Analysis of Drivers' Path Follow Behaviour

Gergő Ignéczi, Ernő Horváth, Attila Borsos

2024

Abstract

Lane keeping is a complex, multi-dimensional problem in terms of driving tasks. The lane-following driver models typically treat the control task as an end-to-end problem where the entire control chain is modelled as a human driver. However, the driver does not actively control the vehicle all the time, but follow a drift and compensate strategy, resulting in oscillations around their planned path. We have separated this oscillation scheme by filtering drivers’ selected offset to the centerline of the lane. It has been shown that there is a certain amount of offset error up to which drivers drift away from the planned path. At this point drivers intervene by applying torque to the steering wheel and steer the vehicle back onto the path. This type of drift and compensate strategy was modelled using Model Predictive Control (MPC) with event-based weights of its cost function. The proposed driver model calculates both the intervention point and the weights of the MPC based on real drivers’ data. As a result, the model together with the MPC can accurately plan the oscillation path of the drivers, contributing to a better understanding of how the driver tolerates offset errors.

Paper Citation

in Harvard Style

Ignéczi G., Horváth E. and Borsos A. (2024). Analysis of Drivers' Path Follow Behaviour. In Proceedings of the 21st International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO; ISBN 978-989-758-717-7, SciTePress, pages 93-100. DOI: 10.5220/0012889100003822

in Bibtex Style

@conference{icinco24,
author={Gergő Ignéczi and Ernő Horváth and Attila Borsos},
title={Analysis of Drivers' Path Follow Behaviour},
booktitle={Proceedings of the 21st International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO},
year={2024},
pages={93-100},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012889100003822},
isbn={978-989-758-717-7},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 21st International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO
TI - Analysis of Drivers' Path Follow Behaviour
SN - 978-989-758-717-7
AU - Ignéczi G.
AU - Horváth E.
AU - Borsos A.
PY - 2024
SP - 93
EP - 100
DO - 10.5220/0012889100003822
PB - SciTePress