TY - GEN
T1 - Online Adaptive Incremental Reinforcement Learning Flight Control for a CS-25 Class Aircraft
AU - Heyer, Stefan
AU - Kroezen, Dave
AU - van Kampen, Erik-jan
PY - 2020
Y1 - 2020
N2 - In recent years Adaptive Critic Designs (ACDs) have been applied to adaptive flight control of uncertain, nonlinear systems. However, these algorithms often rely on representative models as they require an offline training stage. Therefore, they have limited applicability to a system for which no accurate system model is available, nor readily identifiable. Inspired by recent work on Incremental Dual Heuristic Programming (IDHP), this paper derives and analyzes a Reinforcement Learning (RL) based framework for adaptive flight control of a CS-25 class fixed-wing aircraft. The proposed framework utilizes Artificial Neural Networks (ANNs) and includes an additional network structure to improve learning stability. The designed learning controller is implemented to control a high-fidelity, six-degree-of-freedom simulation of the Cessna 550 Citation II PH-LAB research aircraft. It is demonstrated that the proposed framework is able to learn a near-optimal control policy online without a priori knowledge of the system dynamics nor an offline training phase. Furthermore, it is able to generalize and operate the aircraft in not previously encountered flight regimes as well as identify and adapt to unforeseen changes to the aircraft’s dynamics.
AB - In recent years Adaptive Critic Designs (ACDs) have been applied to adaptive flight control of uncertain, nonlinear systems. However, these algorithms often rely on representative models as they require an offline training stage. Therefore, they have limited applicability to a system for which no accurate system model is available, nor readily identifiable. Inspired by recent work on Incremental Dual Heuristic Programming (IDHP), this paper derives and analyzes a Reinforcement Learning (RL) based framework for adaptive flight control of a CS-25 class fixed-wing aircraft. The proposed framework utilizes Artificial Neural Networks (ANNs) and includes an additional network structure to improve learning stability. The designed learning controller is implemented to control a high-fidelity, six-degree-of-freedom simulation of the Cessna 550 Citation II PH-LAB research aircraft. It is demonstrated that the proposed framework is able to learn a near-optimal control policy online without a priori knowledge of the system dynamics nor an offline training phase. Furthermore, it is able to generalize and operate the aircraft in not previously encountered flight regimes as well as identify and adapt to unforeseen changes to the aircraft’s dynamics.
UR - http://www.scopus.com/inward/record.url?scp=85092417785&partnerID=8YFLogxK
U2 - 10.2514/6.2020-1844
DO - 10.2514/6.2020-1844
M3 - Conference contribution
T3 - AIAA Scitech 2020 Forum
BT - AIAA Scitech 2020 Forum
PB - American Institute of Aeronautics and Astronautics Inc. (AIAA)
T2 - AIAA Scitech 2020 Forum
Y2 - 6 January 2020 through 10 January 2020
ER -