Path Following with Deep Reinforcement Learning for Autonomous Cars

Khaled Alomari, Ricardo Mendoza, Daniel Goehring, Raúl Rojas

2021

Abstract

Path-following for autonomous vehicles is a challenging task. Choosing the appropriate controller to apply typical linear/nonlinear control theory methods demands intensive investigation on the dynamics and kinematics of the system. Furthermore, the non-linearity of the system’s dynamics, the complication of its analytical description, disturbances, and the influence of sensor noise, raise the need for adaptive control methods for reaching optimal performance. In the context of this paper, a Deep Reinforcement Learning (DRL) approach with Deep Deterministic Policy Gradient (DDPG) is employed for path tracking of an autonomous model vehicle. The RL agent is trained in a 3D simulation environment. It interacts with the unknown environment and accumulates experiences to update the Deep Neural Network. The algorithm learns a policy (sequence of control actions) that solves the designed optimization objective. The agent is trained to calculate heading angles to follow a path with minimal cross-track error. In the final evaluation, to prove the trained policy’s dynamic, we analyzed the learned steering policy strength to respond to more extensive and smaller steering values with keeping the cross-track error as small as possible. In conclusion, the agent could drive around the track for several loops without exceeding the maximum tolerated deviation, moreover, with reasonable orientation error.

Paper Citation

in Harvard Style

Alomari K., Mendoza R., Goehring D. and Rojas R. (2021). Path Following with Deep Reinforcement Learning for Autonomous Cars. In Proceedings of the 2nd International Conference on Robotics, Computer Vision and Intelligent Systems - Volume 1: ROBOVIS, ISBN 978-989-758-537-1, pages 173-181. DOI: 10.5220/0010715400003061

in Bibtex Style

@conference{robovis21,
author={Khaled Alomari and Ricardo Mendoza and Daniel Goehring and Raúl Rojas},
title={Path Following with Deep Reinforcement Learning for Autonomous Cars},
booktitle={Proceedings of the 2nd International Conference on Robotics, Computer Vision and Intelligent Systems - Volume 1: ROBOVIS,},
year={2021},
pages={173-181},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010715400003061},
isbn={978-989-758-537-1},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 2nd International Conference on Robotics, Computer Vision and Intelligent Systems - Volume 1: ROBOVIS,
TI - Path Following with Deep Reinforcement Learning for Autonomous Cars
SN - 978-989-758-537-1
AU - Alomari K.
AU - Mendoza R.
AU - Goehring D.
AU - Rojas R.
PY - 2021
SP - 173
EP - 181
DO - 10.5220/0010715400003061