Simulation of Vehicles’ Gap Acceptance Decision at Unsignalized Intersections Using SUMO

Implementing Artificial Neural Network-Based Gap Acceptance Models in the Simulation Model of a Traffic Circle in SUMO

“…Therefore, accurate replication of traffic behavior models, such as gap acceptance, car following, lane changing, and so on, necessitates performing a calibration and validation process with the objective of minimizing the difference between simulated and observed outputs (28). There is rich literature focusing on assessing the impact of various design and operational alternatives using simulation models (3,19,(27)(28)(29)(30)(31). Leite et al (31) examined the performance of a roundabout under various operational conditions, such as changing the speed and acceleration within roundabouts as well as the minimum distance between vehicles, with the application of the SUMO simulation tool.…”

“…On the other hand, the probabilistic method takes into account the inconsistency and heterogeneity in the gap acceptance behavior of drivers in the minor stream and treats the critical gap as a random variable. There are different methods of calculating the critical gap in the literature, which includes Raff’s method, the clearing time method, the binary probit model, the maximum likelihood method, and so forth, as well as machine learning methods, such as the decision tree (DT), random forest (RF), support vector machine (SVM), and ANN methods ( 13 – 27 ). For example, Sangole and Patil ( 21 ) applied an adaptive neuro-fuzzy interface system (ANFIS) to model drivers’ gap acceptance behavior at a limited priority T-intersection.…”

“…The study concluded that the ANN model outperformed the GHR model in reproducing drivers’ car-following behavior. Bagheri et al ( 19 ) evaluated the feasibility of validating vehicles’ gap acceptance decisions in a stop-controlled intersection using the ANN model and microscopic traffic simulation programming in SUMO. The analysis results indicated that the ANN-based SUMO model produced superior results and led to significantly more realistic driving behavior in the major stream compared to the SUMO model with default gap acceptance parameters and the SUMO model with calibrated gap acceptance parameters.…”

“…This paper intends to close this gap by reproducing the real-world vehicles’ gap acceptance behavior in three different intersections at a traffic circle using the ANN method and implementing it in SUMO through its API capability. This work is an extension of Bagheri et al ( 19 ), in which only a stop-controlled intersection was modeled independently from the traffic circle and its surrounding network.…”

What Do Traffic Simulations Have to Provide for Virtual Road Safety Assessment? Human Error Modeling in Traffic Simulations

“…Otherwise, the speed must be adjusted (see [151], [152], [153], [154]). In contrast to gap acceptance models based on kinematic equations, there are also machine learning approaches (see [155], [156]).…”