Cascade Flight Control of Quadrotors Based on Deep Reinforcement Learning
- 4 August 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 7 (4) , 11134-11141
Abstract
Numerous algorithms have been proposed for quadrotor flight control. Conventional methods require massive labor of parameter adjustment. Deep reinforcement learning (DRL) methods also need enormous computation and complicated hyperparameter tuning, since most of them regard the quadrotor dynamics as a black box. To overcome the drawbacks of both conventional and learning-based methods, this letter proposes a DRL-based cascade quadrotor flight controller. Under the small-angle restriction, the quadrotor dynamics are decomposed into six subsystems, each containing only one degree of freedom (DOF) for the agent to control. Six agents are sequentially trained to fully control the corresponding DOF without any prior knowledge of quadrotor dynamic parameters. Experiments show that, with a total training time of 17 min, the proposed controller could accomplish the fixed point tracking task with an error lower than 5 mm, rise time lower than 1.5 s, and peak value lower than 1%. The controller could also track time-variant trajectories.Keywords
Funding Information
- National Natural Science Foundation of China (62071104)
- NNSFC&CAAC (U2133211)
This publication has 22 references indexed in Scilit:
- Nonlinear PID controller design for a 6-DOF UAV quadrotor systemEngineering Science and Technology, an International Journal, 2019
- Reinforcement Learning for UAV Attitude ControlACM Transactions on Cyber-Physical Systems, 2019
- Onboard State Dependent LQR for Agile Quadrotors2018
- Centralized predictive ceiling interaction control of quadrotor VTOL UAVAerospace Science and Technology, 2018
- Control of a Quadrotor With Reinforcement LearningIEEE Robotics and Automation Letters, 2017
- Adaptive RBFNNs/integral sliding mode control for a quadrotor aircraftNeurocomputing, 2016
- Sliding mode control for a quadrotor UAV with parameter uncertainties2016
- Self-tuning PID control design for quadrotor UAV based on adaptive pole placement control2013
- Geometric tracking control of a quadrotor UAV on SE(3)2010
- Design and control of an indoor micro quadrotor2004