The standardized data may then easily move within a network and connect to other systems without any time or geographical limitations. This concept is fundamental to the idea of the ubiquitous robot (Ubibot). Here the notion of the ubiquitous robot in a ubiquitous space is presented and the Ubibot is further classified as a Sobot, Embot, or Mobot. For implementing the concept of the Ubibot, this thesis defines the standardized data between Ubibots as the robot genome and proposes its generative mechanism employing evolutionary algorithm or neural network algorithm.
A genetic robot is defined as one which has its own robot genome that is composed of multiple artificial chromosomes. Each chromosome in a robot genome consists of many genes that contribute to defining the robot``s personality. They are also a factor in determining its internal state and external behaviors at any moment in time.
The structure of the robot genome provides three primary advantages. It may allow artificial reproduction, reusability between robots and the ability to evolve. The large number of genes also allows for a highly complex system, however it becomes increasingly difficult and time-consuming to ensure reliability, variability and consistency for the robot``s personality while manually initializing values for the individual genes.
To overcome this difficulty, this thesis proposes an evolutionary generative algorithm for a genetic robot``s personality (EGAGRP). EGAGRP evolves a gene pool that customizes the robot``s genome so that it closely matches a simplified set of features desired by the user. It does this using several new techniques. It acts on a 2 dimensional individual upon which a new masking method, the Eliza-Meme scheme, is used to derive a plausible individual given the restricted preference settings desired by the user. The proposed crossover method allows reproduction for the 2-dimensional genome in a manner that closely matches living creatures. Finally, the evalua...