Self-driven particle model for mixed traffic and other disordered flows

Abstract

Vehicles in developing countries have widely varying dimensions and speeds, and drivers tend to not follow lane discipline. In this flow state called "mixed traffic", the interactions between drivers and the resulting maneuvers resemble more that of general disordered self-driven particle systems than that of the orderly lane-based traffic flow of industrialized countries. We propose a general multi particle model for such self-driven "high-speed particles" and show that it reproduces the observed characteristics of mixed traffic. The main idea is to generalize a conventional acceleration-based car-following model to a two-dimensional force field. For in-line following, the model reverts to the underlying car-following model, for very slow speeds, it reverts to an anisotropic social-force model for pedestrians. With additional floor fields at the position of lane markings, the model reverts to an integrated car-following and lane-changing model with continuous lateral dynamics including cooperative aspects such as zip merging. With an adaptive cruise control (ACC) system as underlying car-following model, it becomes a controller for the acceleration and steering of autonomous vehicles in mixed or lane-based traffic.

Understanding the Lateral Dimension of Traffic: Measuring and Modeling Lane Discipline

“…The first study to call attention to the importance of this issue was that of Gunay ( 2 ). It has since been followed by a series of works presenting two-dimensional models focused primarily on situations of poor lane discipline ( 19–23 ). However, these formulations either do not model lateral position choice or, if they do, neglect the existence of lanes.…”

Calibrating Wiedemann-99 Model Parameters to Trajectory Data of Mixed Vehicular Traffic

“…A recently proposed model for lane-free mixed traffic (15) provides a generalized framework for extending conventional car-following models (including the Wiedemann car-following model) to a fully 2-D microscopic model. In the presence of multiple leaders and staggered following, this framework assumes, with good results, that the longitudinal dynamics depend only on the leader with the strongest interaction and that the repulsive force remains unchanged as long as there is a lateral overlap, that is, the longitudinal acceleration reverts to that of the underlying car-following model.…”

Lane-Free Artificial-Fluid Concept for Vehicular Traffic

“…To The low lane discipline and vehicle size diversity encountered in several developing countries motivated, in the last few years, some microscopic modeling works, which proposed, using various approaches, models for heterogeneous and laneless traffic; see for example [18], [19], where microscopic models for lane-less traffic are proposed, validated with real traffic data, and analyzed with respect to stability and other properties. Clearly, a major distinction to these modeling works is that they attempt to describe the driving behavior of real vehicles and drivers, while for TrafficFluid we need to design opportune movement strategies for safe and efficient CAV traffic flow.…”