Design of DQN-Based Path Tracking Algorithm for Robust Autonomous Driving

Seung Geon Yang, Eun Ho Cho, Jeongyun Kim, Seung Chan Lim

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

Despite the increasing interest in autonomous driving, significant challenges remain, particularly in achieving high and stable tracking performance. We herein propose a deep Q-network (DQN)-based path tracking algorithm to enhance autonomous vehicle navigation. By interpreting the path tracking task as a sequential decision-making problem, we develop a DQN-based steering control algorithm for precise path tracking. Simulation results confirm that the proposed algorithm significantly enhances tracking accuracy and stability, out performing the conventional methods.

Original languageEnglish
Title of host publicationICTC 2024 - 15th International Conference on ICT Convergence
Subtitle of host publicationAI-Empowered Digital Innovation
PublisherIEEE Computer Society
Pages1560-1561
Number of pages2
ISBN (Electronic)9798350364637
DOIs
StatePublished - 2024
Event15th International Conference on Information and Communication Technology Convergence, ICTC 2024 - Jeju Island, Korea, Republic of
Duration: 16 Oct 202418 Oct 2024

Publication series

NameInternational Conference on ICT Convergence
ISSN (Print)2162-1233
ISSN (Electronic)2162-1241

Conference

Conference15th International Conference on Information and Communication Technology Convergence, ICTC 2024
Country/TerritoryKorea, Republic of
CityJeju Island
Period16/10/2418/10/24

Keywords

  • Autonomous driving
  • deep Q-network
  • path tracking

Fingerprint

Dive into the research topics of 'Design of DQN-Based Path Tracking Algorithm for Robust Autonomous Driving'. Together they form a unique fingerprint.

Cite this