Iterative Rule Learning of Quantified Fuzzy Rules for control in mobile robotics
Learning controllers in mobile robotics usually requires expert knowledge to define the input variables. However, these definitions could be obtained within the algorithm that generates the controller. This cannot be done using conventional fuzzy propositions, as the expressiveness that is necessary to summarize tens or hundreds of input variables in a proposition is high. In this paper the Quantified Fuzzy Rules (QFRs) model has been used to transform low-level input variables into highlevel input variables, which are more appropriate inputs to learn a controller. The algorithm that learns QFRs is based on the Iterative Rule Learning approach. The algorithm has been tested learning a controller in mobile robotics and using several complex simulated environments. Results show a good performance of our proposal, which has been compared with another three approaches
keywords: Mobile Robotics, Quantified Fuzzy Rules, Iterative Rule Learning.