2020
DOI: 10.1155/2020/8874619
|View full text |Cite
|
Sign up to set email alerts
|

Model-Free Attitude Control of Spacecraft Based on PID-Guide TD3 Algorithm

Abstract: This paper is devoted to model-free attitude control of rigid spacecraft in the presence of control torque saturation and external disturbances. Specifically, a model-free deep reinforcement learning (DRL) controller is proposed, which can learn continuously according to the feedback of the environment and realize the high-precision attitude control of spacecraft without repeatedly adjusting the controller parameters. Considering the continuity of state space and action space, the Twin Delayed Deep Determinist… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
4
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
6
2
1

Relationship

0
9

Authors

Journals

citations
Cited by 23 publications
(4 citation statements)
references
References 23 publications
0
4
0
Order By: Relevance
“…In [ 33 ], an end-to-end automatic lane changing method was proposed for autonomous vehicles using the DDPG algorithm. In [ 34 ], a Proportional–Integral–Derivative (PID)-Guide controller was designed to continuously learn through RL according to the feedback of environment to achieve high-precision attitude control of spacecraft. In [ 35 ], a controller based on the Robust-DDPG algorithm was developed for UAVs to fly stably in uncertain environments; the controller can continuously control two desired variables (roll and speed) of the UAV.…”
Section: Related Workmentioning
confidence: 99%
“…In [ 33 ], an end-to-end automatic lane changing method was proposed for autonomous vehicles using the DDPG algorithm. In [ 34 ], a Proportional–Integral–Derivative (PID)-Guide controller was designed to continuously learn through RL according to the feedback of environment to achieve high-precision attitude control of spacecraft. In [ 35 ], a controller based on the Robust-DDPG algorithm was developed for UAVs to fly stably in uncertain environments; the controller can continuously control two desired variables (roll and speed) of the UAV.…”
Section: Related Workmentioning
confidence: 99%
“…PIDnn Controller Design. PIDnn is a kind of PID-type controller that relies on the self-adaptation and learning ability of the neural network algorithm [25]. There are various neural network structures that can be designed.…”
Section: System Dynamics Modelmentioning
confidence: 99%
“…The deep learning nature of DDPG may allow autonomous operations, if the network configuration, its hyperparameters, and the reward function are carefully designed. There are many studies focused on implementing DDPG in different environments and/or improving its performance by modifying the algorithm [15][16][17][18][19]. Specifically, DDPG is deployed in the trajectory planning of a dual-arm robot that provides on-orbit services [15].…”
Section: Introductionmentioning
confidence: 99%