An investigation into the relationship between type-2 FOU size and environmental uncertainty in robotic control
It addresses the problem of controller selection under uncertainty for robotic systems, but the findings are incremental as they confirm and detail known suggestions with mixed results.
This paper investigates whether type-2 fuzzy logic controllers outperform type-1 controllers under environmental uncertainty in robotic sailing, finding improved performance in some cases but noting that the size of the footprint of uncertainty (FOU) significantly affects results, with incorrect sizing leading to severe penalties.
It has been suggested that, when faced with large amounts of uncertainty in situations of automated control, type-2 fuzzy logic based controllers will out-perform the simpler type-1 varieties due to the latter lacking the flexibility to adapt accordingly. This paper aims to investigate this problem in detail in order to analyse when a type-2 controller will improve upon type-1 performance. A robotic sailing boat is subjected to several experiments in which the uncertainty and difficulty of the sailing problem is increased in order to observe the effects on measured performance. Improved performance is observed but not in every case. The size of the FOU is shown to be have a large effect on performance with potentially severe performance penalties for incorrectly sized footprints.