Abstract

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 the density of the distribution of training patches with a mixture of Gaussian functions. Key words: sensorimotor anticipation, vision, forward model, mobile robot, perception, multi-layer perceptron, image denoising, Gaussian mixture model ⋆ I am grateful to Ralf Möller for introducing me to the area of perception through sensorimotor anticipation, for numerous discussions, and for comments on the manuscript. Bruno Lara, Helmut Radrich, Karl-Heinz Honsberg, and Fiorello Banci helped setting up the robot. Furthermore, I thank the two anonymous reviewers, whose comments helped to improve the manuscript.

Citations