Exploring a Local Linear Model Tree Approach to Car‐Following

Abstract

Because car‐following (CF) models are fundamental to replicating traffic flow they have received considerable attention over the last 50 years. They are in a continuous state of improvement due to their significant role in traffic microsimulations, intelligent transportation systems, and safety engineering models. This article uses the local linear model tree (LOLIMOT) approach to model driver's CF behavior to incorporate human perceptual imperfections into a CF model. This model defines some localities in the input space. These localities are fuzzy and have overlaps with each other. Specific models for each of the localities are then defined and combined in a fuzzy manner to predict the final output. The model was developed using real world dynamic data sets. Three different data sets were used for training, testing, and validating the model. The performance of the model was compared to a number of existing CF models. The results showed very close agreement between the real data and the LOLIMOT outputs.

Longitudinal collision mitigation via coordinated braking of multiple vehicles using model predictive control

“…Therefore, it is necessary to consider the relationship between the coupled vehicle group and its surrounding environment, i.e., those vehicles in the front and rear of the group that cannot be coupled into the system because of the lack of V2V or automated control capability. Under actual traffic conditions, the coupled group is usually heterogeneous rather than homogeneous, and the group is generally comprised of vehicles of different masses, lengths, and braking systems operated by drivers exhibiting a variety of car-following [3,30] and lane-changing behaviors [33]. The heterogeneous nature of a coupled group can seriously affect platoon control [24] and also the capacity of signalized intersections [40].…”

Cellular automaton model simulating spatiotemporal patterns, phase transitions and concave growth pattern of oscillations in traffic flow

“…In order to simulate the features of traffic flow, different kinds of models have been proposed, such as the carfollowing models (Chandler et al 1958;Rakha and Crowther, 2003;Kesting and Treiber, 2008;Aghabayk et al 2013), the cellular automata models Hafstein et al, 2004) and hydrodynamic models (Lighthill and Whitham, 1955;Papageorgiou 1998;Wong and Wong 2002).…”

Spreading Patterns of Malicious Information on Single‐Lane Platooned Traffic in a Connected Environment

“…One type is macroscopic traffic flow models, which treat traffic as a compressive fluid and capture traffic behaviors using macroscopic parameters, including flow, density, and velocity (Bagloee et al, 2017;Mehrabipour and Hajbabaie, 2017). The other type is microscopic traffic flow models, such as carfollowing models (Woods and Berg, 2001;Aghabayk et al, 2013;Pariota et al, 2015;Li et al, 2018), lanechanging models (Gipps, 1986;Jula et al, 2000;Hidas, 2002), and cellular automation (Ding et al, 2009;Duff et al, 2015;Crociani and Lämmel, 2016) which can describe traffic dynamics at a higher detailed level like movements of individual vehicles. Previous studies (e.g., Kim et al, 2018) suggested to use macroscopic models, such as cell transmission model (CTM), to describe traffic behaviors.…”