TY - GEN
T1 - Quadrotor Aerobatic Maneuver Attitude Controller based on Reinforcement Learning
AU - He, Linkun
AU - Li, Huifeng
N1 - Publisher Copyright:
© 2022 ACA.
PY - 2022
Y1 - 2022
N2 - A model-free attitude controller design framework for aerobatic maneuver of quadrotor is proposed in this paper. We utilize Proximal Policy Optimization, a reinforcement learning algorithm to train a neural network controller. The proposed controller can handle the highly coupled nonlinearity of aerobatic maneuver dynamic while requires no explicit dynamic model of the quadrotor. Compared with traditional PID controller, the proposed controller shows advantage in both rapidity and overshoot when tracking aerobatic maneuver attitude commands.
AB - A model-free attitude controller design framework for aerobatic maneuver of quadrotor is proposed in this paper. We utilize Proximal Policy Optimization, a reinforcement learning algorithm to train a neural network controller. The proposed controller can handle the highly coupled nonlinearity of aerobatic maneuver dynamic while requires no explicit dynamic model of the quadrotor. Compared with traditional PID controller, the proposed controller shows advantage in both rapidity and overshoot when tracking aerobatic maneuver attitude commands.
KW - Neural Network based control
KW - Nonlinear control
KW - Reinforcement learning
UR - https://www.scopus.com/pages/publications/85135602244
U2 - 10.23919/ASCC56756.2022.9828067
DO - 10.23919/ASCC56756.2022.9828067
M3 - 会议稿件
AN - SCOPUS:85135602244
T3 - ASCC 2022 - 2022 13th Asian Control Conference, Proceedings
SP - 2450
EP - 2453
BT - ASCC 2022 - 2022 13th Asian Control Conference, Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 13th Asian Control Conference, ASCC 2022
Y2 - 4 May 2022 through 7 May 2022
ER -