Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Leveraging Gated Recurrent Units for Iterative Online Precise Attitude Control for Geodetic Missions

Vrushabh Zinage, Shrenik Zinage, Srinivas Bettadpur, Efstathios Bakolas

TL;DR

The paper tackles the challenge of achieving high-precision attitude control for geodetic missions like GRACE-FO in the presence of time-varying external disturbances. It proposes a minimally invasive approach that augments a traditional PID controller with a GRU-based disturbance predictor, using GRACE-FO attitude data to learn disturbance trends and generate additive corrections. The method is validated via simulations showing reduced attitude and angular-rate errors with iterative refinements, and the results indicate convergence of error metrics across iterations. This work offers a data-driven framework for online disturbance compensation in spacecraft control with potential to enhance gravity-field mission accuracy.

Abstract

In this paper, we consider the problem of precise attitude control for geodetic missions, such as the GRACE Follow-on (GRACE-FO) mission. Traditional and well-established control methods, such as Proportional-Integral-Derivative (PID) controllers, have been the standard in attitude control for most space missions, including the GRACE-FO mission. Instead of significantly modifying (or replacing) the original PID controllers that are being used for these missions, we introduce an iterative modification to the PID controller that ensures improved attitude control precision (i.e., reduction in attitude error). The proposed modification leverages Gated Recurrent Units (GRU) to learn and predict external disturbance trends derived from incoming attitude measurements from the GRACE satellites. Our analysis has revealed a distinct trend in the external disturbance time-series data, suggesting the potential utility of GRU's to predict future disturbances acting on the system. The learned GRU model compensates for these disturbances within the standard PID control loop in real time via an additive correction term which is updated at regular time intervals. The simulation results verify the significant reduction in attitude error, verifying the efficacy of our proposed approach.

Leveraging Gated Recurrent Units for Iterative Online Precise Attitude Control for Geodetic Missions

TL;DR

The paper tackles the challenge of achieving high-precision attitude control for geodetic missions like GRACE-FO in the presence of time-varying external disturbances. It proposes a minimally invasive approach that augments a traditional PID controller with a GRU-based disturbance predictor, using GRACE-FO attitude data to learn disturbance trends and generate additive corrections. The method is validated via simulations showing reduced attitude and angular-rate errors with iterative refinements, and the results indicate convergence of error metrics across iterations. This work offers a data-driven framework for online disturbance compensation in spacecraft control with potential to enhance gravity-field mission accuracy.

Abstract

In this paper, we consider the problem of precise attitude control for geodetic missions, such as the GRACE Follow-on (GRACE-FO) mission. Traditional and well-established control methods, such as Proportional-Integral-Derivative (PID) controllers, have been the standard in attitude control for most space missions, including the GRACE-FO mission. Instead of significantly modifying (or replacing) the original PID controllers that are being used for these missions, we introduce an iterative modification to the PID controller that ensures improved attitude control precision (i.e., reduction in attitude error). The proposed modification leverages Gated Recurrent Units (GRU) to learn and predict external disturbance trends derived from incoming attitude measurements from the GRACE satellites. Our analysis has revealed a distinct trend in the external disturbance time-series data, suggesting the potential utility of GRU's to predict future disturbances acting on the system. The learned GRU model compensates for these disturbances within the standard PID control loop in real time via an additive correction term which is updated at regular time intervals. The simulation results verify the significant reduction in attitude error, verifying the efficacy of our proposed approach.
Paper Structure (13 sections, 20 equations, 8 figures, 2 tables, 2 algorithms)

This paper contains 13 sections, 20 equations, 8 figures, 2 tables, 2 algorithms.

Table of Contents

  1. Introduction
  2. Preliminaries and Proposed Approach
  3. Coordinate system
  4. Nonlinear attitude dynamics
  5. Feedforward neural network (FNN)
  6. Recurrent neural network (RNN)
  7. Long short term memory (LSTM)
  8. Gated recurrent unit (GRU)
  9. Attitude and orbit control system
  10. Proposed iterative approach
  11. Results
  12. Conclusion
  13. Acknowledgments

Figures (8)

  • Figure 1: (a) The coordinate system. Figs. (b) and (c) represent the actual attitude PID control block in GRACE-FO satellites kornfeld2019grace_grace_2 and the proposed minimally modified PID controller, respectively, with GRU based time varying disturbance compensator $\Delta(t)$.
  • Figure 2: Feedforward neural network (FNN)
  • Figure 3: Schematic of RNN (many to one) with $K$ layers
  • Figure 4: Popular variants of RNN cell
  • Figure 6: Evolution of angular rates and relative attitude with time across different iterations using the modified PID controller ${\boldsymbol{u}}^i_{\text{PID}}$ ($i\in\{1,\dots,4\}$)
  • ...and 3 more figures