A Study on Highway Driving Decision Making with Hybrid Action for Autonomous Vehicles Using Deep Reinforcement Learning 


Vol. 49,  No. 12, pp. 1671-1684, Dec.  2024
10.7840/kics.2024.49.12.1671


PDF
  Abstract

Various traffic situations on multi-lane highways pose challenges for autonomous driving, requiring adherence to traffic rules. Traditional rule-based decision-making struggles with safety in complex environments, leading to research on deep reinforcement learning (DRL). This paper proposes a decision-making method based on proximal policy optimization (PPO) with hybrid actions. The DRL model inputs the states of the ego vehicle and surrounding vehicles, outputting continuous longitudinal control and discrete lateral lane changes. For lane changes, actuator-level steering is controlled via pure pursuit. Experiments show that agents with hybrid actions are safer than those using only continuous or discrete actions.

  Statistics
Cumulative Counts from November, 2022
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


  Related Articles
  Cite this article

[IEEE Style]

S. Kim, K. Shin, J. Jeon, J. Bang, J. Kim, S. Jung, "A Study on Highway Driving Decision Making with Hybrid Action for Autonomous Vehicles Using Deep Reinforcement Learning," The Journal of Korean Institute of Communications and Information Sciences, vol. 49, no. 12, pp. 1671-1684, 2024. DOI: 10.7840/kics.2024.49.12.1671.

[ACM Style]

Seongjun Kim, Kyu-min Shin, Jun-seo Jeon, Ji-yoon Bang, Junyoung Kim, and Soyi Jung. 2024. A Study on Highway Driving Decision Making with Hybrid Action for Autonomous Vehicles Using Deep Reinforcement Learning. The Journal of Korean Institute of Communications and Information Sciences, 49, 12, (2024), 1671-1684. DOI: 10.7840/kics.2024.49.12.1671.

[KICS Style]

Seongjun Kim, Kyu-min Shin, Jun-seo Jeon, Ji-yoon Bang, Junyoung Kim, Soyi Jung, "A Study on Highway Driving Decision Making with Hybrid Action for Autonomous Vehicles Using Deep Reinforcement Learning," The Journal of Korean Institute of Communications and Information Sciences, vol. 49, no. 12, pp. 1671-1684, 12. 2024. (https://doi.org/10.7840/kics.2024.49.12.1671)
Vol. 49, No. 12 Index

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880