Emergence of an internal model in evolving robots subjected to sensory deprivation

Authors:
Onofrio Gigliotta;Giovanni Pezzulo;Stefano Nolfi
Affiliations:
Department of Relational Sciences, University of Naples Federico II, Naples, Italy and Istituto di Scienze e Tecnologie della Cognizione, CNR, Rome, Italy;Istituto di Linguistica Computazionale "Antonio Zampolli", CNR, Pisa, Italy;Istituto di Scienze e Tecnologie della Cognizione, CNR, Rome, Italy
Venue:
SAB'10 Proceedings of the 11th international conference on Simulation of adaptive behavior: from animals to animats
Year:
2010

Citing 8
Cited 0

Mental models: towards a cognitive science of language, inference, and consciousness

Mental models: towards a cognitive science of language, inference, and consciousness
Intelligence without representation

Artificial Intelligence
Towards a cognitive robotics

Adaptive Behavior
On the Coupling Between Agent Internal and Agent/ Environmental Dynamics: Development of Spatial Representations in Evolving Autonomous Robots

Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
A Study of Off-Line Uses of Anticipation

SAB '08 Proceedings of the 10th international conference on Simulation of Adaptive Behavior: From Animals to Animats
Efference copies in neural control of dynamic biped walking

Robotics and Autonomous Systems
Vision-Motor Abstraction toward Robot Cognition

ICONIP '09 Proceedings of the 16th International Conference on Neural Information Processing: Part II
Internal simulation of perception: a minimal neuro-robotic model

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this study we show how simulated robots evolved to display a navigation skills can spontaneously develop an internal model and rely on it to complete their task when sensory stimulation is temporarily unavailable. The analysis of some of the best evolved agents indicates that their internal model operates by anticipating functional properties of the next sensory state rather than the exact state that sensors would have assumed. The characteristics of the states that are anticipated and of the sensory-motor rules that determine how the agents react to the experienced states, however, ensure that the agents produce very similar behaviour during normal and blind phases in which sensory stimulation is available or is self-generated by the agent itself, respectively. The characteristics of the agents' internal models also ensure an effective transition during the phases in which agents' internal dynamics is decoupled and re-coupled with the sensory-motor flow.