Decision-Making Policy for Autonomous Vehicles on Highways Using Deep Reinforcement Learning (DRL) Method

Ali Rizehvandi, Shahram Azadi, Arno Eichberger

Research output: Contribution to journalArticlepeer-review

Abstract

Automated driving (AD) is a new technology that aims to mitigate traffic accidents and enhance driving efficiency. This study presents a deep reinforcement learning (DRL) method for autonomous vehicles that can safely and efficiently handle highway overtaking scenarios. The first step is to create a highway traffic environment where the agent can be guided safely through surrounding vehicles. A hierarchical control framework is then provided to manage high-level driving decisions and low-level control commands, such as speed and acceleration. Next, a special DRL-based method called deep deterministic policy gradient (DDPG) is used to derive decision strategies for use on the highway. The performance of the DDPG algorithm is compared with that of the DQN and PPO algorithms, and the results are evaluated. The simulation results show that the DDPG algorithm can effectively and safely handle highway traffic tasks.
Original languageEnglish
Pages (from-to)564-577
Number of pages14
JournalAutomation
Volume5
Issue number4
DOIs
Publication statusPublished - Dec 2024

Keywords

  • autonomous vehicles
  • DDPG algorithm
  • decision-making
  • deep reinforcement learning (DRL) method
  • overtaking

ASJC Scopus subject areas

  • Automotive Engineering
  • Computer Science (miscellaneous)
  • Engineering (miscellaneous)
  • Control and Systems Engineering

Fields of Expertise

  • Mobility & Production

Treatment code (Nähere Zuordnung)

  • Theoretical

Fingerprint

Dive into the research topics of 'Decision-Making Policy for Autonomous Vehicles on Highways Using Deep Reinforcement Learning (DRL) Method'. Together they form a unique fingerprint.
  • DVS: Vehicle Dynamics

    Koglbauer, I. V. (Co-Investigator (CoI)), Lex, C. (Co-Investigator (CoI)), Shao, L. (Co-Investigator (CoI)), Semmer, M. (Co-Investigator (CoI)), Rogic, B. (Co-Investigator (CoI)), Peer, M. (Co-Investigator (CoI)), Hackl, A. (Co-Investigator (CoI)), Sternat, A. S. (Co-Investigator (CoI)), Schabauer, M. (Co-Investigator (CoI)), Samiee, S. (Co-Investigator (CoI)), Eichberger, A. (Co-Investigator (CoI)), Ager, M. (Co-Investigator (CoI)), Malić, D. (Co-Investigator (CoI)), Wohlfahrter, H. (Co-Investigator (CoI)), Scherndl, C. (Co-Investigator (CoI)), Magosi, Z. F. (Co-Investigator (CoI)), Orucevic, F. (Co-Investigator (CoI)), Puščul, D. (Co-Investigator (CoI)), Arefnezhad, S. (Co-Investigator (CoI)), Karoshi, P. (Co-Investigator (CoI)), Schöttel, C. E. (Co-Investigator (CoI)), Pandurevic, A. (Co-Investigator (CoI)), Harcevic, A. (Co-Investigator (CoI)), Wellershaus, C. (Co-Investigator (CoI)), Li, H. (Co-Investigator (CoI)), Mihalj, T. (Co-Investigator (CoI)), Kanuric, T. (Co-Investigator (CoI)), Gu, Z. (Co-Investigator (CoI)), Wallner, D. (Co-Investigator (CoI)), De Cristofaro, F. (Co-Investigator (CoI)), Soboleva, K. (Co-Investigator (CoI)), Nalic, D. (Co-Investigator (CoI)), Bernsteiner, S. (Co-Investigator (CoI)), Kraus, H. (Co-Investigator (CoI)), Zhao, Y. (Co-Investigator (CoI)), Bodner, J. (Co-Investigator (CoI)), Bui, D. T. (Co-Investigator (CoI)), Hirschberg, W. (Co-Investigator (CoI)), Plöckinger, M. (Co-Investigator (CoI)) & Khoshnood Sarabi, N. (Co-Investigator (CoI))

    1/01/1131/12/24

    Project: Research area

Cite this