Sim-to-real transfer for fixed-wing uncrewed aerial vehicle: pitch control by high-fidelity modelling and domain randomization
Sim-to-real transfer for fixed-wing uncrewed aerial vehicle: pitch control by high-fidelity modelling and domain randomization
Deep reinforcement learning has great potential to automatically generate flight controllers for uncrewed aerial vehicles (UAVs), however these controllers often fail to perform as expected in real world environments due to differences between the simulation environment and reality. This letter experimentally investigated how this reality gap effect could be mitigated, focusing on fixed-wing UAV pitch control in wind tunnel tests. Three different training approaches were conducted: a baseline approach that used simple linear dynamics, a high-fidelity modeling approach, and a domain randomization approach. It was found that the base line controller was susceptible to the reality gap, while the other two approaches successfully transferred to real tests. To further examine the controllers' capabilities to generalize, a variety of configuration changes were experimentally implemented on the UAV, such as increased inertia, extended elevator area, and aileron offset. While the high-fidelity controller failed to cope with these changes, the controller with domain randomization maintained its performance. These results highlight the importance of selecting appropriate sim-to-real transfer approaches and how domain randomization is applicable to fixed-wing UAV control with uncertainty in real environments.
Aerial Systems: Mechanics and Control, Aerodynamics, Atmospheric modeling, Autonomous aerial vehicles, Elevators, Motion Control, Reinforcement Learning, Reinforcement learning, Shafts, Wind tunnels, reinforcement learning, Aerial systems: mechanics and control, motion control
11735-11742
Wada, Daichi
20a1527a-c198-4911-bce2-e1d8f13b2dd6
Araujo-Estrada, Sergio
87793c63-f2bd-4169-b93d-ec1525909a7a
Windsor, Shane P.
be3e4944-d2be-45a4-8100-03c6ca0ebea7
1 October 2022
Wada, Daichi
20a1527a-c198-4911-bce2-e1d8f13b2dd6
Araujo-Estrada, Sergio
87793c63-f2bd-4169-b93d-ec1525909a7a
Windsor, Shane P.
be3e4944-d2be-45a4-8100-03c6ca0ebea7
Wada, Daichi, Araujo-Estrada, Sergio and Windsor, Shane P.
(2022)
Sim-to-real transfer for fixed-wing uncrewed aerial vehicle: pitch control by high-fidelity modelling and domain randomization.
IEEE Robotics and Automation Letters, 7 (4), .
(doi:10.1109/LRA.2022.3205442).
Abstract
Deep reinforcement learning has great potential to automatically generate flight controllers for uncrewed aerial vehicles (UAVs), however these controllers often fail to perform as expected in real world environments due to differences between the simulation environment and reality. This letter experimentally investigated how this reality gap effect could be mitigated, focusing on fixed-wing UAV pitch control in wind tunnel tests. Three different training approaches were conducted: a baseline approach that used simple linear dynamics, a high-fidelity modeling approach, and a domain randomization approach. It was found that the base line controller was susceptible to the reality gap, while the other two approaches successfully transferred to real tests. To further examine the controllers' capabilities to generalize, a variety of configuration changes were experimentally implemented on the UAV, such as increased inertia, extended elevator area, and aileron offset. While the high-fidelity controller failed to cope with these changes, the controller with domain randomization maintained its performance. These results highlight the importance of selecting appropriate sim-to-real transfer approaches and how domain randomization is applicable to fixed-wing UAV control with uncertainty in real environments.
Text
Sim-to-Real_Transfer_for_Fixed-Wing_Uncrewed_Aerial_Vehicle_Pitch_Control_by_High-Fidelity_Modelling_and_Domain_Randomization
- Version of Record
More information
e-pub ahead of print date: 9 September 2022
Published date: 1 October 2022
Additional Information:
Publisher Copyright:
© 2016 IEEE.
Keywords:
Aerial Systems: Mechanics and Control, Aerodynamics, Atmospheric modeling, Autonomous aerial vehicles, Elevators, Motion Control, Reinforcement Learning, Reinforcement learning, Shafts, Wind tunnels, reinforcement learning, Aerial systems: mechanics and control, motion control
Identifiers
Local EPrints ID: 469341
URI: http://eprints.soton.ac.uk/id/eprint/469341
ISSN: 2377-3766
PURE UUID: d34c56ea-e8dc-404d-b0a8-e9a499bbdef3
Catalogue record
Date deposited: 13 Sep 2022 16:48
Last modified: 17 Mar 2024 04:12
Export record
Altmetrics
Contributors
Author:
Daichi Wada
Author:
Sergio Araujo-Estrada
Author:
Shane P. Windsor
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics