Spacecraft Proximity Maneuvering and Rendezvous With Collision Avoidance Based on Reinforcement Learning

Qu, Qingyu; Liu, Kexin; Wang, Wei; Lü, Jinhu

doi:10.1109/taes.2022.3180271

Cited by 26 publications

(4 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the help of the probabilistic programming approach to conjunction assessment and the ability to obtain posterior distributions through Bayesian inference, the model can make more precise predictions and identify the crucial variables and orbital features that increase the likelihood of a collision. [17][18]. According to Broida et al, they develop an autonomous navigation system that can handle any unforeseen situations while maintaining an effective computational load [17].…”

Section: Collision Avoidancementioning

confidence: 99%

“…To be more detailed, Proximal Policy Optimization (PPO) is implemented to create a control policy and its performance is evaluated in a simulated Three-Degree-of-Freedom (3-DoF) dynamics environment. While on the other hand, Qu et al propose a deep deterministic policy gradient (DDPG) algorithm to realize the autonomous spacecraft rendezvous (ASR) [18]. Moreover, they also present a notion based on meta-learning by adjusting the control strategy so that the proposed model can adapt to other similar scenarios efficiently.…”

Section: Collision Avoidancementioning

confidence: 99%

See 1 more Smart Citation

Reframe the Field of Aerospace Engineering Via Machine Learning: Application and Comparison

2022

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

Machine learning (ML) shows its significant efficiency and excellent performance of computing while handling various complex issues in different areas since the term ‘Big Data’ emerged in the early 1990s. Big data analysis and ML that are effective at resolving various multi-objective as well as limited optimization issues that emerge in spacecraft design and manufacture, are positioned to benefit the aerospace industry. This research paper demonstrates a radical analysis of the use of ML in aerospace engineering. Spacecraft section focuses on anomaly detection, collision avoidance and attitude control. Artificial satellite part is categorized in satellite communication and default diagnosis while thermoacoustic instabilities detection and lunar landing are the main concentration on rockets. The vast application of machine learning in aerospace engineering certainly boosts the growth of the modern aerospace industry as each collected data contributes to a better trained system for attitude control, navigation and default diagnosis which significantly increase the success rate of future space exploration missions.

show abstract

Section: Collision Avoidancementioning

confidence: 99%

Section: Collision Avoidancementioning

confidence: 99%

Reframe the Field of Aerospace Engineering Via Machine Learning: Application and Comparison

2022

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

show abstract

“…Artificial potential functions have also been combined with backstepping [15] and sliding mode control [16] to achieve robust and safe proximity operations. Machine learning techniques have also been considered to facilitate ARPOD missions [17][18][19][20][21][22][23]. Yang et al [17] used model-based reinforcement learning and neural networks to address ARPOD mission requirements and computational constraints.…”

mentioning

confidence: 99%

“…Through simulations and experiments, they demonstrated the viability of such an approach for spacecraft proximity operations with obstacle avoidance. In [23], collision avoidance between a chaser and a target was also achieved by leveraging deep reinforcement learning. Many of these articles showcased successful simulated docking maneuvers with obstacles or collision avoidance.…”

mentioning

confidence: 99%

Learning Reference Governor for Constrained Spacecraft Rendezvous and Proximity Maneuvering

Ikeya

Liu

Girard

et al. 2023

Journal of Spacecraft and Rockets

View full text Add to dashboard Cite

Spacecraft automated rendezvous, proximity maneuvering, and docking (ARPOD) play significant roles in many space missions, including on-orbit servicing and active debris removal. Precise modeling and prediction of spacecraft dynamics can be challenging due to the uncertainties and perturbation forces in the spacecraft operating environment and due to the multilayered structure of its nominal control system. Despite this complication, spacecraft maneuvers need to satisfy required constraints (thrust limits, line-of-sight cone constraints, relative velocity of approach constraints, etc.) to ensure safety and achieve ARPOD objectives. This paper considers an application of a learning-based reference governor (LRG) to spacecraft ARPOD operations to enforce constraints without relying on a dynamic model of the spacecraft during the mission. Similar to the conventional reference governor (RG), the LRG is an add-on supervisor to a closed-loop control system, serving as a prefilter on the command generated by the ARPOD planner. The LRG modifies, if it becomes necessary, the reference command to a constraint-admissible value to enforce specified constraints. The LRG is distinguished, however, by the ability to rely on learning instead of an explicit model of the system; and it guarantees constraints’ satisfaction during and after the learning. In this paper, the LRG is applied to the control of combined translational and rotational motions of a chaser spacecraft, and three case studies with different sets of safety constraints and thruster assumptions are used to demonstrate the benefits of the LRG in ARPOD missions.

show abstract

SGFNeRF: Shape Guided 3D Face Generation in Neural Radiance Fields

Zhou,

Liu,

Zhang

2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Spacecraft Proximity Maneuvering and Rendezvous With Collision Avoidance Based on Reinforcement Learning

Cited by 26 publications

References 28 publications

Reframe the Field of Aerospace Engineering Via Machine Learning: Application and Comparison

Reframe the Field of Aerospace Engineering Via Machine Learning: Application and Comparison

Learning Reference Governor for Constrained Spacecraft Rendezvous and Proximity Maneuvering

SGFNeRF: Shape Guided 3D Face Generation in Neural Radiance Fields

Contact Info

Product

Resources

About