Creative design is very hard to model or imitate by computers. However, there exist a variety of artificial intelligence techniques that can be applied to highly constrained, well-defined design tasks. Creative evolutionary design [1] is one such group of techniques with reported success. Here we present our genetic programming based method for automatic design of lace knitting stitch patterns. First we devise a genetic representation of knitting charts that accurately reflects their usage for hand knitting the pattern. We then apply a basic evolutionary algorithm for generating the patterns, where the key of success is evaluation. We propose automatic evaluation of the patterns, without interaction with the user. We present some patterns generated by the method and then discuss further possibilities for bringing automatic evaluation closer to human evaluation.
展开▼