement vision and navigation in artificial systems. Specifically, we coupled a sequence learning mechanism with a visual system capable of interpreting composite visual scenes by inhibiting items that are irrelevant to the agent's current motivational state.