Best Papers
 Real-Time Hierarchical Deep Reinforcement Learning-Based Drone Trajectory Generation Algorithm Parameter Control 


Vol. 48,  No. 10, pp. 1238-1246, Oct.  2023
10.7840/kics.2023.48.10.1238


PDF Full-Text
  Abstract

With the increasing use of drones, research on drone trajectory generation algorithms has gained significant momentum. These algorithms aim to generate real-time trajectories while considering obstacle avoidance. Recent advancements have shown promising results in generating safe and efficient trajectories in complex dynamic environments, such as forests, as well as controlling multiple drones simultaneously. However, most existing drone trajectory generation algorithms impose limitations on the maximum speed and acceleration parameters to ensure drone stability. These restrictions on speed-related parameters hinder the efficiency and practicality of drones. In this paper, we propose a novel approach called “Hierarchical Deep Reinforcement Learning-Based Active Parameter Control Algorithm” that addresses this limitation. This algorithm dynamically sets the maximum speed and acceleration parameters of a drone based on the real-time environment using a hierarchical reinforcement learning framework. The upper layer agent in the hierarchy is responsible for adjusting the maximum speed and acceleration parameters considering the current environmental conditions. The lower layer agent then utilizes these parameters to generate a real-time trajectory. Notably, this approach can be applied to all drone trajectory generation algorithms that involve setting maximum speed and maximum acceleration. Through extensive simulations, we demonstrate that applying the proposed algorithm to drone trajectory generation algorithms results in superior performance in terms of speed, path length, and path smoothness. These improvements showcase the potential of our approach in enhancing the efficiency and overall capabilities of drones operating in complex and dynamic environments.

  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.


  Cite this article

[IEEE Style]

C. Ji, Y. Han, S. Moon, "Real-Time Hierarchical Deep Reinforcement Learning-Based Drone Trajectory Generation Algorithm Parameter Control," The Journal of Korean Institute of Communications and Information Sciences, vol. 48, no. 10, pp. 1238-1246, 2023. DOI: 10.7840/kics.2023.48.10.1238.

[ACM Style]

Chang-Hun Ji, Youn-Hee Han, and Sung-Tae Moon. 2023. Real-Time Hierarchical Deep Reinforcement Learning-Based Drone Trajectory Generation Algorithm Parameter Control. The Journal of Korean Institute of Communications and Information Sciences, 48, 10, (2023), 1238-1246. DOI: 10.7840/kics.2023.48.10.1238.

[KICS Style]

Chang-Hun Ji, Youn-Hee Han, Sung-Tae Moon, "Real-Time Hierarchical Deep Reinforcement Learning-Based Drone Trajectory Generation Algorithm Parameter Control," The Journal of Korean Institute of Communications and Information Sciences, vol. 48, no. 10, pp. 1238-1246, 10. 2023. (https://doi.org/10.7840/kics.2023.48.10.1238)
Vol. 48, No. 10 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