TY - GEN
T1 - Deep Reinforcement Learning Automatic Landing Control of Fixed-Wing Aircraft Using Deep Deterministic Policy Gradient
AU - Tang, Chi
AU - Lai, Ying Chih
N1 - Funding Information:
ACKNOWLEDGEMENT This research was supted bpytho Meinrstry ioScfience and Technology of Taiwan uerngrantdnumber MOST 10-8 2221-E-0-001-M76Y3 and, in part, the Ministry of Educatio, nTaiwan, HeadarqtersuofUnversiity Advancement toth Neationl Caheng Kung University (NCKU).
Publisher Copyright:
© 2020 IEEE.
Copyright:
Copyright 2020 Elsevier B.V., All rights reserved.
PY - 2020/9
Y1 - 2020/9
N2 - Landing phase remains to be one of the most crucial and difficult tasks to achieve among the flight envelope of an aircraft. The proof-of-concept controller in this research implemented the use of DDPG (Deep Deterministic Policy Gradient), a DRL (Deep Reinforcement Learning) approach in attempt to find policies of aircraft landings given designed requirements, or rewards. This research provided new methods in reward shaping, or reward engineering used during training and the investigation of the effects of hyperparameters and different network topologies of Neural Networks in training of aircraft landing control. The results of outer loop control and direct control in this research using DDPG on aircraft landing, with comparisons of numerous baseline and Neural Network approaches, proves the ability and potential of such DRL method, and is validated in numerous wind disturbance conditions, which demonstrated the robustness of DDPG agent. It is also found that besides the ability of DDPG agents to develop control policies for aircraft landings, such method provides insights of the controls and states of aircraft during landing, enabling guidelines of the flight characteristics of the aircraft in landing for pilots or design of controllers.
AB - Landing phase remains to be one of the most crucial and difficult tasks to achieve among the flight envelope of an aircraft. The proof-of-concept controller in this research implemented the use of DDPG (Deep Deterministic Policy Gradient), a DRL (Deep Reinforcement Learning) approach in attempt to find policies of aircraft landings given designed requirements, or rewards. This research provided new methods in reward shaping, or reward engineering used during training and the investigation of the effects of hyperparameters and different network topologies of Neural Networks in training of aircraft landing control. The results of outer loop control and direct control in this research using DDPG on aircraft landing, with comparisons of numerous baseline and Neural Network approaches, proves the ability and potential of such DRL method, and is validated in numerous wind disturbance conditions, which demonstrated the robustness of DDPG agent. It is also found that besides the ability of DDPG agents to develop control policies for aircraft landings, such method provides insights of the controls and states of aircraft during landing, enabling guidelines of the flight characteristics of the aircraft in landing for pilots or design of controllers.
UR - http://www.scopus.com/inward/record.url?scp=85094954542&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85094954542&partnerID=8YFLogxK
U2 - 10.1109/ICUAS48674.2020.9213987
DO - 10.1109/ICUAS48674.2020.9213987
M3 - Conference contribution
AN - SCOPUS:85094954542
T3 - 2020 International Conference on Unmanned Aircraft Systems, ICUAS 2020
SP - 1
EP - 9
BT - 2020 International Conference on Unmanned Aircraft Systems, ICUAS 2020
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2020 International Conference on Unmanned Aircraft Systems, ICUAS 2020
Y2 - 1 September 2020 through 4 September 2020
ER -