Neural-Based Predictive Control for Safe Autonomous Spacecraft Relative Maneuvers
Open accessThe DOI matches its Crossref record; 11 of the 11 references it cites were found in a registry or an index.
Abstract
The justification for this work and the goal of the paper is to develop an algorithm that addresses the following features: To develop a neural-based reconstruction algorithm for system dynamics identification, which allows an autonomous spacecraft to refine the on-board dynamic model as it flies, coping with unmodeled perturbations and nonlinearities. It is achieved by supervised learning of an RNN. To develop a planning algorithm that can adapt to the perturbed environments using the neural reconstructed dynamics. This prevents the failure of traditional algorithms in the presence of unmodeled terms in the dynamic model enhancing the autonomy and flexibility of the spacecraft. The task is performed using the developed MBRL method. To develop a relative trajectories prediction algorithm to ensure collision-free simultaneous reconfigurations. This is required when coordinated maneuvers are needed, where the hypothesis of the formation evolution according to natural dynamics does not hold. The neighboring trajectories are predicted by IRL and LSTM to guarantee safe reconfigurations.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The text we found for this paper looks like another document, so the self-check wasn’t run.
Citations
Cites
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
Neural Networks: A Comprehensive Foundation
Haykin, S. (1998) · Cited by 30,070
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 16
Storkey, A. (2004) · neural information processing systems · Cited by 2,085
Aerospace science and technology
Raumfahrt, D. F. F. L. U., & Raumfahr, D. G. F. L. U. (1997) · Gauthier-Villars eBooks · Cited by 1,007
Model Predictive Control of Swarms of Spacecraft Using Sequential Convex Programming
Morgan, D., Chung, S.-J., & Hadaegh, F. Y. (2014) · Journal of Guidance, Control, and Dynamics · doi:10.2514/1.g000218 · Cited by 384
D'Amico, S., & Montenbruck, O. (2006) · Journal of Guidance, Control, and Dynamics · doi:10.2514/1.15114 · Cited by 345
Learning to search: Functional gradient techniques for imitation learning
Ratliff, N. D., Silver, D., & Bagnell, J. A. (2009) · Autonomous Robots · doi:10.1007/s10514-009-9121-3 · Cited by 198
Pesce, V., Silvestrini, S., & Lavagna, M. (2020) · Aerospace Science and Technology · doi:10.1016/j.ast.2019.105527 · Cited by 95
Self-citationGaudet, B., Linares, R., & Furfaro, R. (2020) · Acta Astronautica · doi:10.1016/j.actaastro.2020.03.026 · Cited by 68
Neural-aided GNC reconfiguration algorithm for distributed space system: development and PIL test
Silvestrini, S., & Lavagna, M. (2021) · Advances in Space Research · doi:10.1016/j.asr.2020.12.014 · Cited by 25
Self-citation
Cited by
Reinforcement learning in spacecraft control applications: Advances, prospects, and challenges
Tipaldi, M., Iervolino, R., & Massenio, P. R. (2022) · Annual Reviews in Control · doi:10.1016/j.arcontrol.2022.07.004 · Cited by 141
Deep Learning and Artificial Neural Networks for Spacecraft Dynamics, Navigation and Control
Silvestrini, S., & Lavagna, M. R. (2022) · Drones · doi:10.3390/drones6100270 · Cited by 96
Self-citationOptical navigation for Lunar landing based on Convolutional Neural Network crater detector
Silvestrini, S., Piccinin, M., Zanotti, G., Brandonisio, A., Bloise, I., Feruglio, L., Lunghi, P., Lavagna, M., & Varile, M. (2022) · Aerospace Science and Technology · doi:10.1016/j.ast.2022.107503 · Cited by 65
Self-citationDistributed safe trajectory optimization for large-scale spacecraft formation reconfiguration
Chen, J., Wu, B., Sun, Z., & Wang, D. (2023) · Acta Astronautica · doi:10.1016/j.actaastro.2023.10.012 · Cited by 43
Robust spacecraft relative pose estimation via CNN-aided line segments detection in monocular images
Bechini, M., Gu, G., Lunghi, P., & Lavagna, M. R. (2023) · Acta Astronautica · doi:10.1016/j.actaastro.2023.11.049 · Cited by 46
Self-citationOptimal Multi-impulse Linear Rendezvous via Reinforcement Learning
Xu, L., Zhang, G., Qiu, S., & Cao, X. (2023) · Space Science & Technology · doi:10.34133/space.0047 · Cited by 37
Specific Tracking Control of Rotating Target Spacecraft Under Safe Motion Constraints
Lin, Z., Wu, B., & Wang, D. (2022) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2022.3214799 · Cited by 32
“A model-based reinforcement learning (RL) control algorithm is developed in [19] to overcome the incomplete description of the dynamic environment.”
Maneuvering Spacecraft Orbit Determination Using Polynomial Representation
Zhou, X., Qin, T., & Meng, L. (2022) · Aerospace · doi:10.3390/aerospace9050257 · Cited by 29
Event-Triggered Model Predictive Control of Spacecraft Formation
Sun, Z., Wu, B., Wang, D., & Chen, J. (2024) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2024.3468459 · Cited by 27
“Silvestrini and Lavagna explored safe autonomous spacecraft relative maneuvers using neural-based predictive control, requiring only minimal computation to generate reconfiguration trajectories [11].”
Capra, L., Brandonisio, A., & Lavagna, M. R. (2022) · Advances in Space Research · doi:10.1016/j.asr.2022.11.048 · Cited by 30
Self-citationBrandonisio, A., Capra, L., & Lavagna, M. R. (2023) · Advances in Space Research · doi:10.1016/j.asr.2023.07.007 · Cited by 29
Self-citationCui, B., Chen, X., Chai, R., Xia, Y., & Shin, H. (2024) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2024.3406312 · Cited by 23
“The related technique has been applied to some space missions, including on-orbit ser-vicing [26], [27], asteroid detumbling [28], and formation maintenance [29].”
MethodA Neural Network Warm-Started Indirect Trajectory Optimization Method
Shi, J., Wang, J., Su, L., Ma, Z., & Chen, H. (2022) · Aerospace · doi:10.3390/aerospace9080435 · Cited by 22
Implicit Extended Kalman Filter for Optical Terrain Relative Navigation Using Delayed Measurements
Silvestrini, S., Piccinin, M., Zanotti, G., Brandonisio, A., Lunghi, P., & Lavagna, M. R. (2022) · Aerospace · doi:10.3390/aerospace9090503 · Cited by 23
Self-citationWu, J., Wei, C., Zhang, H., Liu, Y., & Li, K. (2024) · Aerospace Science and Technology · doi:10.1016/j.ast.2024.109112 · Cited by 17
Neural Network–Assisted Initial Orbit Determination Method for Libration Point Orbits
Zhou, X., Li, X., & Zhang, Z. (2024) · Journal of Aerospace Engineering · doi:10.1061/jaeeez.aseng-5482 · Cited by 12
Small bodies non-uniform gravity field on-board learning through Hopfield Neural Networks
Pasquale, A., Silvestrini, S., Capannolo, A., Lunghi, P., & Lavagna, M. (2022) · Planetary and Space Science · doi:10.1016/j.pss.2022.105425 · Cited by 10
Self-citationRobust and efficient single-CNN-based spacecraft relative pose estimation from monocular images
Bechini, M., & Lavagna, M. R. (2025) · Acta Astronautica · doi:10.1016/j.actaastro.2025.04.016 · Cited by 13
Self-citationTahir, H., Jabbarpour, M. R., Vo, Q. B., Kowalczyk, R., Barr, J., & Bessell, T. (2025) · IEEE Access · doi:10.1109/access.2025.3639551 · Cited by 7
“Traditional fault detection, isolation, and recovery (FDIR) systems rely on hard-coded thresholds and rule-based logic [182], [183], [184] that lack the adaptability of machine learning approaches but benefit from deterministic behavior and predictable resource usage [130], [160], [161].”
Nchama, V. A. O. B., Shi, P., & Bose, L. (2025) · Advances in Space Research · doi:10.1016/j.asr.2025.09.075 · Cited by 12
Comparative Analysis of Machine Learning Regression Models for Unknown Dynamics
Ordoñez, J. C., & Ferguson, P. A. (2023) · IEEE Journal of Radio Frequency Identification · doi:10.1109/jrfid.2023.3284670 · Cited by 5
“Silvestrini and Lavagna [15] investigated using a physics informed approach for Low-Earth orbit formation flight maneouvering.”
Wang, C., Chen, D. S., & Liao, W. (2024) · Aerospace · doi:10.3390/aerospace11110894 · Cited by 4
Collision-Free Configuration Control of Spacecraft Systems Using Relative Measurements
Xia, K., Zhang, Y., Wang, W., Zou, Y., & Zuo, Z. (2024) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2024.3523277 · Cited by 4
“To ensure the safe reconfiguration, a reinforcement learning predictive control was developed [18].”
Orbit Determination of Impulsively Maneuvering Spacecraft Using Adaptive State Noise Compensation
Ren, H. L., Zhou, X., & Yang, Q. (2025) · Symmetry · doi:10.3390/sym17040540 · Cited by 3
Shao, S., Zhou, D. X., Sun, G., Ma, W., & Deng, R. (2025) · Aerospace · doi:10.3390/aerospace12030170 · Cited by 3
Markov Decision Processes for Satellite Maneuver Planning and Collision Avoidance
Kuhl, W., Wang, J., Eddy, D., & Kochenderfer, M. J. (2025) · IEEE Aerospace Conference (AERO) · doi:10.1109/aero63441.2025.11068672 · Cited by 3
“Silvestrini and Lavagna use a model-based reinforcement learning approach with inverse reinforcement learning and long short-term memory algorithms for the guidance and control of distributed formation flying missions [5].”
Silvestrini, S., Cassinis, L. P., Hinz, R., González-Arjona, D., Tipaldi, M., Visconti, P., Corradino, F., Pesce, V., & Colagrossi, A. (2023) · Elsevier eBooks · doi:10.1016/b978-0-323-90916-7.00015-9 · Cited by 5
Self-citationDeep Reinforcement Learning as Guidance for Aerospace Robotics
Hovell, K. (2022) · Carleton University's Institutional Repository (MacOdrum Library, Carleton University) · doi:10.22215/etd/2022-14922 · Cited by 3
Silvestrini, S. (2026) · Astrodynamics · doi:10.1007/s42064-025-0282-4 · Cited by 2
Self-citationQuantifying Impact of Information Sharing on Satellite Navigation
Dolan, S. I., Nayak, S. N., & Balakrishnan, H. (2025) · Journal of Guidance Control and Dynamics · doi:10.2514/1.g008921 · Cited by 2
Applicative GNC cases and examples
Silvestrini, S., Colagrossi, A., Paolini, E., Rivolta, A., Capannolo, A., Pesce, V., Bhaskaran, S., Sanfedino, F., & Alazard, D. (2023) · Elsevier eBooks · doi:10.1016/b978-0-323-90916-7.00014-7 · Cited by 1
Self-citationOn-Orbit Proximity Operations About Controlled Uncooperative Targets Using Meta-Predictor
Fu, J., Chen, L., Zhang, D., & Shao, X. (2024) · Journal of Guidance Control and Dynamics · doi:10.2514/1.g007718 · Cited by 1
Shokrolahi, P., & Ebrahimi, M. (2025) · Advances in Space Research · doi:10.1016/j.asr.2025.09.067
Yang, C., & Xia, Y. (2026) · Intelligent control and learning systems · doi:10.1007/978-981-95-9179-4_1
Obstacle avoidance maneuvering control method for service spacecraft based on superquadric surfaces
Rong, J., Yang, H., Wu, J., & Dai, H. (2026) · Aerospace Science and Technology · doi:10.1016/j.ast.2026.113445
Neural Network-based Imitation Learning for Optimal Satellite Formation Control
Dyblenko, O., Santoro, C., Blasi, L., D’Amato, E., & Notaro, I. (2026) · International Conference on Control, Decision and Information Technologies (CoDIT) · doi:10.1109/codit70676.2026.11630889
“In the context of SFC, several works have addressed the use of neural networks and machine learning [19], [20], distinguishing between offline pre-trained controllers as surro-gates of optimal or model-based policies and online/adaptive schemes that update the network in flight [21], [22].”
Metadata
- Authors
- Silvestrini, S., & Lavagna, M.
- Affiliations
- Politecnico di Milano (IT)
- Venue
- Journal of Guidance, Control, and Dynamics
- Published
- 2021-12
- Volume
- 44
- Issue
- 12
- Pages
- 2303-2310
- ISSN
- 0731-5090 (ISSN-L)
- 1533-3884
- OpenAlex
- W3200345956
- Cited by
- 35
- References
- 10
- Citations by year
- 2026: 4 · 2025: 8 · 2024: 7 · 2023: 7 · 2022: 9
- FWCI
- 2.97
- Type
- journal article
- Language
- en
- Open access
- green
- hdl.handle.net
- Licence
- other-oa
- Locations
- Journal of Guidance Control and Dynamics (publishedVersion)
- Virtual Community of Pathological Anatomy (University of Castilla La Mancha) (submittedVersion, other-oa)
- Topics
- Physical Sciences › Engineering › Aerospace Engineering › Spacecraft Dynamics and Control
- Physical Sciences › Engineering › Aerospace Engineering › Space Satellite Systems and Control
- Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
- Keywords
- autonomous spacecraft, model-based reinforcement learning, recurrent neural networks, formation reconfiguration, collision avoidance, trajectory prediction, inverse reinforcement learning, LSTM, neural predictive control
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.