Curious Design Agents and Artificial Creativity


Creative products are generally recognised as satisfying two requirements: firstly they are useful, and secondly they are novel. Much effort in AI and design computing has been put into developing systems that can recognise the usefulness of the products that they generate. In contrast, the work presented in this thesis has concentrated on developing computational systems that are able to recognise the novelty of their work. The research has shown that when computational systems are given the ability to recognise both the novelty and the usefulness of their products they gain a level of autonomy that opens up new possibilities for the study of creative behaviour in single agents and the emergence of social creativity in multi-agent systems. The work presented in this thesis has developed a model of curiosity in design as the selection of design actions with the goal of generating novel artefacts. Agents that embody this model of curiosity are called “curious design agents”. The behaviour of curious design agents is demonstrated with a range of applications to visual and non- visual design domains. Visual domains include rectilinear drawings, Spirograph patterns, and “genetic artworks” similar to the work of Karl Sims. Non-visual domains include an illustrative abstract design space useful for visualising the behaviour of curious agents and the design of doorways to accommodate the passage of large crowds. The design methods used in the different domains show that the model of curiosity is applicable to models of designing by direct manipulation, parametric configuration or by using a separate design tool that embodies the generative aspects of the design process. In addition, an approach to developing multi-agent systems with autonomous notions of creativity called artificial creativity is presented. The opportunities for studying social creativity in design are illustrated with an artificial creativity system used to study the emergence of social notions of whom and what are creative in a society of curious design agents. Developing similar artificial creativity systems promises to be a useful synthetic approach to the study of socially situated, creative design.

PhD Thesis, University of Sydney