Techniques for inferring context-free Lindenmayer systems with genetic algorithm

Lindenmayer systems (L-systems) are a formal grammar system, where the most notable feature is a set of rewriting rules that are used to replace every symbol in a string in parallel; by repeating this process, a sequence of strings is produced. Some symbols in the strings may be interpreted as instructions for simulation software. Thus, the sequence can be used to model the steps of a process. Currently, creating an L-system for a specific process is done by hand by experts through much effort. The inductive inference problem attempts to infer an L-system from such a sequence of strings generated by an unknown system; this can be thought of as an intermediate step to inferring from a sequence of images. This paper evaluates and analyzes different genetic algorithm encoding schemes and mathematical properties for the L-system inductive inference problem. A new tool, the Plant Model Inference Tool for Deterministic Context-Free L-systems (PMIT-D0L) is implemented based on these techniques. PMIT-D0L is successfully evaluated on 28 known L-systems created by experts with alphabets up to 31 symbols, and PMIT-D0L can successfully infer even the largest of these L-systems in less than a few seconds. It is also evaluated and can correctly infer any system in a larger test set of algorithmically created L-systems with much larger alphabets.