Abstract
Visual forward models predict future visual data from the previous visual sensory state and a motor command. The adaptive acquisition of visual forward models in robotic applications is plagued by the high dimensionality of visual data which is not handled well by most machine learning and neural network algorithms. Moreover, the forward model has to learn which parts of the visual output are really predictable and which are not because they lack any corresponding part in the visual input. In the present study, a learning algorithm is proposed which solves both problems. It relies on predicting the mapping between pixel positions in the visual input and output instead of directly forecasting visual data. The mapping is learned by matching corresponding regions in the visual input and output while exploring different visual surroundings. Unpredictable regions are detected by the lack of any clear correspondence. The proposed algorithm is applied successfully to a robot camera head under additional distortion of the camera images by a retinal mapping. Two future applications of the final visual forward model are proposed, saccade learning and a task from the domain of eye-hand coordination.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Blakemore, S.J., Wolpert, D., Frith, C.: Why can’t you tickle yourself? NeuroReport 11(11), R11–R16 (2000)
Bridgeman, B.: Failure to detect displacement of the visual world during saccadic eye movements. Vision Research 15(1), 719–722 (1975)
Deubel, H., Schneider, W.X.: Saccade target selection and object recognition: Evidence for a common attentional mechanism. Vision Research 36(12), 1827–1837 (1996)
Deubel, H., Schneider, W.X., Bridgeman, B.: Postsaccadic target blanking prevents saccadic suppression of image displacement. Vision Research 36(7), 985–996 (1996)
Deubel, H.: Localization of targets across saccades: Role of landmark objects. Visual Cognition 11(2-3), 173–202 (2004)
Eimer, M., Van Velzen, J., Gherri, E., Press, C.: Manual response preparation and saccade programming are linked to attention shifts: ERPevidence for covert attentional orienting and spatially specific modulations of visual processing. Brain Research 1105(1), 7–19 (2006)
Gross, H.M., Heinze, A., Seiler, T., Stephan, V.: Generative character of perception: A neural architecture for sensorimotor anticipation. Neural Networks 12(7-8), 1101–1129 (1999)
Große, S.: Visuelle Vorwärtsmodelle für einen Roboter-Kamera-Kopf, Diploma Thesis. Computer Engineering Group, Faculty of Technology, Bielefeld University (2005)
Hoffmann, H., Möller, R.: Action selection and mental transformation based on a chain of forward models. In: Schaal, S., Ijspeert, A., Billard, A., Vijayakumar, S., Hallam, J., Meyer, J.A. (eds.) From Animals to Animats 8. Proceedings of the Eighth International Conference on the Simulation of Adaptive Behavior, Los Angeles, CA, pp. 213–222. MIT Press, Cambridge (2004)
Hoffmann, H., Schenck, W., Möller, R.: Learning visuomotor transformations for gaze-control and grasping. Biological Cybernetics 93(2), 119–130 (2005)
Hoffmann, H.: Perception through visuomotor anticipation in a mobile robot. Neural Networks 20(1), 22–33 (2007)
von Holst, E., Mittelstaedt, H.: Das Reafferenzprinzip. Die Naturwissenschaften 37(20), 464–476 (1950)
Jordan, M.I., Rumelhart, D.E.: Forward models: Supervised learning with a distal teacher. Cognitive Science 16(3), 307–354 (1992)
Kawato, M.: Internal models for motor control and trajectory planning. Current Opinion in Neurobiology 9(6), 718–727 (1999)
Miall, R.C., Weir, D.J., Wolpert, D.M., Stein, J.F.: Is the cerebellum a smith predictor? Journal of Motor Behavior 25(3), 203–216 (1993)
Möller, R.: Perception through anticipation—a behavior-based approach to visual perception. In: Riegler, A., Peschl, M., von Stein, A. (eds.) Understanding Representation in the Cognitive Sciences, pp. 169–176 Plenum Academic / Kluwer Publishers, New York (1999)
Moody, J., Darken, C.J.: Fast learning in networks of locally-tuned processing units. Neural Computation 1, 281–294 (1989)
Rizzolatti, G., Riggio, L., Sheliga, B.M.: Space and selective attention. In: Umiltà, C., Moscovitch, M. (eds.) Attention and Performance VI: Conscious and Nonconscious Information Processing, pp. 231–265. MIT Press, Cambridge, MA (1994)
Schenck, W., Möller, R.: Learning strategies for saccade control. Künstliche Intelligenz Iss. 3/06, 19–22 (2006)
Snyder, L.H., Batista, A.P., Andersen, R.A.: Saccade-related activity in the parietal reach region. Journal of Neurophysiology 83(2), 1099–1102 (2000)
Tani, J.: Model-based learning for mobile robot navigation from the dynamical systems perspective. IEEE Transactions on Systems, Man, and Cybernetics—Part.B 26(3), 421–436 (1996)
Wolpert, D.M., Kawato, M.: Multiple paired forward and inverse models for motor control. Neural Networks 11(7-8), 1317–1329 (1998)
Ziemke, T., Jirenhed, D.A., Hesslow, G.: Internal simulation of perception: A minimal neuro-robotic model. Neurocomputing 68, 85–104 (2005)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Schenck, W., Möller, R. (2007). Training and Application of a Visual Forward Model for a Robot Camera Head. In: Butz, M.V., Sigaud, O., Pezzulo, G., Baldassarre, G. (eds) Anticipatory Behavior in Adaptive Learning Systems. ABiALS 2006. Lecture Notes in Computer Science(), vol 4520. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-74262-3_9
Download citation
DOI: https://doi.org/10.1007/978-3-540-74262-3_9
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-74261-6
Online ISBN: 978-3-540-74262-3
eBook Packages: Computer ScienceComputer Science (R0)