A Physics-Informed Generative Car-Following Model for Connected Autonomous Vehicles
نویسندگان
چکیده
This paper proposes a novel hybrid car-following model: the physics-informed conditional generative adversarial network (PICGAN), designed to enhance multi-step modeling in mixed traffic flow scenarios. model leverages strengths of both physics-based and deep-learning-based models. By taking advantage inherent structure GAN, PICGAN eliminates need for an explicit weighting parameter typically used combination traditional data-driven The effectiveness proposed is substantiated through case studies using NGSIM I-80 dataset. These demonstrate model’s superior trajectory reproduction, suggesting its potential as strong contender replace conventional models prediction tasks. Furthermore, deployment significantly enhances stability efficiency environments. Given reliable stable results, framework contributes substantially development efficient longitudinal control strategies connected autonomous vehicles (CAVs) real-world conditions.
منابع مشابه
Benefits of V2V Communication for Autonomous and Connected Vehicles
In this paper, we investigate the benefits of Vehicleto-Vehicle (V2V) communication for autonomous vehicles and provide results on how V2V information helps reduce employable time headway in the presence of parasitic lags. For a string of vehicles adopting a Constant Time Headway Policy (CTHP) and availing the on-board information of predecessor’s vehicle position and velocity, the minimum empl...
متن کاملA Car Following Model for Motorway Traffic
This paper presents a new car-following model which aims to capture some of the key motorway flow characteristics, namely traffic breakdown, hysteresis, shockwave propagation as well as close-following behaviour. The model proposes three different driving states: non-alert, alert and close-following. Under the different driving states, drivers apply different reaction time and acceleration. Thi...
متن کاملA Path-Following Preview Controller for Autonomous Air Vehicles
This paper addresses the path-following problem of steering an autonomous air vehicle along a predefined 3-D path, while tracking a desired velocity profile. The presented solution relies on the definition of a path-dependent error space to express the dynamic model of the vehicle, which exhibits a high degree of directional accuracy. The proposed methodology adopts a polytopic Linear Parameter...
متن کاملA 3d Path-following Velocity-tracking Controller for Autonomous Vehicles
This paper addresses the path-following problem of steering an autonomous vehicle along a desired path, while tracking a predefined velocity profile. The presented solution relies on the definition of a path-dependent error space to express the dynamic model of the vehicle, which is specially suited for a Dmethodology controller implementation. The error space exhibits a high-degree of directio...
متن کاملA Dynamic Programming Based Path-following Controller for Autonomous Vehicles
The problem of path following for autonomous vehicles under adversarial behaviour is considered. The objective is to keep the cross-track error to the reference path inside a given tolerance interval. The adversarial behaviour models system uncertainty and unknown or poorly estimated bounded disturbances to ensure that the concept of weakly invariant set is used, i.e., the set of states that th...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Entropy
سال: 2023
ISSN: ['1099-4300']
DOI: https://doi.org/10.3390/e25071050