A General Purpose Distributed Learning Model for Robotic Ecologies

The design of a learning system for robotic ecologies need to account for some key aspects of the ecology model such as distributivity, heterogeneity of the computational, sensory and actuator capabilities, as well as self-configurability. The paper proposes general guiding principles for learning systems’ design that ensue from key ecology properties, and presents a distributed learning system for the Rubicon ecology that draws inspiration from such guidelines. The proposed learning system provides the Rubicon ecology with a set of generalpurpose learning services which can be used to learn generic computational tasks that involve predicting information of interest based on dynamic sensorial input streams.