Adaptive Neural-Network-Based Unscented Kalman Filter for Robust Pose Tracking of Noncooperative Spacecraft
Open accessThe DOI matches its Crossref record; 53 of the 53 references it cites were found in a registry or an index.
Abstract
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 27
“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-citationObject-centric Reconstruction and Tracking of Dynamic Unknown Objects Using 3D Gaussian Splatting
Barad, K. R., Richard, A., Dentler, J., Olivares-Méndez, M. A., & Martínez, C. (2024) · International Conference on Space Robotics (iSpaRo) · doi:10.1109/isparo60631.2024.10688304 · Cited by 15
“Simulta-neously, these learned models for pose estimation were extended to state tracking assuming natural motion [4], [19].”
BackgroundPark, T. H., & D’Amico, S. (2024) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57147.2024.10610138 · Cited by 19
“The offline robust training and OST are performed with the SPEED+ [10] and SHIRT [64] datasets.”
MethodInfluentialSelf-citationChen, Z., Gui, H., & Zhong, R. (2024) · Advances in Space Research · doi:10.1016/j.asr.2024.11.006 · Cited by 14
Review and Prospect of On-Orbit Servicing Technologies
Xiao, Y., Yong-qiang, J., Yan, H., Dou, Y., Cui, G., Li, F., & Meng, T. (2025) · Advances in Astronautics · doi:10.1007/s42423-025-00182-6 · Cited by 14
“[ 42] gave the research of applying the method to realize the closed loop approximation by using the corresponding information in the laboratory.”
Bridging the Domain Gap for Flight-Ready Spaceborne Vision
Park, T. H., & D’Amico, S. (2025) · Journal of Spacecraft and Rockets · doi:10.2514/1.a36130 · Cited by 18
“One such example is the Testbed for Rendezvous and Optical Navigation (TRON) facility at Stanford’s Space Rendezvous Laboratory (SLAB) ∗ [18], which was used to create the so-called Hardware-In-the-Loop (HIL) images that constitute datasets such as SPEED+ [19] and SHIRT [20].”
InfluentialSelf-citationObservability-Based Space Noncooperative Target Motion Estimation
Zhang, Y., Wang, J., Sun, B., Hou, B., Wang, D., & Zhou, X. (2024) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2024.3460756 · Cited by 13
“D’Amico [14] proposed an unscented Kalman filter based on neural networks, and integrated spacecraft pose network v2 into the unscented Kalman filter to track the orbital state, direction, and angular velocity of targets in close-range scenes.”
High-accuracy real-time satellite pose estimation for in-orbit applications
Wang, Z., Jinghao, W. A. N. G., Yu, J., Li, Z., & Yu, Q. (2025) · Chinese Journal of Aeronautics · doi:10.1016/j.cja.2025.103458 · Cited by 16
EvSat3D: Satellite Pose Estimation and 3D Reconstruction With Event Camera
Malik, S. S., Moshrefizadeh, M., Tahri, O., Bai, X., Blasch, E., Sagan, V., & Aliakbarpour, H. (2025) · IEEE Access · doi:10.1109/access.2025.3589506 · Cited by 13
“Each of these methods is designed to address the distinct challenges of the space environment [13], [14], [15], [16], [17], [18].”
Reconstructing Satellites in 3D From Amateur Telescope Images
Chang, Z., Liu, B., Xia, Y., Guo, Y., Shi, B., & Sun, H. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3599949 · Cited by 14
“Recent advancements have leveraged deep learning to improve spaceborne monocular pose estimation, supported by synthetic datasets like SPEED[41], SPEED+[34], and SHIRT[32].”
Novel learning for control of nonlinear spacecraft dynamics
Huang, B.-R., & Sands, T. A. (2023) · Journal of AppliedMath · doi:10.59400/jam.v1i1.42 · Cited by 13
“proposed an adaptive control strategy based on the full, nonlinear equations accounting for modeling uncertainties using an adaptive neural network amidst external disturbances([22]), where the Cornell approach stems from naval approaches proposed in 2020, called deterministic artificial intelligence([23]), which stat…”
MethodKruger, J. J., Guffanti, T., Park, T. H., Murray-Cooper, M., Low, S. Y. W., Bell, T., D’Amico, S., Roscoe, C. W. T., & Westphal, J. J. (2024) · AIAA SciTech Forum · doi:10.2514/6.2024-0430 · Cited by 10
“Station-keeping commences after the waypoint is reached.”
Self-citationOnline Test-Time Adaptation for On-Orbit Noncooperative Spacecraft Pose Estimation
Feng, S., Wang, T., Guo, Y., & Qiu, J. (2025) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2025.3623610 · Cited by 13
“Notably, the Testbed for Rendezvous and Optical Navigation (TRON) facility at Stanford University has produced datasets, such as SPEED+ [3] and SHIRT [4], by integrating robotic simulations with controlled orbit illumination.”
Event-RGB fusion for spacecraft pose estimation under harsh lighting
Jawaid, M., Märtens, M., & Chin, T.-J. (2025) · Aerospace Science and Technology · doi:10.1016/j.ast.2025.111039 · Cited by 18
“The SHIRT [16] dataset aimed to address this limitation by introducing sequences of images but does not contain any sequences with the harsh lighting conditions of the sunlamp dataset of SPEED + and similarly, only contains RGB data of a single satellite of object of a relatively simplistic…”
Golroudbari, A. A., & Sabour, M. H. (2023) · doi:10.22541/au.168664884.43899660/v2 · Cited by 8
Adaptive trajectory tracking control of robotic manipulators based on integral sliding mode
Qi, M., Han, S., Guo, G., Liu, P., Zhi, Y., & Zhao, Z. (2024) · Asian Journal of Control · doi:10.1002/asjc.3507 · Cited by 8
Ai, H., Zheng, Y., Xu, Z., Jiang, L., Zhu, A., & Fu, X. (2026) · ISA Transactions · doi:10.1016/j.isatra.2026.04.012 · Cited by 7
Monocular SLAM with Point and Line Features Applied to Spacecraft Relative Navigation
Pan, R., Wang, C., Zhai, Z., Liu, J., Pan, T., & Chen, X. (2024) · International Journal of Aeronautical and Space Sciences · doi:10.1007/s42405-024-00817-2 · Cited by 6
Test-Time Adaptation for Keypoint-Based Spacecraft Pose Estimation Based on Predicted-View Synthesis
Pérez-Villar, J. I. B., García‐Martín, Á., Bescós, J., & SanMiguel, J. C. (2024) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2024.3410956 · Cited by 7
Wang, Z., Liu, Y., & Zhang, E. (2024) · Aerospace · doi:10.3390/aerospace11110948 · Cited by 5
Jiang, Y., Ren, X., Yin, H., Jiang, L., Wang, C., & Wang, Z. (2025) · Remote Sensing · doi:10.3390/rs17122020 · Cited by 5
Park, T. H., & D’Amico, S. (2025) · International Conference on Space Robotics (iSpaRo) · doi:10.1109/isparo66239.2025.11437016 · Cited by 7
“In this setting, many works adopted Machine Learning (ML) and Neural Networks (NN) to perform pose estimation from a single image [9]–[20] or continuous tracking with a navigation filter in the loop given a sequence of images during RPO [21]– [24].”
Self-citationImage moment-based visual positioning and robust tracking control of ultra-redundant manipulator
Li, Z., Zhou, Y., Zhu, M., Chu, Y., & Wu, Q. (2024) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-024-02103-5 · Cited by 5
A Gaussian approximation filter for nonlinear systems with compound noises
Yin, S. Y., Zhang, J., Yu, L. J., & Yang, X. (2024) · Signal Processing · doi:10.1016/j.sigpro.2024.109578 · Cited by 5
Globally Convergent Near-Optimal Pose and Inertia Estimation of On-Orbit Uncooperative Targets
Parreira, J. L., Lourenço, P., & Batista, P. (2024) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2024.3381925 · Cited by 4
“The current state-of-the-art of image processing employs convolutional neural networks [4], which were successfully applied in the past, for example, in [5], [6], [7], and [8].”
MethodMeng, C., Yang, H., Jiang, C., Hu, Q., & Li, D. (2025) · Remote Sensing · doi:10.3390/rs17132176 · Cited by 4
Li, J., Wu, Z., Lu, W., He, H. S., & He, Y. (2024) · Stochastic Environmental Research and Risk Assessment · doi:10.1007/s00477-024-02761-9 · Cited by 4
Hu, Q., Wu, S., Meng, F., & Wu, Z. (2024) · Sensors · doi:10.3390/s24061811 · Cited by 3
“In [13], a convolutional neural network (CNN) was applied to monocular images for pose determination.”
MethodThree-stage training for cross-domain pose estimation of non-cooperative spacecraft
Wang, G., Zhao, H., & Li, S. (2025) · Aerospace Science and Technology · doi:10.1016/j.ast.2025.111131 · Cited by 3
Yu, Y., Li, Z., & Yu, Q. (2025) · Drones · doi:10.3390/drones9110774 · Cited by 4
Deep recurrent neural network-based satellite indirect pose tracking with adaptive Huber loss
Chen, Z., Li, Q., Zhong, R., & Gui, H. (2025) · Advances in Space Research · doi:10.1016/j.asr.2025.11.021 · Cited by 4
Song, Z., Zhang, Z., Zhang, F., & Bao, W. (2026) · Aerospace Science and Technology · doi:10.1016/j.ast.2026.112090 · Cited by 3
Chen, J., He, Z., Wu, F., Zhao, Z., & Chen, X. (2026) · Aerospace Science and Technology · doi:10.1016/j.ast.2026.112310 · Cited by 4
Swarm intention identification via dynamic distribution probability image
Wang, Y., Wang, J., He, S., Wang, F., & Wang, Y. (2024) · Chinese Journal of Aeronautics · doi:10.1016/j.cja.2024.03.018 · Cited by 3
TAP-Track: Generalizable Spacecraft Pose Tracking by Tracking Any Points
Liu, Y., Qi, Z., Chen, P., Fan, H., Zhu, Y., Yang, J., & Zhang, Y. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3584925 · Cited by 3
“The most recent pose tracking method [41] further introduces SPNv2 as a module into the whole pipeline of the Kalman filter (KF), to track a spacecraft’s pose across frames in an image sequence, demonstrating promising performance even in real scenarios.”
InfluentialEvent-Driven Simulation for Rapid Iterative Development of Distributed Space Flight Software
Bell, T., & D’Amico, S. (2025) · IEEE Aerospace Conference (AERO) · doi:10.1109/aero63441.2025.11068699 · Cited by 3
Self-citationFlexKalmanNet: A Modular AI-Enhanced Kalman Filter Framework Applied to Spacecraft Motion Estimation
Vogt, M. D. P.-T., Huwald, M., Ben‐Larbi, M. K., & Stoll, E. (2024) · IEEE Congress on Evolutionary Computation (CEC) · doi:10.1109/cec60901.2024.10612159 · Cited by 3
“Notable exceptions include Park and D’Amico’s work [8], which integrates Convolutional Neural Network (CNN)-based pose estimation with an Unscented Kalman Filter (UKF) for both pose and twist estimation.”
BackgroundAdaptive Relative Pose Estimation Framework with Dual Noise Tuning for Safe Approaching ManeuversPreprint
Candan, B., Oktay, M. B., & Servadio, S. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2507.16214 · Cited by 4
“The majority of filters used in space applications rely on image processing from cameras [37, 52, 53].”
Motion Aware ViT-based Framework for Monocular 6-DoF Spacecraft Pose EstimationPreprint
Sosa, J., Pineau, D., Rathinam, A., Shabayek, A., & Aouada, D. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2509.06000 · Cited by 5
“For example, methods such as [28, 29] combine CNN-based keypoint regression with an Un-scented Kalman Filter (UKF), introducing adaptive noise models and uncertainty-aware filtering.”
Global Light Curve Attitude Estimation with Noisy Measurements and Inertia Uncertainty
Robinson, L., & Frueh, C. E. (2026) · The Journal of the Astronautical Sciences · doi:10.1007/s40295-025-00557-9 · Cited by 3
“Even when resolved imagery is available for LEO objects, attitude [6 ] and shape estimation [ 7 ] are not straight-forward.”
Fast Learning of Non-Cooperative Spacecraft 3D Models through Primitive InitializationPreprint
Huc, P. F., Bates, E., & D’Amico, S. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2507.19459 · Cited by 2
“More recently, CNNs have been combined with classical estimation techniques 13 in order to further refine the pose estimates and improve the robustness to the harsh lighting conditions found in space.”
Self-citationShukla, S., Srivastava, R., Lima, R., & Bera, T. (2024) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros58592.2024.10801805 · Cited by 1
“[ 21] adds an Adaptive Unscented Kalman Filter to SPNv2 [17] architecture.”
Napolano, G., Nocerino, A., Fasano, G., Grassi, M., & Opromolla, R. (2025) · Acta Astronautica · doi:10.1016/j.actaastro.2025.06.012 · Cited by 4
Zhou, Z., Wang, S., Wang, X., Zheng, W. T., & Xu, Y. (2025) · Entropy · doi:10.3390/e27090902 · Cited by 1
“Monocular vision systems are particularly favored due to their significant advantages in size, weight, power consumption, and cost [13], and have been implemented in advanced missions such as RemoveDEBRIS [14] and Restore-L [15].”
6-DOF object tracking method based on lensless event sensor
You, Y., Zhu, M., Zhang, H., & He, B. (2025) · Measurement · doi:10.1016/j.measurement.2025.119389 · Cited by 1
Zhu, Q., Xu, C., Zhang, Y., Lu, Y., Wang, X., & Li, P. (2025) · Remote Sensing · doi:10.3390/rs17213543 · Cited by 1
Yang, S., Zhang, Y., & Zhang, X. (2025) · IEEE Access · doi:10.1109/access.2025.3634758 · Cited by 1
“At the front-end trajectory smoothing level, the Unscented Kalman Filter (UKF) has been widely recognized as an effective tool for handling nonlinear motion in aircraft tracking scenarios [36].”
Liu, K., Yu, Y., Liu, T., Han, D., & Liao, W. (2026) · Acta Astronautica · doi:10.1016/j.actaastro.2026.04.033 · Cited by 1
Equivariant Filter for Relative Attitude and Target Angular Velocity Estimation
Serrano, G., Guerreiro, B. J., Lourenço, P., & Cunha, R. (2025) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2025.3643413 · Cited by 1
“Nevertheless, learning-based approaches could be useful in perception, an area where these methods have had a significant impact and outperform classical computer vision algorithms, or as sources of pose measurements that are fed to a filter, as is done in [13].”
Golroudbari, A. A., & Sabour, M. H. (2023) · doi:10.22541/au.168727976.63672670/v1 · Cited by 1
Digital and Robotic Twinning for Validation of Proximity Operations and Formation FlyingPreprint
Ahmed, Z., Bates, E., Huc, P. F., Low, S. Y. W., Golan, A., Bell, T., Rizza, A., & D'Amico, S. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2507.20034 · Cited by 1
Self-citationA Robust Approach Merging Deep Learning and Unscented Kalman for Vision Based Space Rendez-Vous
Chambon, T., & Gallet, F. (2024) · IAF Astrodynamics Symposium · doi:10.52202/078368-0156
Faraco, N., Maestrini, M., Massari, M., & Lizia, P. D. (2024) · IAF Astrodynamics Symposium · doi:10.52202/078368-0157
Zhang, X., Zhang, M., & Wang, W. (2024) · IEEE Smart World Congress (SWC) · doi:10.1109/swc62898.2024.00101
“RF tracking, including Doppler and two-way ranging [23], enables accurate orbit determination but requires cooperative satellite transponders [24] [25].”
Pose and Velocity Estimation of Noncooperative Spacecraft with Deep Landmark Regression and Tracking
Chen, Z., Gui, H., & Zhong, R. (2025) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc65474.2025.11091016
“For more details about SHIRT, please refer to [6].”
InfluentialCollaborative Spacecraft Servicing Under Partial Feedback Using Lyapunov-Based Deep Neural Networks
Nino, C. F., Patil, O. S., Petersen, C., Phillips, S. A., & Dixon, W. E. (2025) · The Journal of the Astronautical Sciences · doi:10.1007/s40295-025-00516-4
“Several results have demonstrated the effectiveness of adaptive NNs in spacecraft rendezvous applications, including estimating nonlinear dynamical models in the presence of J 2 perturbations and orbit uncertainty estimation [14, 15], and uncertain spacecraft dynamics [16, 17].”
Trinocular vision with deep learning for object twist estimation: a benchmark approach and dataset
Wang, J., Cui, K., Teng, T., Wang, Z., Ren, B., & Yu, Q. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-025-11461-x
Multiview Optical Navigation for Space Manipulator Systems During In-Orbit Servicing Missions
Faraco, N., Maestrini, M., Massari, M., & Di Lizia, P. (2024) · Virtual Community of Pathological Anatomy (University of Castilla La Mancha)
Dickinson, T., Friesenhahn, D., Fletcher, J., Walvoord, D. J., Montera, D., & Gartley, M. G. (2026) · Aerospace · doi:10.3390/aerospace13080744
A Novel RGB-D Camera Based Dataset for Spacecraft Pose Estimation
Zhao, H., Hu, J., Wang, G., Sha, J., Huang, X., Wang, B., & Li, S. (2026) · Space Science & Technology · doi:10.34133/space.0446 · Cited by 1
Goodridge, R., & Ulrich, S. (2026) · AIAA SciTech Forum · doi:10.2514/6.2026-2443
D4PED: A Realistic Pose Estimation Dataset for DFH-4 Satellite Driven by Dynamics
Chen, X., Xue, Y., Liu, Z., Xu, L., & Wang, X. F. (2026) · Advances in Astronautics · doi:10.1007/s42423-026-00208-7
Banker, L., Wozniak, M., Alameer, M., Paul, S. N., Meisinger, D., Baer, G., Hunting, T., Dunham, R., & Kamdar, J. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2603.20575
“These accurately labeled simulated images are used alongside synthetic computer-rendered images to create datasets such as SPEED (Sharma et al., 2019), SPEED + (Park et al., 2022), and SHIRT (Park & D’Amico, 2017).”
COMET: Continuous-Time Trajectory-Guided Temporal Modeling for Spacecraft Pose Estimation
Qi, Z., Fan, H., Zou, Y., & Zhang, Y. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11463426
Unscented Kalman Filter Based Long-Term Dense Optical Flow Tracking for Noncooperative Spacecraft
Xing, B., Li, C., Cheng, D., & Nie, X. (2026) · Lecture notes in electrical engineering · doi:10.1007/978-981-95-7641-8_10
Towards Robust 6D Pose Tracking for On-Orbit-Servicing with Learned Segmentation and Motion Priors
Reichert, A. E., Ulmer, M., Piccinin, M., Eklund, D. F., Haglund, H., Schenk, D., Durner, M., & Triebel, R. (2026) · IEEE Aerospace Conference (AERO) · doi:10.1109/aero66936.2026.11519910
“While SHIRT [22] provides sequential data, it features only two simulated rendezvous trajectories of the Tango spacecraft, which does not suffice for a qualitative evaluation.”
FGSat: A New Dataset and Performance Benchmark for Fine-Grained Satellite Classification
Li, Y., He, J., & Gao, Y. (2025) · IEEE International Conference on Control Science and Systems Engineering (ICCSSE) · doi:10.1109/iccsse67426.2025.11552469
“Similarly, hardware-in-the-loop datasets such as SHIRT [14] capture partial high-fidelity imagery from experimental modules, enabling validation under controlled yet realistic conditions.”
Bridging the domain gap in spacecraft pose estimation: A novel image generative model
Song, Z., Zhang, Z., Zhang, F., & Xiao, X. (2026) · Aerospace Science and Technology · doi:10.1016/j.ast.2026.112871
Cruz, P., Batista, P., & Sanyal, A. K. (2026) · Aerospace Science and Technology · doi:10.1016/j.ast.2026.113146
Koushafar, M., & Kosari, A. (2026) · Acta Astronautica · doi:10.1016/j.actaastro.2026.07.027 · Cited by 1
Lightweight Monocular Relative Pose Estimation of Spacecraft via Scale-Adaptive Multi-Task Learning
Hu, Z., Zhang, Y., Hou, B., & Yao, G. (2026) · Aerospace · doi:10.3390/aerospace13090813
“Subsequent work has improved direct estimation through multi-task auxiliary supervision (SPNv2 [14]), transformer-based feature extraction and bidirectional fusion (SPTN [15]), and balanced loss design (URSONet [16]).”
Li, W., Sun, G., Lu, Y., Fang, Y., & Zhang, Y. (2026) · Aerospace Science and Technology · doi:10.1016/j.ast.2026.113898
RIFusion-Lite: Lightweight Vis–NIR Fusion for Space-Target Remote Sensing Under Complex Illumination
Qingliang, Y., Zhang, H., Yu, M., Chahan, B., & YunJi, C. U. I. (2026) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2026.3742367
Xin, Z. E. N. G., Hairong, C. H. U., Wu, G., Miao, X. U., Zhang, D., Yuan, Y., Lang, Y. A. N. G., & Liu, P. (2026) · Chinese Journal of Aeronautics · doi:10.1016/j.cja.2026.104514
Wavelet-Enhanced Feature Pyramid Network for Pose Estimation of Non-Cooperative Spacecraft
Yang, L., Zhang, Z., Nie, X., & Zhang, B. (2026) · Journal of Aerospace Information Systems · doi:10.2514/1.i011815
Foundation Models for Autonomous Space Robotics: Architectures, Physical Adaptation, and ValidationPreprint
Wang, Z., Deng, J., Lu, X., Jia, Z., Huang, Y., Zhu, Y., & Li, J. (2026) · arXiv (Cornell University) · doi:10.13140/rg.2.2.27769.22885
Sanoja, C. E. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.34819
“SHIRT adds temporally structured rendezvous observations [11].”
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
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.