Modeling with discrete-time recurrent fuzzy systems via mixed-integer optimization
Fuzzy Sets and Systems
| Hi-index | 0.01 |
In this paper, we propose a model for microscopic traffic simulation, which uses recurrent fuzzy systems. Its rule base reflects the recurrent decisions of the vehicle drivers. In contrast to cellular automata models, which also work rule based, our proposed model processes vague or "fuzzy" data and utilizes full intervals for the state values, e.g. for the velocities. We show that the recurrent fuzzy system is capable of modeling traffic flow that exhibits realistic macroscopic behavior and where the vehicle velocities are no longer confined to a small set of discrete values on the microscopic level.