Learning motor dependent Crutchfield's information distance to anticipate changes in the topology of sensory body maps

Thomas Schatz 1 Pierre-Yves Oudeyer 1
1 Flowers - Flowing Epigenetic Robots and Systems
Inria Bordeaux - Sud-Ouest, U2IS - Unité d'Informatique et d'Ingénierie des Systèmes
Abstract : What can a robot learn about the structure of its own body when he does not already know the semantics, the type and the position of its sensors and motors? Previous work has shown that an information theoretic approach, based on pairwise Crutchfield's information distance on sensorimotor channels, could allow to measure the informational topology of the set of sensors, i.e. reconstruct approximately the topology of the sensory body map. In this paper, we argue that the informational sensors topology changes with motor configurations in many robotic bodies, but yet, because measuring Crutchfield's distance is very time consuming, it is impossible to remeasure the body's topology for each novel motor configuration. Rather, a model should be learnt that allows the robot to predict Crutchfield's informational distances, and thus anticipate informational body maps, for novel motor configurations. We present experiments showing that learning motor dependent Crutchfield distances can indeed be achieved.
Document type :
Conference papers
Complete list of metadatas

Cited literature [12 references]  Display  Hide  Download

https://hal.inria.fr/inria-00420186
Contributor : Jérôme Béchu <>
Submitted on : Monday, September 28, 2009 - 1:45:27 PM
Last modification on : Wednesday, July 3, 2019 - 10:48:03 AM
Long-term archiving on : Tuesday, June 15, 2010 - 10:17:58 PM

File

SchatzOudeyerICDL09.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00420186, version 1

Citation

Thomas Schatz, Pierre-Yves Oudeyer. Learning motor dependent Crutchfield's information distance to anticipate changes in the topology of sensory body maps. IEEE International Conference on Learning and Development, 2009, Shangaï, China. pp.n/a. ⟨inria-00420186⟩

Share

Metrics

Record views

680

Files downloads

217