Robot Learning by Guided Self-Organization

Abstract

Self-organizing processes are not only crucial for the development of living beings, but can also spur new developments in robotics, e. g. to increase fault tolerance and enhance flexibility, provided that the prescribed goals can be realized at the same time. This combination of an externally specified objective and autonomous exploratory behavior is very interesting for practical applications of robot learning. In this chapter, we will present several forms of guided self-organization in robots based on homeokinesis.Self-organization in the sense used in natural sciences means the spontaneous creation of patterns in space and/or time in systems consisting of many individual components. This involves the emergence, meaning the spontaneous creation, of structures or functions that are not directly explainable from the interactions between the constituents of the system. Examples are for instance spontaneous magnetization, convection patterns and reaction diffusion systems leading to the wonderful coloring of shells or animal coats. For robotic applications it is important to translate self-organization effects to a single robots considered as complex physical systems consisting of many constituents that are constraining each other in an intensive

Entropy Methods in Guided Self-Organisation

“…The approach advocated in the paper not only illustrates the guided self-organisation of a specific embodied system, but also highlights a methodological perspective on the research field: guidance and self-organisation within a dynamic system may be combined through a proper coupling of the behavioral primitives with (selectable) attractors, setting suitable levels of noise and appropriately expressing current goals via the sensory feedback function. This research perspective is well aligned with the view on GSO developed at the intersection of the theory of dynamical systems and machine learning [49][50][51][52][53][54][55][56]: in order to guide a dynamical system, one may restrict its flow to a certain region in phase space, allowing for an otherwise unrestricted development within this bounded area of phase space [57].…”