Attitude Control of a Moving Mass–Actuated UAV Based on Deep Reinforcement Learning

Qiu, Xiaoqi; Gao, Changsheng; Wang, Kefan; Jing, Wuxing

doi:10.1061/(asce)as.1943-5525.0001381

Cited by 15 publications

(3 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…According to the design model (27), the expansion state space can be expressed as . u = f u + g u u δ t ;…”

Section: Forward Velocity Controllermentioning

confidence: 99%

“…Based on this structure, they analyzed its dynamic characteristics and designed an adaptive sliding mode attitude controller incorporating the fuzzy system and RBF neural network for it. Based on deep reinforcement learning, an end-to-end attitude controller of MAUAVs was designed and the robustness of this controller was verified by random initialization and parameter perturbation during simulation [27]. However, these studies related to MAUAVs did not design detailed and complete automatic landing control strategies for the landing phase.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Auto-Landing of Moving-Mass Actuated Unmanned Aerial Vehicles Based on Linear Active Disturbance Rejection Control

Zheng,

Neusypin,

Selezneva

2023

Drones

View full text Add to dashboard Cite

Unlike the roll motion of the unmanned aerial vehicle (UAV) controlled by the ailerons, the moving-mass actuated unmanned aerial vehicle (MAUAV) uses the motion of the mass block inside the wing to generate the roll moment. The light weight and severe coupling of lateral and longitudinal motion of this type of small UAV make its landing control a challenging task. Considering the above problems, the dynamic models of MAUAV are first established. Then, forward velocity, altitude, attitude, and moving-mass position controllers are designed separately to make the MAUAV track a given path during the landing process. Linear active disturbance rejection control (LADRC) is introduced in the design process of all four controllers, compensating for unknown disturbances in the system. Simulation results show that the proposed control scheme can achieve fast and accurate tracking of forward velocity and flight trajectory commands with good robustness to model uncertainties.

show abstract

“…According to the design model (27), the expansion state space can be expressed as . u = f u + g u u δ t ;…”

Section: Forward Velocity Controllermentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Auto-Landing of Moving-Mass Actuated Unmanned Aerial Vehicles Based on Linear Active Disturbance Rejection Control

Zheng,

Neusypin,

Selezneva

2023

Drones

View full text Add to dashboard Cite

show abstract

“…It was first used in spacecraft and lighterthan-air vehicles, but its application to multi-rotor flying robots has been investigated in recent years. [1][2][3][4][5][6].…”

Section: Introductionmentioning

confidence: 99%

On the Performance of the Model-Free Adaptive Control For A Novel Moving-Mass Controlled Flying Robot

Heydari,

Darvishpoor,

Novinzadeh

et al. 2024

J Intell Robot Syst

View full text Add to dashboard Cite

In this paper, the performance of Model-Free Adaptive Control (MFAC) has been investigated on a novel and specific moving-mass controlled (MMC) flying robot system. The novel one-degree-of-freedom (1 DOF) MMC flying robot test bed presented in this paper has highly nonlinear and slow dynamics with a variable center of gravity (CoG) and moment of inertia. This makes the control of this system a challenging problem. One of the solutions to this challenge is the use of data-driven control methods, in particular, MFAC. This controller uses a data-driven model to control the system using only input and output (I/O) data. This paper compares this data-driven controller with proportional-integral-derivative (PID) control, and Linear Quadratic Regulator (LQR) as two model-free and model-based controllers which are widely used controllers in industry. The results of the comparison show that in the various scenarios applied, MFAC has a clear superiority over the PID and LQR, and its adaptive structure gives more freedom of action in the implementation of different scenarios and the presented noise. The results are obtained using the Integral Time Absolute Error (ITAE) criteria and the mean maximum error has also been compared in a Monte Carlo analysis. For a more detailed study, the amount of control energy consumption was also compared, which showed a clear superiority of the MFAC. Also, the robustness of the controller was demonstrated by introducing uncertainty in the plant parameters and by running 100 Monte Carlo simulations with random initial conditions. Finally, despite the PID controller, the MFAC followed the desired scenarios well and compared to LQR consumed less energy. The results demonstrate that the MFAC outperformed the PID and LQR controllers in the presence of random initial conditions and noise in terms of mean maximum error $$(70.4\%)$$ ( 70.4 % ) , mean ITAE $$(91\%)$$ ( 91 % ) , and energy consumption $$(46\%)$$ ( 46 % ) .

show abstract

The niching-based adaptive space reconstruction method for airfoil aerodynamic/stealth design

Zhang

Gao

Wang³

et al. 2023

Struct Multidisc Optim

View full text Add to dashboard Cite

Attitude Control of a Moving Mass–Actuated UAV Based on Deep Reinforcement Learning

Cited by 15 publications

References 36 publications

Auto-Landing of Moving-Mass Actuated Unmanned Aerial Vehicles Based on Linear Active Disturbance Rejection Control

Auto-Landing of Moving-Mass Actuated Unmanned Aerial Vehicles Based on Linear Active Disturbance Rejection Control

On the Performance of the Model-Free Adaptive Control For A Novel Moving-Mass Controlled Flying Robot

The niching-based adaptive space reconstruction method for airfoil aerodynamic/stealth design

Contact Info

Product

Resources

About