This Chapter concludes Part II of the present Volume. Here the hypothesis of an internal model arises is needed at the aim to generate internal representations which enable the robot to reach a suitable behavior so as to optimize ideally arbitrary motivational needs. Strongly based on the idea, common to Behavior-based robotics, that perception is a holistic process, strongly connected to behavioral needs of the robot, here we present a bio-inspired framework for sensing-perception-action, based on complex self-organizing dynamics. These are able to generate internal models of the environment, strictly depending both on the environment and on the robot motivation. The strategy, as a starting simple task, is applied to a roving robot in a random foraging task. Perception is here considered as a complex and emergent phenomenon where a huge amount of information coming from sensors is used to form an abstract and concise representation of the environment, useful to take a suitable action or sequence of actions. In this chapter a model for perceptual representation is formalized by means of Reaction-Diffusion Cellular Nonlinear Networks (RD-CNNs) used to generate self-organising Turing patterns. They are thought as attractive states for particular set of environmental conditions in order to associate, via a reinforcement learning, a proper action. Learning is also introduced at the afferent stage to shape the environment information according to the particular emerging pattern. The basins of attraction for the Turing patterns are so dynamically tuned by an unsupervised learning in order to form an internal, abstract and plastic representation of the environment, as recorded by the sensors. In the second part of the Chapter, the representation layer together with the other blocks already introduced in the previous Chapters (i.e. basic behaviours, correlation layer, memory blocks, and others), has been structured in an unique framework, the SPARK cognitive model. The role assigned to the representation layer inside this complete architecture consists in modulating the influence of each basic behaviour with respect to the final behaviour performed by the robot to fulfill the assigned mission. © Springer-Verlag Berlin Heidelberg 2009.

Complex systems and perception

Patane L.
2009-01-01

Abstract

This Chapter concludes Part II of the present Volume. Here the hypothesis of an internal model arises is needed at the aim to generate internal representations which enable the robot to reach a suitable behavior so as to optimize ideally arbitrary motivational needs. Strongly based on the idea, common to Behavior-based robotics, that perception is a holistic process, strongly connected to behavioral needs of the robot, here we present a bio-inspired framework for sensing-perception-action, based on complex self-organizing dynamics. These are able to generate internal models of the environment, strictly depending both on the environment and on the robot motivation. The strategy, as a starting simple task, is applied to a roving robot in a random foraging task. Perception is here considered as a complex and emergent phenomenon where a huge amount of information coming from sensors is used to form an abstract and concise representation of the environment, useful to take a suitable action or sequence of actions. In this chapter a model for perceptual representation is formalized by means of Reaction-Diffusion Cellular Nonlinear Networks (RD-CNNs) used to generate self-organising Turing patterns. They are thought as attractive states for particular set of environmental conditions in order to associate, via a reinforcement learning, a proper action. Learning is also introduced at the afferent stage to shape the environment information according to the particular emerging pattern. The basins of attraction for the Turing patterns are so dynamically tuned by an unsupervised learning in order to form an internal, abstract and plastic representation of the environment, as recorded by the sensors. In the second part of the Chapter, the representation layer together with the other blocks already introduced in the previous Chapters (i.e. basic behaviours, correlation layer, memory blocks, and others), has been structured in an unique framework, the SPARK cognitive model. The role assigned to the representation layer inside this complete architecture consists in modulating the influence of each basic behaviour with respect to the final behaviour performed by the robot to fulfill the assigned mission. © Springer-Verlag Berlin Heidelberg 2009.
2009
978-3-540-88463-7
File in questo prodotto:
Non ci sono file associati a questo prodotto.
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11570/3151078
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? 0
social impact