The DOI matches its Crossref record; 53 of the 53 references it cites were found in a registry or an index.
Adaptive Neural-Network-Based Unscented Kalman Filter for Robust Pose Tracking of Noncooperative Spacecraft
Open accessAbstract
This paper presents a neural-network-based unscented Kalman filter (UKF) to estimate and track the pose (i.e., position and orientation) of a known, noncooperative, tumbling target spacecraft in a close-proximity rendezvous scenario. The UKF estimates the target’s orbit and attitude relative to the servicer based on the pose information provided by a multitask convolutional neural network (CNN) from incoming monocular images of the target. To enable reliable tracking, the process noise covariance matrix of the UKF is tuned online using adaptive state noise compensation, which leverages a newly developed closed-form process noise model for relative attitude dynamics. This paper also introduces the Satellite Hardware-In-the-loop Rendezvous Trajectories (SHIRT) dataset to enable comprehensive analyses of the performance and robustness of the proposed pipeline. SHIRT comprises the labeled images of two representative rendezvous trajectories in a low Earth orbit created using both a graphics renderer and a robotic testbed. Specifically, the CNN is solely trained on synthetic data, whereas functionality and performance of the complete navigation pipeline are evaluated on real images from the robotic testbed. The proposed UKF is evaluated on SHIRT and is shown to have subdecimeter-level position and degree-level orientation errors at steady state.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The TANGO satellite [145] model used in the multiple datasets [19,20,51,51,85,132] has a coarse dimension of 80 × 75 × 32 cm will lead to the operation range of ∼10 m.”
From A survey on deep learning-based monocular spacecraft pose estimation: Current state, limitations and prospects (2023) · cites this paper as [132]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The SHIRT dataset provides two representative in-orbit rendezvous docking scenarios, each containing sequences of images from both the synthetic and lightbox domains under the same pose labels.”
From Pose Estimation for Cross-Domain Non-Cooperative Spacecraft Based on Spatial-Aware Keypoints Regression (2024) · cites this paper as [27]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
EfficientDet: Scalable and Efficient Object Detection
Tan, M., Pang, R., & Le, Q. V. (2019) · arXiv · Cited by 9,841 · cited 1×
“1, SPNv2 [17] is a multi-scale, multi-task learning CNN with a shared feature encoder based on the EfficientNet [29] backbone and BiFPN layers [30] which fuse features at different scales.”
BackgroundUnscented Filtering and Nonlinear Estimation
Julier, S. J., & Uhlmann, J. K. (2004) · Proceedings of the IEEE · doi:10.1109/jproc.2003.823141 · Cited by 6,588 · cited 1×
“The primary contribution of this paper is the integration of SPNv2 into an Unscented Kalman Filter (UFK) [20] to enable continuous, stable pose tracking of a noncooperative spacecraft from a sequence of images during a rendezvous phase.”
MethodNRLMSISE‐00 empirical model of the atmosphere: Statistical comparisons and scientific issues
Picone, J. M., Hedin, A. E., Drob, D. P., & Aikin, A. C. (2002) · Journal of Geophysical Research: Space Physics · doi:10.1029/2002ja009430 · Cited by 3,749 · cited 1×
“3 hrs) Force Models Geopotential field (degree × order) GGM05S (120 × 120) [42] Atmospheric density NRLMSISE-00 [43] Solar radiation pressure Cannon-ball, conical Earth shadow Third-body gravity Analytical Sun & Moon [44] Relativistic effect 1st order [44] Torque Models Gravity gradient Analytical [45] Atmospheric den…”
A family of embedded Runge-Kutta formulae
Dormand, J. R., & Prince, P. J. (1980) · Journal of Computational and Applied Mathematics · doi:10.1016/0771-050x(80)90013-3 · Cited by 3,634 · cited 1×
“Table 2 SHIRT simulation parameters Simulation Parameters Initial epoch 2011/07/18 01:00:00 UTC Integrator Runge-Kutta (Dormand-Prince) [41] Step size 1 s Simulation time 2 orbits (3.”
BackgroundWu, Y., & He, K. (2020) · International Journal of Computer Vision · doi:10.1007/s11263-019-01198-w · Cited by 3,601 · cited 1×
“5M learnable parameters in the feature encoder and is built with Group Normalization (GN) layers [34] throughout the network.”
MethodA theory of learning from different domains
Ben-David, S., Blitzer, J., Crammer, K., Kulesza, A., Pereira, F., & Vaughan, J. W. (2010) · Machine Learning · doi:10.1007/s10994-009-5152-4 · Cited by 3,515 · cited 1×
“However, as evidenced by the result of the first Satellite Pose Estimation Competition (SPEC2019) [10] organized by the authors, the models trained exclusively on synthetic images suffer from the domain gap problem [14, 15] as neural networks may overfit features which are specific to the synthetic imagery used for tr…”
BackgroundEPnP: An Accurate O(n) Solution to the PnP Problem
Lepetit, V., Moreno-Noguer, F., & Fua, P. (2009) · International Journal of Computer Vision · doi:10.1007/s11263-008-0152-6 · Cited by 3,298
The Journal of the Astronautical Sciences
(2013) · The Journal of the Astronautical Sciences · doi:10.1007/40295.2195-0571 · Cited by 2,775
Spacecraft Attitude Determination and Control
(1978) · Astrophysics and Space Science Library · doi:10.1007/978-94-009-9907-7 · Cited by 1,892
Fundamentals of Spacecraft Attitude Determination and Control
Markley, F. L., & Crassidis, J. L. (2014) · doi:10.1007/978-1-4939-0802-8 · Cited by 1,035 · cited 1×
“4 due to the bijective nature of mapping from quaternions to MRP, but it has a singularity at 0◦ instead [38].”
Background
Research works printed but not linked: 1
- D’AmicoS. “Autonomous Formation Flying in Low Earth Orbit,” Ph.D. Thesis, Technical Univ. of Delft, Delft, The Netherlands, 2010.
Cited by
Pauly, L., Rharbaoui, W., Shneider, C., Rathinam, A., Gaudillière, V., & Aouada, D. (2023) · Acta Astronautica · doi:10.1016/j.actaastro.2023.08.001 · Cited by 121
PVSPE: A pyramid vision multitask transformer network for spacecraft pose estimation
Yang, H., Xiao, X., Yao, M., Xiong, Y., Cui, H., & Fu, Y. (2024) · Advances in Space Research · doi:10.1016/j.asr.2024.05.011 · Cited by 41
Golroudbari, A. A., & Sabour, M. H. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2302.11089 · Cited by 34
SPTN: Transformer-based spacecraft pose estimation network for space objects tracking
Gui, Y., Qi, Y., Xiao, X., Lin, B., Cui, H., & Huang, X. (2025) · Astrodynamics · doi:10.1007/s42064-024-0260-2 · Cited by 24
“In our experiment, we used the SPEED+ dataset [43] to evaluate the attitude estimation performance of SPTN and the SHIRT dataset [44] to validate its efficiency for translation estimation.”
Rapid Abstraction of Spacecraft 3D Structure from Single 2D Image
Park, T. H., & D’Amico, S. (2024) · AIAA SciTech Forum · doi:10.2514/6.2024-2768 · Cited by 27
“For example, the SPEED [3], SPEED+ [4] and SHIRT [5] datasets consist of synthetic images of the Tango spacecraft from the PRISMA mission [17] rendered with OpenGL and Hardware-in-the-loop (HIL) images of a mockup Tango model captured with the Testbed for Rendezvous and Optical Navigation (TRON)…”
MethodSelf-citation
Metadata
- Authors
- Park, T. H., & D’Amico, S.
- Affiliations
- Stanford University (US)
- Venue
- Journal of Guidance, Control, and Dynamics
- Published
- 2023-09
- Volume
- 46
- Issue
- 9
- Pages
- 1671-1688
- ISSN
- 0731-5090 (ISSN-L)
- 1533-3884
- OpenAlex
- W4383909160
- Cited by
- 63
- References
- 35
- Citations by year
- 2026: 18 · 2025: 24 · 2024: 21
- FWCI
- 7.68
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- Journal of Guidance Control and Dynamics (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Taqnia International (1232617-1-GWNDV)
- Topics
- Physical Sciences › Engineering › Aerospace Engineering › Space Satellite Systems and Control
- Physical Sciences › Engineering › Aerospace Engineering › Spacecraft Dynamics and Control
- Physical Sciences › Computer Science › Artificial Intelligence › Target Tracking and Data Fusion in Sensor Networks
- Keywords
- pose tracking, unscented Kalman filter, convolutional neural networks, relative attitude estimation, low Earth orbit, robotic testbed
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Adaptive Neural-Network-Based Unscented Kalman Filter for Robust Pose Tracking of Noncooperative Spacecraft. https://app.cochat.ai/papers/10.2514/1.g007387
- The paper
- Park, T. H., & D’Amico, S. (2023). Adaptive Neural-Network-Based Unscented Kalman Filter for Robust Pose Tracking of Noncooperative Spacecraft. Journal of Guidance, Control, and Dynamics. https://doi.org/10.2514/1.g007387
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.