Low-level autonomous control and tracking of quadrotor using reinforcement learning

Chen Huan Pi, Kai Chun Hu, Stone Cheng*, I. Chen Wu

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

6 Scopus citations


This paper proposes a low-level quadrotor control algorithm using neural networks with model-free reinforcement learning, then explores the algorithm's capabilities on quadrotor hover and tracking tasks. We provide a new point of view by examining the well-known policy gradient algorithm from reinforcement learning, then relaxing its requirements to improve training efficiency. Without requiring expert demonstrations, the improved algorithm is then applied to train a quadrotor controller with its output directly mapped to four actuators in a simulator, which is a technique used to control any linear or nonlinear system under unknown dynamic parameters and disturbances. We show two experimental tasks both in simulation and real-world quadrotors to verify our method and demonstrate performance: 1) hovering at a fixed position, and 2) tracking along a specific trajectory. The video of our experiments can be found at https://youtu.be/oEVcdiFPnMo.

Original languageEnglish
Article number104222
JournalControl Engineering Practice
StatePublished - Feb 2020


  • Policy gradient
  • Quadrotor
  • Reinforcement learning

Fingerprint Dive into the research topics of 'Low-level autonomous control and tracking of quadrotor using reinforcement learning'. Together they form a unique fingerprint.

Cite this