Experimenting With an Efficient Driver Behavior Dynamical Model Applicable to Simulated Lane Changing Tasks

Abstract

We test an approach to modelling the car driver behaviour during simulated lane changing tasks, aiming to obtain a sufficiently precise model in the simplest possible form, namely, with a small number of parameters. Various applications of such models are available in the literature. Based on a recent review of the research to date, the cybernetic single-loop transfer function models employing McRuer’s theory are applied. The purpose of the presented method is to evaluate the optimal structure of the transfer function via cross-validation as a technique known from machine learning. The experiments utilize a driving simulator with in-house developed software; this configuration facilitates acquiring the data at the desired sampling frequency and in a manner that ensures the repeatability of the test process scenarios. Using the cross-validation results, we evaluate the second-order model with a derivative state and a reaction delay component as an optimal structure for approximating the measured data, which originated from a set of measurements on 92 active drivers. Even though more complex driving tasks could require high-order models, driver’s control action during our specific experiment is described through only four parameters. The parameters are jointly determined by the current driver’s mental state and the testing conditions defined in our scenario. Since the parameters are related to his/her dynamical behaviour, they allow easier mutual comparison of the drivers than complex models with many parameters. The results are verified via establishing a relationship to the multi-loop model presented in the recent literature. The larger dataset enables evaluating the confidence intervals of the drivers’ parameters which is inconvenient with 4 to 10 drivers commonly presented in the relevant sources.We test an approach to modelling the car driver behaviour during simulated lane changing tasks, aiming to obtain a sufficiently precise model in the simplest possible form, namely, with a small number of parameters. Various applications of such models are available in the literature. Based on a recent review of the research to date, the cybernetic single-loop transfer function models employing McRuer’s theory are applied. The purpose of the presented method is to evaluate the optimal structure of the transfer function via cross-validation as a technique known from machine learning. The experiments utilize a driving simulator with in-house developed software; this configuration facilitates acquiring the data at the desired sampling frequency and in a manner that ensures the repeatability of the test process scenarios. Using the cross-validation results, we evaluate the second-order model with a derivative state and a reaction delay component as an optimal structure for approximating the measured data, which originated from a set of measurements on 92 active drivers. Even though more complex driving tasks could require high-order models, driver’s control action during our specific experiment is described through only four parameters. The parameters are jointly determined by the current driver’s mental state and the testing conditions defined in our scenario. Since the parameters are related to his/her dynamical behaviour, they allow easier mutual comparison of the drivers than complex models with many parameters. The results are verified via establishing a relationship to the multi-loop model presented in the recent literature. The larger dataset enables evaluating the confidence intervals of the drivers’ parameters which is inconvenient with 4 to 10 drivers commonly presented in the relevant sources.