Imitation Learning for Satellite Attitude Control under Unknown Perturbations
Mechanical and Aerospace Engineering Department, Rutgers, the State University of New Jersey（机械与航空航天工程系，新泽西州立大学拉特格斯分校）；Aerospace Engineering Department, Embry-Riddle Aeronautical University（航空航天工程系，埃姆布里-瑞德航空大学）
This paper presents a novel satellite attitude control framework that integrates Soft Actor-Critic (SAC) reinforcement learning with Generative Adversarial Imitation Learning (GAIL) to achieve robust performance under various unknown perturbations. Traditional control techniques often rely on precise system models and are sensitive to parameter uncertainties and external perturbations. To overcome these limitations, we first develop a SAC-based expert controller that demonstrates improved resilience against actuator failures, sensor noise, and attitude misalignments, outperforming our previous results in several challenging scenarios. We then use GAIL to train a learner policy that imitates the expert's trajectories, thereby reducing training costs and improving generalization through expert demonstrations. Preliminary experiments under single and combined perturbations show that the SAC expert can rotate the antenna to a specified direction and keep the antenna orientation reliably stable in most of the listed perturbations. Additionally, the GAIL learner can imitate most of the features from the trajectories generated by the SAC expert. Comparative evaluations and ablation studies confirm the effectiveness of the SAC algorithm and reward shaping. The integration of GAIL further reduces sample complexity and demonstrates promising imitation capabilities, paving the way for more intelligent and autonomous spacecraft control systems.
University of Surrey（萨里大学）；Karlshule Institute of Technology（卡尔斯鲁厄理工学院）
This work adds on to the on-going efforts to provide more autonomy to space robots. Here the concept of programming by demonstration or imitation learning is used for trajectory planning of manipulators mounted on small spacecraft. For greater autonomy in future space missions and minimal human intervention through ground control, a robot arm having 7-Degrees of Freedom (DoF) is envisaged for carrying out multiple tasks like debris removal, on-orbit servicing and assembly. Since actual hardware implementation of microgravity environment is extremely expensive, the demonstration data for trajec…
Attitude estimation or determination is a fundamental task for satellites to remain effectively operational. This task is furthermore complicated on small satellites by the limited space and computational power available on-board. This, coupled with a usually low budget, restricts small satellites from using high precision sensors for its especially important task of attitude estimation. On top of this, small satellites, on account of their size and weight, are comparatively more sensitive to environmental or orbital disturbances as compared to their larger counterparts. Magnetic disturbance f…
This paper studies the attitude control of a satellite in three-axis by thrusters. The mathematical model of attitude dynamics and kinematics of the satellite is represented as a switched system with sub-systems. Each sub-system is defined according to on/off thrusters state. A training method based on dynamic programming is utilized which can find the appropriate switching between sub-systems such that a cost function is optimized. Furthermore to extend the solution for a specific domain of interest neural network is used for approximating the cost function with basis functions. The training …
Agile attitude maneuvering maximizes the utility of remote sensing satellite constellations. By taking into account a satellite's physical properties and its actuator specifications, we may leverage the full performance potential of the attitude control system to conduct agile remote sensing beyond conventional slew-and-stabilize maneuvers. Employing a constellation of agile satellites, coordinated by an autonomous and responsive scheduler, can significantly increase overall response rate, revisit time and global coverage for the mission. In this paper, we use recent advances in sequential con…
Recent successes in the deployment of sails in space have reduced the risk associated with solar sailing missions. The attitude control requirements for a solar sailing mission is low with only slow attitude maneuvers needed to maintain a stable attitude and produce a required solar thrust. Future science missions will require large attitude maneuvers with a fully deployed sail. This article investigates the current options for attitude control on solar sails and proposes a gyro-controlled solar sailing. This concept uses a spinning solar sail to construct a control moment gyroscope capable to…
Hong Kong University（香港大学）；Hong Kong University of Science and Technology（香港科技大学）
In this paper, we investigate the problem of enabling a drone to fly through a tilted narrow gap, without a traditional planning and control pipeline. To this end, we propose an end-to-end policy network, which imitates from the traditional pipeline and is fine-tuned using reinforcement learning. Unlike previous works which plan dynamical feasible trajectories using motion primitives and track the generated trajectory by a geometric controller, our proposed method is an end-to-end approach which takes the flight scenario as input and directly outputs thrust-attitude control commands for the qu…
We propose a tracking control law for the fully actuated rigid body system in the presence of any unknown constant disturbance by employing quaternions with the stable embedding technique and Lyapunov stability theory. The stable embedding technique extends the attitude dynamics from the set of unit quaternions to the set of quaternions, which is a Euclidean space, such that the set of unit quaternions is an invariant set of the extended dynamics. Such a stable extension of the system dynamics to a Euclidean space allows us to employ well studied Lyapunov techniques in Euclidean spaces such as…
Shenyang Sport University（沈阳体育学院）；University of Illinois at Chicago（伊利诺伊大学芝加哥分校）；State University of New York at Binghamton（纽约州立大学宾汉姆顿分校）；Northeastern University（东北大学）
In recent decades, one of the scientists' main concerns has been to improve the accuracy of satellite attitude, regardless of the expense. The obvious result is that a large number of control strategies have been used to address this problem. In this study, an adaptive neuro-fuzzy integrated (ANFIS) satellite attitude estimation and control system was developed. The controller is trained with the data provided by an optimal controller. A pulse modulator is used to generate the right ON/OFF commands of the thruster actuator. To evaluate the performance of the AN-FIS controller in closed-loop si…
Over the past few decades, continuous quaternion-based attitude control has been proven highly effective for driving rotational systems that can be modeled as rigid bodies, such as satellites and drones. However, methods rooted in this approach do not enforce the existence of a unique closed-loop (CL) equilibrium attitude-error quaternion (AEQ); and, for rotational errors about the attitude-error Euler axis larger than πrad, their proportional-control effect diminishes as the system state moves away from the stable equilibrium of the CL rotational dynamics. In this paper, we introduce a new ty…
The attitude stabilization of a micro-satellite employing a variable-amplitude cold gas thruster which reflects as a time varying gain on the control input is considered. Existing literature uses a persistence filter based approach that typically leads to large control gains and torque inputs during specific time intervals corresponding to the 'on' phase of the external actuation. This work aims at reducing the transient spikes placed upon the torque commands by the judicious introduction of an additional time varying scaling signal as part of the control law. The time update mechanism for the…
The Attitude Determination and Control System is one of the critical boards of any satellite, specially the micro-satellites. The ADCS is the bridge linking sensors data to actuators by several computationally complex algorithms such as Extended Kalman Filter, Detumbling and Tumbling controller and so on. In this thesis, I will focus on the implementation of each of the required algorithms and then make a whole integrated package. This thesis focuses on developing the first version of the on-board computer software for ADCS of SSS-1P and required preliminary tests to assure the minimum perform…
This work deals with an ADCS model for a satellite orbiting around Earth. The object is to achieve a preliminary design and perform some analysis on it. To do so, a GNB was selected and main properties are exploited. Previous works of [9], [13], [14], [15] and [17] were analyzed and a synthesis was obtained; then a suitable control system was designed to satisfy technical requirements. Coding was performed using Matlab and Simulink. Keywords: Attitude Determination, Attitude Control, Nanosatellite, Orbital Perturbations, Quaternion, Two Body Problem, Euler's Equations, Lyapunov Function.
Closed-loop attitude steering can be used to implement a non-standard attitude maneuver by using a conventional attitude control system to track a non-standard attitude profile. The idea has been employed to perform zero-propellant maneuvers on the International Space Station and minimum time maneuvers on NASA's TRACE space telescope. A challenge for operational implementation of the idea is the finite capacity of a space vehicle's command storage buffer. One approach to mitigate the problem is to downsample-and-hold the attitude commands as a set of waypoints for the attitude control system t…
In this paper, a dynamic-programming approach to the coupled translational and rotational control of thruster-driven spacecraft is studied. To reduce the complexity of the problem, dynamic-programming-based optimal policies are calculated using decoupled position and attitude dynamics with generalized forces and torques as controls. A quadratic-programming-based control allocation is then used to map the controls to actuator commands. To control the spacecraft in the event of thruster failure, both the dynamic programming policies and control allocation are reconfigured to cope with the losses…
