Fuzzy inference systems for discretionary lane changing decisions: Model improvements and research challenges

Abstract

The lane changing decision model (LCDM) is a critical component in semi- and fully-automated driving systems. Recent research has found that the fuzzy inference system (FIS) is a promising approach to implementing LCDMs. To improve the FIS’s performance, this research reviewed the challenges in the development an FIS model to make the $\left(yes,no\right)$ decisions in discretionary lane changes. The FIS model was revised to bring its fuzzy inference rules more consistent with the fuzzy membership functions, and its composition and defuzzification methods more in line with the classical fuzzy logic theory. An equitable test data set with approximately equal number of $\left(yes,no\right)$ data points was assembled from the same next generation simulation (NGSIM) data used in the past research. The test results proved that: (1) an LCDM’s performance was dependent on how the $\left(yes,no\right)$ decisions in the test data set were manually labeled; (2) separating the fuzzy inference rules into a $\left(yes\right)$ group and a $\left(no\right)$ group and compute the results separately yielded potentially better decision accuracy. Furthermore, The gene expression programming model (GEPM) performed better than the improved FIS-based model. The findings led the authors to suggest two possible research directions: (1) add the subject vehicle’s speed as an input to the LCDM and redesign the decision-making model; (2) construct models for congested and uncongested traffic separately. The authors further suggested the use of instrumented vehicles to collect a set of high-fidelity lane changing data in the naturalistic driving environment.