Evolving the morphology of a neural network for controlling a foveating retina: and its test on a real robot

Authors:
Peter Eggenberger Hotz;Gabriel Gómex;Rolf Pfeifer
Affiliations:
Artificial Intelligence Laboratory, Dept. of Info. Tech., Univ. Zurich, Switzerland and Emergent Communication Mechanisms Project, ATR Human Information Science Laboratories, Kyoto, Japan;Artificial Intelligence Laboratory, Department of Information Technology, University of Zurich, Winterthurerstrasse 190, CH-8057 Zuerich, Switzerland;Artificial Intelligence Laboratory, Department of Information Technology, University of Zurich, Winterthurerstrasse 190, CH-8057 Zuerich, Switzerland
Venue:
ICAL 2003 Proceedings of the eighth international conference on Artificial life
Year:
2002

Citing 7
Cited 7

Fractals everywhere

Fractals everywhere
Artificial Life IV: Proceedings of the Fourth International Workshop on the Synthesis and Simlulation of Living Systmes

Artificial Life IV: Proceedings of the Fourth International Workshop on the Synthesis and Simlulation of Living Systmes
Proceedings of the 7th International Conference on Artificial Neural Networks

ICANN '97 Proceedings of the 7th International Conference on Artificial Neural Networks
Interposing an Ontogenetic Model Between Genetic Algorithms and Neural Networks

Advances in Neural Information Processing Systems 5, [NIPS Conference]
Synthesis of Developmental and Evolutionary Modeling of Adaptive Autonomous Agents

ICANN '97 Proceedings of the 7th International Conference on Artificial Neural Networks
Evolving 3d morphology and behavior by competition

Artificial Life
Evolution and development of neural controllers for locomotion, gradient-following, and obstacle-avoidance in artificial insects

IEEE Transactions on Neural Networks

Evolutionary models for maternal effects in simulated developmental systems

GECCO '05 Proceedings of the 7th annual conference on Genetic and evolutionary computation
Environment as a spatial constraint on the growth of structural form

Proceedings of the 9th annual conference on Genetic and evolutionary computation
Tree-Based Indirect Encodings for Evolutionary Development of Neural Networks

ICANN '08 Proceedings of the 18th international conference on Artificial Neural Networks, Part II
A developmental algorithm for ocular-motor coordination

Robotics and Autonomous Systems
Evolutionary simulations of maternal effects in artificial developmental systems

ECAL'05 Proceedings of the 8th European conference on Advances in Artificial Life
Evolution and analysis of genetic networks for stable cellular growth and regeneration

Artificial Life
A biologically constrained architecture for developmental learning of eye---head gaze control on a humanoid robot

Autonomous Robots

Quantified Score

Hi-index	0.00

Visualization

Abstract

The standard approach in evolutionary robotics is to evolve neural networks for control by encoding the parameters of the network in the genome. By contrast, we have evolved a neural controller based on biological principles from molecular and developmental biology. The kay principles employed in our algorithms model the specific ligand-receptor interactions and gene regulation. These mechanisms were used to control the growth of the axons, the generation of synapses including the synaptic efficiencies (i.e. the synaptic weights in a neural network model). The evolved neural network was then transferred to a real robotic system with results comparable to the ones achieved the simulation. We hypothesize that the incorporation of mechanisms of gene regulation potentially leads to more adaptive neural networks, that can help bridging the "reality gap" between simulation and the real world.