Abstract
We address in this paper the design of behavior based systems from a bottom-up viewpoint. Although behavior is an observable property of a system, and therefore immediately causes a topdown model, the approach has to be inverted to support the learning of equivalence classes of the perception-action cycle. After introducing the paradigm in the frame of a socio-ecological theory of biological systems, we discuss the natural science problems to be solved for successful design of behavior based systems by a bootstrap of perception-action cycles. The necessary fusion of robotics with computer vision, neural computation, and signal theory needs a common theoretical framework. This framework consists of a global algebraic frame for embedding the perceptual and motor categories, a local algebraic framework for bottom up construction of the necessary information, and a framework for learning and self-control, based on the equivalence of perception and action. Geometric algebra will be identified as the adequate global algebraic frame, and the Lie theory will be introduced as the local algebraic frame. We will demonstrate several applications of the frames in early visual processing. Finally, we will finish our discussion with the fusion of local approaches and the global algebraic frame with respect to both the formulation of an adequate multidimensional signal theory and the design of algebraic embedded neural processing. In both cases we will discuss the relation to the non-linear Volterra series approach, which, in our framework, will be reduced to a linear one.
This work was supported by DFG grant So 320-2-1.
Preview
Unable to display preview. Download preview PDF.
References
Aloimonos Y., Weiss I. and Bandopadhay A.: Active vision. Int. J. Comp. Vis. 7: 333–356. 1988
Aloimonos Y. (Ed.): Active Perception. Lawrence Erlbaum Ass., Hillsdale. 1993
Aloimonos Y.: Active vision revisited. In: [2],, Hillsdale. 1993 pp. 1–18
Aloimonos Y.: What I have learned. CVGIP: Image Understanding 60 (1): 74–85. 1994
Bajcsy R.: Active perception. Proc. IEEE 76 (8): 996–1005. 1988
Ballard D.H.: Animate vision. Artif. Intelligence 48: 57–86. 1991
Bayro-Corrochano E. and Lasenby J.: A unified language for computer vision and robotics. In: Proc. AFPAC'97. Kiel. G. Sommer and J.J. Koenderink (Eds.). LNCS Vol. XXX. Springer-Verlag. Heidelberg. 1997
Bayro-Corrochano E. and Buchholz S.: Geometric neural networks. In: Proc. AFPAC'97. Kiel. G. Sommer and J.J. Koenderink (Eds.). LNCS Vol. XXX. Springer-Verlag. Heidelberg. 1997
Bayro-Corrochano E., Daniilidis K. and Sommer G.: Hand-eye calibration in terms of motion of lines using geometric algebra. In: Proc. 10th Scandinavian Conference on Image Analysis. Lappeenranta. Finland. 1997
Benediktsson J., Sveinsson J., Ersoy O. and Swain P.: Parallel consensual neural networks. IEEE Trans. Neural Networks 8: 54–64. 1997
Brooks R.A.: A robust layered control system for a mobile robot. IEEE Trans. Robotics and Automation 2 (1): 14–23. 1986
Bruske J., Ahrns I. and Sommer G.: Neural fuzzy control based on reinforcement learning and Dynamic Cell Structures. In: Proc. EUFIT, Vol. 2. 710–714. Aachen. 1996
Bruske J. and Sommer G.: An algorithm for intrinsic dimensionality estimation. In: Proc. CAIP'97, Kiel, Sept. 1997. LNCS Vol. XXX. Springer-Verlag. Heidelberg. 1997
Bruske J. and Sommer G.: Dynamic cell structure learns perfectly topology preserving map. Neural Computation 7 (4): 845–865. 1995
Bruske J., Hansen M., Riehn L. and Sommer G.: Adaptive saccade control of a binocular head with dynamic cell structures. In: Proc. ICANN'96. 215–220. LNCS Vol. 1112. Springer-Verlag. 1996
Billow T. and Sommer G.: Multi-dimensional signal processing using an algebraically extended signal representation. In: Proc. AFPAC'97. Kiel. G. Sommer and J.J. Koenderink (Eds.). LNCS Vol. XXX, Springer-Verlag. Heidelberg. 1997
Chevallier D.P.: Lie algebras, modules, dual quaternions and algebraic methods in kinematics. Mech. Mach. Theory 26 (6): 613–627. 1991
Connell J.A.: A behavior-based arm controller. IEEE Trans. Robot. & Automation 5 (6): 784–791. 1989
Cutting J.E.: Perception with an Eye for Motion. MIT Press. Cambridge. 1986
Danielson D.A.: Vectors and Tensors in Engineering and Physics. Addison-Wesley Publ., Redwood City. 1992
Daniilidis K.: Fixation simplifies 3D motion estimation. Comp. Vis. and Image Understanding. 1996. to appear
Daniilidis K. and Bayro-Corrochano E.: The dual quaternion approach to hand-eye calibration. In: Proc. 13th ICPR, Vienna, Vol. A. 318–322. ICPR. 1996
Doran C., Hestenes D., Sommen F. and Van Acker N.: Lie groups as spin groups. J. Math. Phys. 34 (8): 3642–3669. 1993
Eccles J.C.: Evolution of the Brain: Creation of the Self. Routledge. London and New York. 1989
Eigen M. and Schuster P.: The Hypercycle — a Principle of Natural Self-Organization. Springer-Verlag. Heidelberg, New York. 1979
Faugeras O.: Stratification of three-dimensional vision: projective, affine, and metric representations. J. Opt. Soc. Am. A 12 (3): 465–484. 1995
Furth H.G.: Piaget and Knowledge. Theoretical Foundations. Prentice Hall, Inc. Englewood Cliffs. 1969
Gibson J.J.: The Ecological Approach to Visual Perception. Houghton Mifflin. Boston. 1979
Gool van L., Moons T., Pauwels E. and Oosterlinck A.: Vision and Lie's approach to invariance. Image and Vision Computing 13(4): 259–277. 1995
Granlund G.H. and Knutsson H.: Signal Processing for Computer Vision. Kluwer Academic Publ. 1995
Hailu G. and Sommer G.: Learning from reinforcement signal. submitted. 1997
Haken H.: Synergetics. An Introduction. Springer-Verlag. Berlin. 1977
Hestenes D. and Sobczyk G.: Clifford Algebra to Geometric Calculus: A Unified Language for Mathematics and Physics. D. Reidel. Dordrecht. 1984
Hestenes D.: New Foundations for Classical Mechanics. Kluwer Academic Publ. Dordrecht. 1986
Koenderink J.J.: Wechsler's vision. Ecological Psychology 4 (2): 121–128. 1992
Koenderink J.J.: Embodiments of geometry. In: A. Aertsen (Ed.). Advanced Neural Computers. 303–312. Elsevier Science Publ. Amsterdam. 1990
Koenderink J.J., Kappers A. and van Doorn A.: Local operations: the embodiment of geometry. In: G.A. Orban, H.H. Nagel (Eds.): Artificial and Biological Vision Systems. 1–23. Springer-Verlag. Berlin. 1992
Krüger G. and Zetzsche C.: Nonlinear image operators for the evaluation of local intrinsic dimensionality. IEEE Trans. Image Processing 5 (6): 1026–1042. 1996
Landy M.S., Maloney L.T. and Pavel M. (Eds.): Exploratory Vision. The Active Eye. Springer-Verlag. New York. 1996
Lorenz K.: Evolution and Modification of Behavior. Merhuen. London, 1966
Luong Q.T. and Vieville T.: Canonic representations for the geometries of multiple projective views. In: J.O. Eklundh (Ed.) Proc. ECCV'94. 589–599. LNCS Vol. 800. Springer-Verlag. Berlin. 1994
Malsburg von der C.: Considerations for a visual architecture. In: R. Eckmiller (Ed.). Advanced Neural Computers. 303–312. Elsevier Science Publ. Amsterdam. 1990
Marr D.: Vision. W.H. Freeman. San Francisco. 1982
Mataric M.J.: Integration of representation into goal-driven behavior-based robots. IEEE Trans. Robot. & Automation 8 (3): 304–312. 1992
Michaelis M. and Sommer G.: Junction classification by multiple orientation detection. In: J.O. Eklundh (Ed.). Proc. ECCV'94. 101–108. LNCS Vol. 800. Springer-Verlag. Berlin. 1994
Michaelis M. and Sommer G.: A Lie group approach to steerable filters. Patt. Rec. Lett. 16: 1165–1174. 1995
Michaelis M.: Low Level Image Processing Using Steerable Filters. PhD Thesis. Technical Faculty. University of Kiel. Germany. 1995
Newell A. and Simon H.A.: Computer science as empirical enquiry: symbol and search. Commun. of the ACM 19: 113–126. 1976
Nicolis J.S.: Chaotic Dynamics Applied to Biological Information Processing. Akademie-Verlag, Berlin. 1987
Pao Y.H.: Adaptive Pattern Recognition and Neural Networks. Addison-Wesley. 1989
Park F.C., Bobrow J.E. and Ploen S.R.: A Lie group formulation of robot dynamics. Int. J. Robotics Res. 14 (6): 609–618. 1995
Paton R. (Ed.): Computing with Biological Metaphors. Chapman and Hall. London. 1994
Pauli J., Benkwitz M. and Sommer G.: RBF networks for appearance-based object detection. In: Proc. ICANN'95, Vol. 1. 359–369. ICANN, Paris. 1995
Pearson D.W.: Linear systems equivalent to artificial neural networks via Lie theory. Neurocomputing 8: 157–170.1995
Pelc A.: Purposive Progressive Representation of Images using Wavelet Nets. Master Thesis (in German). Cognitive Systems Group. Computer Science Institute. University of Kiel. Germany. 1997
Pellionisz A. and Llinas R.: Tensor network theory of the metaorganization of functional geometries in the central nervous system. Neuroscience 16 (2): 245–273. 1985
Popper K.R.: Objective Knowledge. The Clarendon Press. Oxford, 1972
Porteous I.R.: Clifford Algebras and the Classical Groups. Cambridge University Press. 1995
Rayner P.J.W. and Lynch M.R.: A new connectionist model based on a nonlinear adaptive filter. In: Proc. IEEE Int. Conf. Acoust., Speech & Signal Process. Vol. 2. 1191–1194. 1989
Rooney J.: On the three types of complex numbers and planar transformations. Environment and Planning B5: 89–99. 1978
Sattinger D.H. and Weaver O.L.: Lie Groups and Algebras with Applications to Physics, Geometry, and Mechanics. Springer-Verlag. New York. 1993
Schetzen M.: Nonlinear system modeling based on the Wiener Theory. Proc. IEEE 69 (12): 1557-57
Segman J. and Y.Y. Zeevi: Image Analysis by wavelet-type transforms: group theoretical approach. J. Math. Imaging and Vision 3: 51–77. 1993
Sommer G., Bayro-Corrochano E. and Bülow T.: Geometric algebra as a framework for the perception-action cycle. In: Proc. Int. Workshop Theor. Foundations of Computer vision. Dagstuhl. March 1996. Springer-Verlag. Wien. 1997
Tikhonov A.N. and Arsenin V.Y.: Solutions of Ill-Posed Problems. Wiley. New York. 1977
Tinbergen N.: The Study of Instinct. Oxford University Press. New York, 1951
Workshop on Visual Behaviors. Seattle. Washington. June 19, 1994, Proc.: IEEE Computer Society Press. Los Alamitos. 1994
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Sommer, G. (1997). Algebraic aspects of designing behavior based systems. In: Sommer, G., Koenderink, J.J. (eds) Algebraic Frames for the Perception-Action Cycle. AFPAC 1997. Lecture Notes in Computer Science, vol 1315. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0017858
Download citation
DOI: https://doi.org/10.1007/BFb0017858
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63517-8
Online ISBN: 978-3-540-69589-9
eBook Packages: Springer Book Archive