A computational approach on the co-development of artificial visual sensorimotor

Abstract

To follow a goal-directed behavior, an autonomous agent must be able to acquire knowledge about the causality between its motor actions and corresponding sensory feedback. Since the complexity of such sensorimotor relationships directly influences required cognitive resources, this work proposes that it is of importance to keep the agent’s sensorimotor relationships simple. This implies that the agent should be designed in a way such that sensory consequences can be described and predicted in a simplified manner. Living organisms implement this paradigm by adapting sensory and motor systems specifically to their behavior and environment. As a result, they are able to predict sensorimotor consequences with a strongly limited amount of (expensive) nervous tissue. In this context, the present work proposes that advantageous artificial sensory and motor layouts can be evolved by rewarding the ability to predict self-induced stimuli through simple sensorimotor relationships. Experiments consider a simulated agent recording realistic visual stimuli from natural images. The obtained results demonstrate the ability of the proposed method to (i) synthesize visual sensorimotor structures adapted to an agent’s environment and behavior, and (ii) serve as a computational model for testing hypotheses regarding the development of biological visual sensorimotor systems.

Keywords

Sensorimotor learning sensorimotor coupling self-organization of sensorimotor structures visual receptors visual motor primitives visual stimulus prediction

Get full access to this article

View all access options for this article.

References

Absil

P.-A.

Mahoney

Sepulchre

(2008). Optimization algorithms on matrix manifolds. Princeton University Press.

Cherniak

(1995). Neural component placement. Trens Neurosci., 18, 522–527.

Chklovskii

D. B.

(2004). Synaptic connectivity and neuronal morphology: viewpoint two sides of the same coin. Neuron, 43, 609–617.

Clippingdale

S. M.

Wilson

(1996). Self-similar neural networks based on a kohonen learning rule. Neural Networks, 9(5), 747–763.

Crapse

T. B.

Sommer

M. A.

(2008). Corollary discharge across the animal kingdom. Nat. Rev. Neuroscience, 9, 587–600.

Floreano

Kato

Marocco

Sauser

(2004). Coevolution of active vision and feature selection. Biol. Cybern., 90, 218–228.

Franceschini

Pichon

J. M.

Blanes

(1992). From insect vision to robot vision. Phil. Trans. Biological Sciences, 337, 283–294.

Franceschini

Ruffier

Serres

(2007). A bio-inspired flying robot sheds light on insect piloting abilities. Curr. Biol., 17, 329–335.

Lichtensteiger

Eggenberger

(1999). Evolving the morphology of a compound eye on a robot. In Proc. 3rd europ. worksh. on adv. mobile robots (pp. 127–134).

10.

Niven

J. E.

Laughlin

S. B.

(2008). Review, energy limitation as a selective pressure on the evolution of sensory systems. Experimental Biology, 211, 1792–1804.

11.

Olshausen

B. A.

Field

D. J.

(2004). Sparse coding of sensory inputs. Curr. Opin. Neurobiol., 14, 481–487.

12.

Parker

G. A.

Smith

J. M.

(1990). Optimality theory in evolutionary biology. Nature, 348, 27–33.

13.

Paul

(2006). Morphological computation, a basis for the analysis of morphology and control requirements. Robotics and Autonomous Systems, 54, 619–630.

14.

Pfeifer

Bongard

(2006). How the body shapes the way we think. MIT Press.

15.

Pfeifer

Iida

Gómez

(2006). Morphological computation for adaptive behavior and cognition. Int. Congress Series, 1291, 22–29.

16.

Pfeifer

Scheier

(1999). Understanding intelligence. MIT Press.

17.

Reiser

M. B.

Dickinson

M. H.

(2003). A test bed for insect-inspired robotic control. Phil. Trans. R. Soc. Lond. A, 361, 2267–2285.

18.

Ruesch

Ferreira

Bernardino

(2011). A measure of good motor actions for active visual perception. In Proc. int. conf. on development and learning (icdl), frankfurt, germany. IEEE.

19.

Ruesch

Ferreira

Bernardino

(2012). Predicting visual stimuli from self-induced actions: an adaptive model of a corollary discharge circuit. IEEE Transactions on Autonomous Mental Development, 4, 290–304.

20.

Swindale

N. V.

(2004). How different feature spaces may be represented in cortical maps. Network: Computation in Neural Systems, 15.

21.

Tibshirani

(1996). Regression shrinkage and selection via the lasso. Royal Statistical Society. Series B, 58, 267–288.

22.

Vinje

W. E.

Gallant

J. L.

(2000). Sparse coding and decorrelation in primary visual cortex during natural vision. Science, 287, 1273–1276.

23.

Webb

(2004). Neural mechanisms for prediction: Do insects have forward models? Trends in Neuroscience, 27, 278–282.

24.

Wehner

(1987). ‘matched filters’- neural models of the external world. Comp. Physiol. A, 161, 511–531.

25.

Wolpert

D. M.

Diedrichsen

Flanagan

J. R.

(2011). Principles of sensorimotor learning. Nature Reviews Neuroscience, 12, 739–751.

26.

Wolpert

D. M.

Kawato

(1998). Multiple paired forward and inverse models for motor control. Neural Networks, 11, 1317–1329.