Book ChapterDOI
Extended Homeostatic Adaptation: Improving the Link between Internal and Behavioural Stability
Hiroyuki Iizuka,Ezequiel A. Paolo +1 more
- pp 1-11
TLDR
The extended homeostatic networks designed to exploit the internal dynamics of a neural network in the absence of sensory input perform much better and are more adaptive to morphological disruptions that have never been experienced before by the agents.Abstract:
This study presents an extended model of homeostatic adaptation designed to exploit the internal dynamics of a neural network in the absence of sensory input. In order to avoid typical convergence to asymptotic states under these conditions plastic changes in the network are induced in evolved neurocontrollers leading to a renewal of dynamics that may favour sensorimotor adaptation. Other measures are taken to avoid loss of internal variability (as caused, for instance, by synaptic strength saturation). The method allows the generation of reliable adaptation to morphological disruptions in a simple simulated vehicle using a homeostatic neurocontroller that has been selected to behave homeostatically while performing the desired behaviour but non-homeostatically in other circumstances. The performance is compared with simple homeostatic neural controllers that have only been selected for a positive link between internal and behavioural stability. The extended homeostatic networks perform much better and are more adaptive to morphological disruptions that have never been experienced before by the agents.read more
Citations
More filters
Journal ArticleDOI
Enactive artificial intelligence: Investigating the systemic organization of life and mind
Tom Froese,Tom Ziemke +1 more
TL;DR: It is argued that the biological foundations of enactive cognitive science can provide the conceptual tools that are needed to diagnose more clearly the shortcomings of current embodied AI and provide a promising way of eventually overcoming the current limitations of embodied AI, especially in terms of providing fuller models of natural embodied cognition.
Journal ArticleDOI
Learning to perceive in the sensorimotor approach: Piaget’s theory of equilibration interpreted dynamically
Ezequiel A. Di Paolo,Ezequiel A. Di Paolo,Ezequiel A. Di Paolo,Xabier E. Barandiaran,Michael Beaton,Michael Beaton,Thomas Buhrmann +6 more
TL;DR: The compatibility between Piaget’s theory and the sensorimotor approach is demonstrated by providing a dynamical formalization of equilibration to give an explicit micro-genetic account of sensorsimotor learning and, by extension, of how the authors learn to perceive.
Journal ArticleDOI
Robotics Inspired in the Organism
TL;DR: In this article, a continuite vie-esprit appuyee sur des notions telles que corporeite, systemes complexes adaptatifs, enaction ainsi que sur des theorisations d'inspiration phenomenologique and existentialiste.
Journal ArticleDOI
Allostatic control for robot behavior regulation: a comparative rodent-robot study
Martí Sánchez-Fibla,Ulysses Bernardet,Erez Wasserman,Tatiana Pelc,Matti Mintz,Jadin C. Jackson,Carien S. Lansink,Cyriel M. A. Pennartz,Paul F. M. J. Verschure +8 more
TL;DR: It is shown that a rat is influenced by the shape of the arena in terms of its openness and the allostatic reactive control model is proposed as an augmentation of the Distributed Adaptive Control architecture and provides a further contribution towards the realization of an artificial rodent.
Journal ArticleDOI
Self-Organized Criticality, Plasticity and Sensorimotor Coupling. Explorations with a Neurorobotic Model in a Behavioural Preference Task
TL;DR: A conceptual model of a minimal neurorobotic agent solving a behavioural task that makes it possible to relate mechanistic (neurodynamic) and behavioural levels of description is presented and the role of conceptual models as mediators between nomothetic and mechanistic models is discussed.
References
More filters
Book
Design for a Brain: The origin of adaptive behaviour
TL;DR: This chapter discusses Adaptation in Iterated and Serial Systems, the Organism as Machine, and the Effects of Constancy.
Book
Intelligence as Adaptive Behavior: An Experiment in Computational Neuroethology
TL;DR: The Artificial Insect: Locomotion Controller, Lesion Studies, and Behavioral Choice - Discussion.
Toward the Evolution of Dynamical Neural Networks for Minimally Cognitive Behavior
TL;DR: The results of preliminary experiments on the evolution of dynamical neural networks for visually-guided orientation, object discrimination and accurate pointing with a simple manipulator to objects appearing in its field of view are presented.
Homeostatic adaptation to inversion of the visual field and other sensorimotor disruptions
Di Paolo,A Ezequiel +1 more
TL;DR: A novel neural architecture based on continuous dynamical neural networks is implemented to bring Ashbyan ideas on the relation between adaption and internal stability into the context of current research on evolutionary robotics.