Research Trends on PID Control and Reinforcement Learning Control on Drone

Journal of Advanced Technology Research, Vol. 4, No. 1, pp. 6-13, Jun. 2019
10.11111/JATR.2019.4.1.006, Full Text:
Keywords: Unmanned Air Vehicle, Drone, Drone Swarm, PID Control, Artificial intelligence, Reinforcement Learning
Abstract

This paper presents the basic dynamics theory based on rolling, pitching and yawing of quadcopter control, and explains the latest research trends on the conventional control using quadcopter's PID control and reinforcement learning control. In particular, we describe the definition of states, actions, and rewards for reinforcement learning architecture for quadcopter control based on the work of [12]. Finally, by providing a comparative analysis of PID control and reinforcement learning control, we propose the necessity of deeper reinforcement learning control study for various intelligent control of drones in the future.


Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from September 1st, 2017)
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]
J. Kim, G. Hwang, C. An, Y. Han, "Research Trends on PID Control and Reinforcement Learning Control on Drone," Journal of Advanced Technology Research, vol. 4, no. 1, pp. 6-13, 2019. DOI: 10.11111/JATR.2019.4.1.006.

[ACM Style]
Ju-bong Kim, Gyu-Young Hwang, Chae-Hun An, and Youn-Hee Han. 2019. Research Trends on PID Control and Reinforcement Learning Control on Drone. Journal of Advanced Technology Research, 4, 1, (2019), 6-13. DOI: 10.11111/JATR.2019.4.1.006.