EUVIMEDEUVIMED entdecken
Crossref

Imagination-Augmented Hierarchical Reinforcement Learning for Safe and Interactive Autonomous Driving in Urban Environments

Sang-Hyun Lee, Yoonjae Jung, Seung-Woo Seo

IEEE Transactions on Intelligent Transportation Systems · 2024-12 · 25 (12) · 19522-19535

DOI: 10.1109/tits.2024.3457776 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Intelligent Transportation Systems, 2024-12. Verfasst von Sang-Hyun Lee und 2 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 61 Literaturangaben. Gefördert von: Korea National Police Agency through the Project “Development of Autonomous Driving Patrol Service for Active Prevention and Response to Traffic Accidents”.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Hierarchical reinforcement learning (HRL) incorporates temporal abstraction into reinforcement learning (RL) by explicitly taking advantage of hierarchical structures. Modern HRL typically designs a hierarchical agent composed of a high-level policy and low-level policies. The high-level policy selects which low-level policy to activate at a lower frequency and the activated low-level policy selects an action at each time step. Recent HRL algorithms have achieved performance gains over standard RL algorithms in synthetic navigation tasks. However, these HRL algorithms still cannot be applied to real-world navigation tasks. One of the main challenges is that real-world navigation tasks require an agent to perform safe and interactive behaviors in dynamic environments. In this paper, we propose imagination-augmented HRL (IAHRL) that efficiently integrates imagination into HRL to enable an agent to learn safe and interactive behaviors in real-world navigation tasks. Imagination is to predict the consequences of actions without interactions with actual environments. The key idea behind IAHRL is that the low-level policies imagine safe and structured behaviors, and then the high-level policy infers interactions with surrounding objects by interpreting the imagined behaviors. We also introduce a new attention mechanism that allows the high-level policy to be permutation-invariant to the order of surrounding objects and to prioritize our agent over them. To evaluate IAHRL, we introduce five complex urban driving tasks, which are among the most challenging real-world navigation tasks. The experimental results indicate that IAHRL enables an agent to perform safe and interactive behaviors, achieving higher success rates and lower average episode steps than baselines.

Förderung

  • Korea National Police Agency through the Project “Development of Autonomous Driving Patrol Service for Active Prevention and Response to Traffic Accidents”

Zitieren

APA

Lee, S., Jung, Y., & Seo, S. (2024). Imagination-Augmented Hierarchical Reinforcement Learning for Safe and Interactive Autonomous Driving in Urban Environments. IEEE Transactions on Intelligent Transportation Systems, 25(12), 19522-19535. https://doi.org/10.1109/tits.2024.3457776

Vancouver

Lee S, Jung Y, Seo S. Imagination-Augmented Hierarchical Reinforcement Learning for Safe and Interactive Autonomous Driving in Urban Environments. IEEE Transactions on Intelligent Transportation Systems. 2024;25(12):19522-19535. doi:10.1109/tits.2024.3457776

BibTeX
@article{Lee2024,
  author = {Lee, Sang-Hyun and Jung, Yoonjae and Seo, Seung-Woo},
  title = {Imagination-Augmented Hierarchical Reinforcement Learning for Safe and Interactive Autonomous Driving in Urban Environments},
  journal = {IEEE Transactions on Intelligent Transportation Systems},
  year = {2024},
  volume = {25},
  number = {12},
  pages = {19522--19535},
  doi = {10.1109/tits.2024.3457776}
}
Kostenlos starten →