Evolutionary Generation of Artificial Creature’s Personality for Ubiquitous Services

Abstract

Ubiquitous robot systems represent the state-of-the-art in robotic technology. This paradigm seamlessly blendsmobile robot technology (Mobot) with distributed sensor systems (Embot) and overseeing software intelligence (Sobot), for various integrated services. The wide scope for research in each component area notwithstanding, the design of the Sobot is critical since it performs the dual purpose of overseeing intelligence as well as user interface. The Sobot is hencemodeled as an Artificial Creature with autonomously driven behavior. This chapter discusses the evolutionary generation of an artificial creature’s personality. The artificial creature has its own genome in which each chromosome consists of many genes that contribute to defining its personality. 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 artificial creature’s personality while manually assigning gene values for the individual genome. One effective approach to counter these problems is the Evolutionary Generative Process for an Artificial Creature’s Personality (EGPP) which forms the focus of this chapter. EGPP evolves a genome population such that it customizes the genome, meeting a simplified set of personality traits desired by the user. An evaluation procedure for each genome of the population is carried out in a virtual environment using tailored perception scenarios. Effectiveness of this scheme is demonstrated by using an artificial creature Sobot, ‘Rity’ in the virtual 3D world created in a PC, designed to be a believable interactive software agent for human–robot interaction.