A binary decision model for discretionary lane changing move based on fuzzy inference system

TLDR: A Fuzzy Inference System (FIS) which models a driver’s binary decision to or not to execute a discretionary lane changing move on freeways and has a potential to be implemented in lane change advisory systems, in autonomous vehicles, as well as microscopic traffic simulation tools.

Abstract: This paper presents a Fuzzy Inference System (FIS) which models a driver’s binary decision to or not to execute a discretionary lane changing move on freeways. It answers the following question “Is it time to begin to move into the target lane?” after the driver has decided to change lane and have selected the target lane. The system uses four input variables: the gap between the subject vehicle and the preceding vehicle in the original lane, the gap between the subject vehicle and the preceding vehicle in the target lane, the gap between the subject vehicle and the following vehicle in the target lane, and the distance between the preceding and following vehicles in the target lanes. The input variables were selected based on the outcomes of a drivers survey, and can be measured by sensors instrumented in the subject vehicle. The FIS was trained with Next Generation SIMulation (NGSIM) vehicle trajectory data collected at the I-80 Freeway in Emeryville, California, and then tested with data collected at the U.S. Highway 101 in Los Angeles, California. The results of the test have shown that the system made lane change recommendations of “yes, change lane” with 82.2% accuracy, and “no, do not change lane” with 99.5% accuracy. These accuracies are better than the same performance measures given by the TRANSMODELER’s gap acceptance model for discretionary lane change on freeways, which is also calibrated with NGSIM data. The developed FIS has a potential to be implemented in lane change advisory systems, in autonomous vehicles, as well as microscopic traffic simulation tools.