Abstract
We describe how current work in Artificial Intelligence is using rigorous tools from information theory, namely information distance and experience distance to organize the self-structuring of sensorimotor perception, motor control, and experiential episodes with extended temporal horizon. Experience is operationalized from an embodied agent’s own perspective as the flow of values taken by its sensors and effectors (and possibly other internal variables) over a temporal window. Such methods allow an embodied agent to acquire the sensorimotor fields and control structure of its own body, and are being applied to pursue autonomous scaffolded proximal development in the zone between the familiar experience and the unknown.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Lungarella, M., Metta, G., Pfeifer, R., Sandini, G.: Developmental robotics: A survey. Connection Science 15(4), 151–190 (2003)
Lungarella, M., Sporns, O.: Information self-structuring: Key principles for learning and development. In: ICDL 2005. Proc. of 4th International Conference on Development and Learning, pp. 25–30 (2005)
Shannon, C.E.: A mathematical theory of communication. Bell Systems Technical Journal 27, 379–423, 623–656 (1948)
Olsson, L., Nehaniv, C.L., Polani, D.: Sensory channel grouping and structure from uninterpreted sensor data. In: 2004 NASA/DoD Conference on Evolvable Hardware, Seattle, Washington, USA, June 24-26, 2004, pp. 153–160. IEEE Computer Society Press, Los Alamitos (2004)
Olsson, L., Nehaniv, C.L., Polani, D.: From unknown sensors and actuators to actions grounded in sensorimotor perceptions. Connection Science 18(2), 121–144 (2006)
Pierce, D., Kuipers, B.: Map learning with uninterpreted sensors and effectors. Artificial Intelligence 92, 169–229 (1997)
Philipona, D., O’Regan, J.K., Nadal, J.P.: Is there something out there? Inferring space from sensorimotor dependencies. Neural Computation 15(9) (2003)
Mirza, N.A., Nehaniv, C.L., Dautenhahn, K., te Boekhorst, R.: Using sensory-motor phase-plots to characterise robot-environment interactions. In: CIRA 2005. Proc. of 6th IEEE International Symposium on Computational Intelligence in Robotics and Automation, pp. 581–586. IEEE Computer Society Press, Los Alamitos (2005)
Kaplan, F., Hafner, V.: Mapping the space of skills: An approach for comparing embodied sensorimotor organizations. In: ICDL 2005. Proceedings of the 4th IEEE International Conference on Development and Learning, pp. 129–134. IEEE Computer Society Press, Los Alamitos (2005)
Mirza, N.A., Nehaniv, C.L., Dautenhahn, K., te Boekhorst, R.: Interaction histories: From experience to action and back again. In: ICDL 2006. Proceedings of the 5th IEEE International Conference on Development and Learning, Bloomington, IN, USA, IEEE Computer Society Press, Los Alamitos (2006)
te Boekhorst, R., Lungarella, M., Pfeifer, R.: Dimensionality reduction through sensory-motor coordination. In: Kaynak, O., Alpaydin, E., Öja, E., Xu, L. (eds.) ICANN 2003 and ICONIP 2003. LNCS, vol. 2714, pp. 496–503. Springer, Heidelberg (2003)
Mirza, N.A., Nehaniv, C.L., Dautenhahn, K., te Boekhorst, R.: Grounded sensorimotor interaction histories in an information theoretic metric space for robot ontogeny. Adaptive Behavior 15(2), 167–187 (2007)
Crutchfield, J.: Information and its metric. In: Lam, L., Morris, H.C. (eds.) Nonlinear Structures in Physical Systems - Pattern Formation, Chaos and Waves, pp. 119–130. Springer-Verlag, New York (1990)
Mirza, N.A., Nehaniv, C.L., Dautenhahn, K., te Boekhorst, R.: Using temporal information distance to locate sensorimotor experience in a metric space. In: CEC 2005. Proc. of 2005 IEEE Congress on Evolutionary Computation, Edinburgh, Scotland, UK, 2-5 September 2005, vol. 1, pp. 150–157. IEEE Computer Society Press, Los Alamitos (2005)
Nehaniv, C.L., Polani, D., Olsson, L., Klyubin, A.S.: Information-theoretic modeling of sensory ecology. In: Laubichler, M., Müller, G.B. (eds.) Modeling Biology: Structures, Behavior, Evolution. The Vienna Series in Theoretical Biology, MIT Press, Cambridge (in press)
Chklovskii, D.B., Koulakov, A.A.: Maps in the brain: What can we learn from them? Annu. Rev. Neurosci. 27, 369–392 (2004)
Diamond, M.E., Petersen, R.S., Harris, J.A.: Learning through maps: Functional significance of topographic organization in the primary sensory cortex. J. Neurobiol. 41, 64–68 (1999)
Olsson, L., Nehaniv, C.L., Polani, D.: Measuring informational distances between sensors and sensor integration. In: Artificial Life X, MIT Press, Cambridge (2006)
King, A.J.: Sensory experience and the formation of a computational map of auditory space in the brain. BioEssays 21(11), 900–911 (1999)
Knudsen, E.I., Brainard, M.S.: Creating a unified representation of visual and auditory space in the brain. Annual Review of Neuroscience 18, 19–43 (1995)
King, A.J.: The superior colliculus. Current Biology 14(4), R335–R338 (2004)
Nehaniv, C.L., Dautenhahn, K., Loomes, M.J.: Constructive biology and approaches to temporal grounding in post-reactive robotics. In: McKee, G.T., Schenker, P., (eds.) Sensor Fusion and Decentralized Control in Robotics Systems II (September 19-20, Boston, Massachusetts), Proceedings of SPIE. vol. 3839 pp. 156–167 (1999)
Dautenhahn, K., Christaller, T.: Remembering, rehearsal and empathy - towards a social and embodied cognitive psychology for artifacts. In: Ó Nualláin, S., McKevitt, P., Mac Aogáin, E., (eds.) Two Sciences of the Mind: Readings in Cognitive Science and Consciousness. John Benjamins North America Inc. pp. 257–282 (1996)
Nehaniv, C.L.: Sensorimotor experience and its metrics. In: Proc. of 2005 IEEE Congress on Evolutionary Computation, Edinburgh, Scotland, UK, 2-5 September 2005, vol. 1, pp. 142–149. IEEE Computer Society Press, Los Alamitos (2005)
Nehaniv, C.L., Mirza, N.A., Dautenhahn, K., te Boekhorst, R.: Extending the temporal horizon of autonomous robots. In: Murase, K., Sekiyama, K., Kubota, N., Naniwa, T., Sitte, J. (eds.) AMiRE 2005. Proc. of the 3rd International Symposium on Autonomous Minirobots for Research and Edutainment, pp. 389–395. Springer, Heidelberg (2006)
Bruner, J.S., Sherwood, V.: Peekaboo and the learning of rule structures. In: Bruner, J., Jolly, A., Sylva, K. (eds.) Play: Its Role in Development and Evolution, pp. 277–285. Penguin, New York (1975)
Rochat, P., Querido, J.G., Striano, T.: Emerging sensitivity to the timing and structure of protoconversation in early infancy. Developmental Psychology 35(4), 950–957 (1999)
Song, S., Miller, K.D., Abbott, L.F.: Competitive Hebbian learning through spike-timing-dependent synaptic plasticity. Nature Neuroscience 3, 919–926 (2000)
Izhikevich, E.M.: Polychronization: Computation with spikes. Neural Computation 18, 245–282 (2006)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Nehaniv, C.L., Mirza, N.A., Olsson, L. (2007). Development Via Information Self-structuring of Sensorimotor Experience and Interaction. In: Lungarella, M., Iida, F., Bongard, J., Pfeifer, R. (eds) 50 Years of Artificial Intelligence. Lecture Notes in Computer Science(), vol 4850. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-77296-5_9
Download citation
DOI: https://doi.org/10.1007/978-3-540-77296-5_9
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-77295-8
Online ISBN: 978-3-540-77296-5
eBook Packages: Computer ScienceComputer Science (R0)