Perception through visuomotor anticipation in a mobile robot

Several scientists suggested that certain perceptual qualities are based on sensorimotor anticipation: for example, the softness of a sponge is perceived by anticipating the sensations resulting from a grasping movement. For the perception of spatial arrangements, this article demonstrates that this concept can be realized in a mobile robot. The robot first learned to predict how its visual input changes under movement commands. With this ability, two perceptual tasks could be solved: judging the distance to an obstacle in front by ‘mentally’ simulating a movement toward the obstacle, and recognizing a dead end by simulating either an obstacle-avoidance algorithm or a recursive search for an exit. A simulated movement contained a series of prediction steps. In each step, a multi-layer perceptron anticipated the next image, which, however, became increasingly noisy. To denoise an image, it was split into patches, and each patch was projected onto a manifold obtained by modeling th...

• Type: Journal
• Year: 2007
• Where: NN
• Authors: Heiko Hoffmann
• Keywords: Mobile Robot, Multi-layer Perceptron, Neural Networks, NN 2007, Sensorimotor Anticipation