pith. machine review for the scientific record. sign in

arxiv: 2604.25782 · v1 · submitted 2026-04-28 · 💻 cs.NI · cs.RO

Recognition: unknown

EOS-Bench: A Comprehensive Benchmark for Earth Observation Satellite Scheduling

Qian Yin , Jiaxing Li , Jiaqi Cheng , Qizhang Luo , Annalisa Riccardi , Abhijit Chatterjee , Rafael Vazquez , Carlo Novara
show 18 more authors
Michalis Mavrovouniotis Ponnuthurai Nagaratnam Suganthan Shengzhou Bai Xiaoxuan Hu Lining Xing Ming Xu Shuang Li Zixuan Zheng Xin Shen Xiaoyu Chen Yi Gu Yanjie Song Witold Pedrycz Evan L. Kramer Laio Oriel Seman Cletah Shoko Guohua Wu Xinwei Wang
Authors on Pith no claims yet

Pith reviewed 2026-05-07 14:21 UTC · model grok-4.3

classification 💻 cs.NI cs.RO
keywords earth observation satellitescheduling benchmarkcombinatorial optimisationNP-hard problemagile satellitesorbital dynamicsmixed-integer programmingdeep reinforcement learning
0
0 comments X

The pith

EOS-Bench supplies 1,390 realistic scenarios and 13,900 instances to compare Earth observation satellite schedulers on quality and speed.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

Earth observation satellite scheduling is a difficult NP-hard combinatorial problem whose complexity rises sharply with agile satellites. Without a shared open benchmark, studies have been hard to compare directly. The paper builds EOS-Bench by generating scenarios that embed high-fidelity orbital dynamics and platform limits, ranging from small validation sets to problems with 1,000 satellites and 10,000 requests. It adds a scheme to measure structural difficulty through factors such as opportunity density and conflict intensity, plus a five-metric evaluation protocol. Tests with mixed-integer programming, heuristics, meta-heuristics, and deep reinforcement learning show the benchmark separates solver performance across scales and reveals quality-efficiency trade-offs.

Core claim

EOS-Bench is established as a unified open framework that generates 1,390 scenarios and 13,900 benchmark instances by integrating high-fidelity orbital dynamics and platform constraints, covering small-scale cases through large coordination problems with up to 1,000 satellites. A scenario characterisation scheme quantifies difficulty via opportunity density, task flexibility, conflict intensity, and satellite congestion. A multidimensional protocol then evaluates solvers on task profit, completion rate, workload balance, timeliness, and runtime, demonstrating that the benchmark distinguishes performance across scales and conditions for mixed-integer programming, heuristics, meta-heuristics,,

What carries the argument

The EOS-Bench scenario generator that couples high-fidelity orbital dynamics with platform constraints to produce instances, together with the difficulty characterisation scheme and the five-metric evaluation protocol.

If this is right

  • Researchers can now run controlled comparisons of mixed-integer programming, heuristics, meta-heuristics, and reinforcement learning on identical scenario sets.
  • Trade-offs between solution quality and computational runtime become measurable across small, medium, and large problem scales.
  • The characterisation scheme allows systematic study of how opportunity density and conflict intensity affect solver success.
  • The open testbed supports reproducible extension to new algorithms and to both agile and non-agile satellite settings.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Widespread adoption could standardise evaluation practices and reduce duplicated effort in developing schedulers for operational missions.
  • The same generation approach might be adapted to related large-scale scheduling domains such as drone fleet routing or ground station tasking.
  • Future work could test whether the benchmark instances predict performance on proprietary real-world datasets from specific satellite operators.

Load-bearing premise

The generated scenarios with integrated high-fidelity orbital dynamics and platform constraints accurately represent the structural difficulty and real-world complexity of actual Earth observation satellite scheduling problems.

What would settle it

If algorithms ranked highly by EOS-Bench produce markedly worse schedules on real satellite mission data than lower-ranked ones, or if real problems show different difficulty patterns than the generated set, the benchmark's representativeness would be falsified.

Figures

Figures reproduced from arXiv: 2604.25782 by Abhijit Chatterjee, Annalisa Riccardi, Carlo Novara, Cletah Shoko, Evan L. Kramer, Guohua Wu, Jiaqi Cheng, Jiaxing Li, Laio Oriel Seman, Lining Xing, Michalis Mavrovouniotis, Ming Xu, Ponnuthurai Nagaratnam Suganthan, Qian Yin, Qizhang Luo, Rafael Vazquez, Shengzhou Bai, Shuang Li, Witold Pedrycz, Xiaoxuan Hu, Xiaoyu Chen, Xin Shen, Xinwei Wang, Yanjie Song, Yi Gu, Zixuan Zheng.

Figure 1
Figure 1. Figure 1: Differences between non-agile and agile satellites. Non-agile satellites mainly observe near nadir, view at source ↗
Figure 2
Figure 2. Figure 2: Modular architecture and end-to-end workflow of the EOS-Bench framework, from initial modelling to view at source ↗
Figure 3
Figure 3. Figure 3: Orbital ground tracks of the 20 real satellites. These ground tracks illustrate the orbital diversity of view at source ↗
Figure 4
Figure 4. Figure 4: Hierarchical organisation and generation mechanism of the EOS-Bench. It illustrates the mapping of view at source ↗
Figure 5
Figure 5. Figure 5: Merged continuous conflict windows in a representative scenario. Specifically, data for a single satellite, view at source ↗
Figure 6
Figure 6. Figure 6: Evolution of the ten scenario characterisation descriptors as constellation size scales from 1 to 100 view at source ↗
Figure 7
Figure 7. Figure 7: Effect of constellation orbital architecture on structural descriptors at 50- and 100-satellite scales. Bars view at source ↗
Figure 8
Figure 8. Figure 8: Solution quality and optimality assessment. view at source ↗
Figure 9
Figure 9. Figure 9: Computational effort and scalability analysis. view at source ↗
Figure 10
Figure 10. Figure 10: Distributional robustness and sensitivity analysis. view at source ↗
Figure 11
Figure 11. Figure 11: Multi-objective trade-off and Pareto analysis via performance profiles. view at source ↗
Figure 12
Figure 12. Figure 12: Algorithm sensitivity to resource capacity in Regional Distribution. view at source ↗
Figure 13
Figure 13. Figure 13: Algorithm sensitivity to satellite agility. view at source ↗
Figure 14
Figure 14. Figure 14: Impact of Orbit Architecture at medium scales. view at source ↗
Figure 15
Figure 15. Figure 15: Performance analysis in Realistic-target scenarios with scaling constellation size ( view at source ↗
Figure 16
Figure 16. Figure 16: Scheduling visualisation in EOS-Bench. Interactive visualisation of satellite trajectories, target loca view at source ↗
read the original abstract

Earth observation satellite imaging scheduling is a challenging NP-hard combinatorial optimisation problem central to space mission operations. While next-generation agile Earth observation satellites (EOS) increase operational flexibility, they also significantly raise scheduling complexity. The lack of a unified, open-source benchmark makes it difficult to compare algorithms across studies. This paper introduces EOS-Bench, a comprehensive framework for systematic and reproducible evaluation of scheduling methods. By integrating high-fidelity orbital dynamics and platform constraints, EOS-Bench generates 1,390 scenarios and 13,900 benchmark instances, spanning from small-scale validation cases to large coordination problems with up to 1,000 satellites and 10,000 requests. We further propose a scenario characterisation scheme to quantify structural difficulty based on factors such as opportunity density, task flexibility, conflict intensity, and satellite congestion. A multidimensional evaluation protocol is introduced, assessing performance across five metrics: task profit, completion rate, workload balance, timeliness, and runtime. The framework is evaluated using mixed-integer programming, heuristics, meta-heuristics, and deep reinforcement learning across both agile and non-agile settings. Results show that EOS-Bench effectively distinguishes solver performance across scales and conditions, revealing trade-offs between solution quality and computational efficiency, and providing deeper insight into scenario complexity. EOS-Bench offers a unified and extensible open testbed for advancing research in Earth observation satellite scheduling. The code and data are available at https://github.com/Ethan19YQ/EOS-Bench.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 2 minor

Summary. The paper introduces EOS-Bench, an open benchmark framework for Earth observation satellite (EOS) scheduling. It generates 1,390 scenarios and 13,900 instances using high-fidelity orbital dynamics and platform constraints, covering agile and non-agile cases from small validation instances to large problems with up to 1,000 satellites and 10,000 requests. A characterization scheme quantifies structural difficulty via opportunity density, task flexibility, conflict intensity, and satellite congestion. A multidimensional evaluation protocol assesses solvers (MIP, heuristics, meta-heuristics, DRL) on five metrics: task profit, completion rate, workload balance, timeliness, and runtime. Results indicate the benchmark distinguishes performance across scales and conditions while revealing quality-efficiency trade-offs.

Significance. If the synthetic scenarios prove representative of real operational complexity, EOS-Bench fills a notable gap by supplying a unified, extensible, and publicly available testbed (with code and data at the cited GitHub repository) for comparing optimization and learning-based methods on an NP-hard problem. This could standardize evaluations, enable reproducible cross-study comparisons, and accelerate progress on agile EOS scheduling where flexibility increases both capability and difficulty.

major comments (2)
  1. [§3] §3 (Scenario Generation and Characterization): The 1,390 scenarios are produced from high-fidelity orbital dynamics and platform constraints, yet no quantitative comparison is reported against real historical schedules or operator-provided instances (e.g., no Kolmogorov-Smirnov tests or moment-matching on opportunity density or conflict intensity distributions). Because the central claim that EOS-Bench 'provides deeper insight into scenario complexity' rests on these instances reflecting actual structural difficulty, the absence of external validation leaves open the possibility that reported solver distinctions are generator-specific artifacts.
  2. [§5] §5 (Evaluation Protocol and Results): The multidimensional protocol reports trade-offs across scales, but without a sensitivity analysis that perturbs generation parameters (e.g., varying conflict intensity thresholds or orbital assumptions) and re-ranks the MIP/heuristic/DRL solvers, it is unclear whether the observed performance distinctions are robust or tied to the particular synthetic model. This directly affects the claim that the benchmark 'effectively distinguishes solver performance across scales and conditions.'
minor comments (2)
  1. [Abstract] The derivation of the 13,900 instances from the 1,390 scenarios (apparently 10 instances per scenario) should be stated explicitly in the text or a table, including how random seeds or perturbations are applied.
  2. A summary table listing the ranges or distributions of the four characterization metrics across the scenario set would help readers assess coverage without consulting the repository.

Simulated Author's Rebuttal

2 responses · 1 unresolved

We thank the referee for the constructive and detailed feedback on EOS-Bench. The comments highlight important aspects of external validation and robustness that we address point by point below. We indicate the revisions we will incorporate where feasible.

read point-by-point responses

  1. Referee: [§3] §3 (Scenario Generation and Characterization): The 1,390 scenarios are produced from high-fidelity orbital dynamics and platform constraints, yet no quantitative comparison is reported against real historical schedules or operator-provided instances (e.g., no Kolmogorov-Smirnov tests or moment-matching on opportunity density or conflict intensity distributions). Because the central claim that EOS-Bench 'provides deeper insight into scenario complexity' rests on these instances reflecting actual structural difficulty, the absence of external validation leaves open the possibility that reported solver distinctions are generator-specific artifacts.

    Authors: We acknowledge that a direct quantitative comparison to real historical schedules would provide stronger support for the representativeness of the generated scenarios. Real operational EOS scheduling data is typically proprietary and unavailable for public benchmarking due to mission sensitivities. Our generation process employs established high-fidelity orbital dynamics and constraint models drawn from the peer-reviewed literature on EOS operations. The proposed characterization scheme focuses on measurable structural properties (opportunity density, task flexibility, conflict intensity, satellite congestion) that are recognized in the domain as primary drivers of scheduling difficulty. In the revised manuscript we will expand §3 with an explicit limitations subsection that discusses the synthetic nature of the benchmark, cites the validation status of the underlying models, and clarifies that EOS-Bench is intended as a standardized, extensible testbed rather than a replica of any single operator’s dataset. We cannot perform Kolmogorov-Smirnov or moment-matching tests without access to the requisite real instances. revision: partial

  2. Referee: [§5] §5 (Evaluation Protocol and Results): The multidimensional protocol reports trade-offs across scales, but without a sensitivity analysis that perturbs generation parameters (e.g., varying conflict intensity thresholds or orbital assumptions) and re-ranks the MIP/heuristic/DRL solvers, it is unclear whether the observed performance distinctions are robust or tied to the particular synthetic model. This directly affects the claim that the benchmark 'effectively distinguishes solver performance across scales and conditions.'

    Authors: We agree that an explicit sensitivity analysis would strengthen the robustness claim. Although the existing 1,390 scenarios already span wide ranges of scales and structural conditions, we did not systematically perturb isolated generation parameters (such as conflict-intensity thresholds) and re-rank solvers. In the revised version we will add a dedicated sensitivity subsection in §5. For a representative subset of scenarios we will vary key parameters (conflict intensity, task flexibility, and orbital assumptions within realistic bounds) and report whether the relative ordering of MIP, heuristic, meta-heuristic, and DRL solvers remains consistent across the five metrics. This analysis will be included in the next manuscript version. revision: yes

standing simulated objections not resolved
  • Quantitative comparison of scenario distributions against real historical or operator-provided EOS schedules (e.g., via Kolmogorov-Smirnov tests or moment matching), because such detailed instances are not publicly available.

Circularity Check

0 steps flagged

No significant circularity; benchmark results are direct empirical evaluations on externally supplied generated instances.

full rationale

The paper generates 1,390 scenarios from high-fidelity orbital dynamics and platform constraints, defines a characterisation scheme (opportunity density, task flexibility, conflict intensity, satellite congestion), runs MIP, heuristics, meta-heuristics and DRL solvers, and reports performance on five metrics. No derivation step reduces a claimed distinction or insight to a quantity defined by the paper's own fitted parameters or prior self-citations. The central claim rests on observable differences across the supplied instances rather than any self-referential prediction or uniqueness theorem. Code and data are released publicly, allowing independent reproduction outside the paper's internal choices.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The central claim rests on standard domain models of orbital mechanics and scheduling constraints plus the assumption that the generated instances are representative; no new physical entities or fitted constants are introduced in the abstract description.

axioms (1)
  • domain assumption High-fidelity orbital dynamics and platform constraints can be faithfully encoded in the scenario generator
    Invoked when the abstract states that EOS-Bench integrates these elements to produce realistic instances.

pith-pipeline@v0.9.0 · 5677 in / 1285 out tokens · 49527 ms · 2026-05-07T14:21:48.548260+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

129 extracted references · 112 canonical work pages · 1 internal anchor

  1. [1]

    X. Wang, G. Wu, W. Pedrycz, L. Xing, Agile earth observation satellite scheduling over 20 years: Formulations, methods, and future directions, IEEE Systems Journal 15 (2020) 3881–3892. doi: 10.1109/JSYST.2020.2997050

    work page doi:10.1109/jsyst.2020.2997050 2020

  2. [2]

    Y. Gu, C. Han, Y. Chen, S. Liu, X. Wang, Large region targets observation schedul- ing by multiple satellites using resampling particle swarm optimization, IEEE Trans- actions on Aerospace and Electronic Systems 59 (2022) 1800–1815. doi: 10.1109/TAES. 2022.3205565

    work page doi:10.1109/taes 2022

  3. [3]

    Y. Gu, H. Liu, T. Pan, S. Bai, J. Liu, Y. Wu, G. Wu, Ensemble time freedom heuristic and intelligent optimization algorithm for relay satellites scheduling considering multi- type task requirements, Expert Systems with Applications 316 (2026) 131815. doi: 10. 1016/j.eswa.2026.131815

    work page arXiv 2026

  4. [4]

    Lema ˆıtre, G

    L. Michel, G. Verfaillie, F. Jouhaud, J.-M. Lachiver, N. Bataille, Selecting and scheduling observations of agile satellites, Aerospace Science and Technology 6 (2002) 367–381. doi:10.1016/S1270-9638(02)01173-2

    work page doi:10.1016/s1270-9638(02)01173-2 2002

  5. [5]

    Ferrari, J.-F

    B. Ferrari, J.-F. Cordeau, M. Delorme, M. Iori, R. Orosei, Satellite scheduling problems: A survey of applications in earth and outer space observation, Computers & Operations Research 173 (2025) 106875. doi: 10.1016/j.cor.2024.106875

    work page doi:10.1016/j.cor.2024.106875 2025

  6. [6]

    Y. Chen, J. Lu, R. He, J. Ou, An efficient local search heuristic for earth observation satellite integrated scheduling problems, Applied Sciences 10 (2020) 5616. doi: 10.3390/ app10165616

    2020

  7. [8]

    L. Wei, Y. Chen, M. Chen, Y.-W. Chen, Deep reinforcement learning and parameter transfer based approach for the multi-objective agile earth observation satellite scheduling problem, Applied Soft Computing 110 (2021) 107607. doi: 10.1016/j.asoc.2021.107607. 62

    work page doi:10.1016/j.asoc.2021.107607 2021

  8. [10]

    Rocha, G

    Y. Rocha, G. O. Chagas, L. C. Coelho, A. Subramanian, The integrated agile earth observation satellite scheduling problem, Computers & Operations Research 184 (2025) 107212. doi: 10.1016/j.cor.2025.107212

    work page doi:10.1016/j.cor.2025.107212 2025

  9. [11]

    A. E. Vasegaard, A. K. Larsen, EOSpython version 0.0.11: A framework for sce- nario generation and a solution system for the agile earth observation satellite schedul- ing problem, arXiv preprint arXiv:2410.13462 (2024). doi: 10.48550/arXiv.2410.13462. arXiv:2410.13462

    work page doi:10.48550/arxiv.2410.13462 2024

  10. [12]

    L. Wang, Y. Xiang, H. Huang, D. Li, C. Gao, S. Liu, Towards realistic earth-observation constellation scheduling: Benchmark and methodology, arXiv preprint (2025). doi: 10. 48550/arXiv.2510.26297. arXiv:2510.26297

    work page arXiv 2025

  11. [13]

    P. W. Kenneally, S. Piggott, H. Schaub, Basilisk: A flexible, scalable and modular astrodynamics simulation framework, Journal of aerospace information systems 17 (2020) 496–507. doi: 10.2514/1.I010762

    work page doi:10.2514/1.i010762 2020

  12. [14]

    Tangpattanakul, N

    P. Tangpattanakul, N. Jozefowiez, P. Lopez, A multi-objective local search heuristic for scheduling earth observations taken by an agile satellite, European Journal of Operational Research 245 (2015) 542–554. doi: 10.1016/j.ejor.2015.03.011

    work page doi:10.1016/j.ejor.2015.03.011 2015

  13. [15]

    X. Liu, G. Laporte, Y. Chen, R. He, An adaptive large neighborhood search metaheuristic for agile satellite scheduling with time-dependent transition time, Computers & Opera- tions Research 86 (2017) 41–53. doi: 10.1016/j.cor.2017.04.006

    work page doi:10.1016/j.cor.2017.04.006 2017

  14. [16]

    G. Peng, G. Song, Y. He, J. Yu, S. Xiang, L. Xing, P. Vansteenwegen, Solving the agile earth observation satellite scheduling problem with time-dependent transition times, IEEE Transactions on Systems, Man, and Cybernetics: Systems 52 (2022) 1614–1625. doi:10.1109/TSMC.2020.3031738

    work page doi:10.1109/tsmc.2020.3031738 2022

  15. [17]

    G. Peng, R. Dewil, C. Verbeeck, A. Gunawan, L. Xing, P. Vansteenwegen, Agile earth observation satellite scheduling: An orienteering problem with time-dependent profits and travel times, Computers & Operations Research 111 (2019) 84–98. doi: 10.1016/j.cor. 2019.05.030

    work page doi:10.1016/j.cor 2019

  16. [18]

    G. Peng, G. Song, L. Xing, A. Gunawan, P. Vansteenwegen, An exact algorithm for agile earth observation satellite scheduling with time-dependent profits, Computers & Operations Research 120 (2020) 104946. doi: 10.1016/j.cor.2020.104946

    work page doi:10.1016/j.cor.2020.104946 2020

  17. [19]

    Perea, R

    F. Perea, R. Vazquez, J. Galán-Vioque, Swath-acquisition planning in multiple-satellite missions: an exact and heuristic approach, IEEE Transactions on Aerospace and Elec- tronic Systems 51 (2015) 1717–1725. doi: 10.1109/TAES.2015.130751. 63

    work page doi:10.1109/taes.2015.130751 2015

  18. [20]

    X.-W. Wang, Z. Chen, C. Han, Scheduling for single agile satellite, redundant targets problem using complex networks theory, Chaos, Solitons & Fractals 83 (2016) 125–132. doi:10.1016/j.chaos.2015.12.003

    work page doi:10.1016/j.chaos.2015.12.003 2016

  19. [21]

    C. G. Valicka, D. Garcia, A. Staid, J.-P. Watson, G. Hackebeil, S. Rathinam, L. Ntaimo, Mixed-integer programming models for optimal constellation scheduling given cloud cover uncertainty, European Journal of Operational Research 275 (2019) 431–445. doi: 10.1016/ j.ejor.2018.11.043

    2019

  20. [22]

    X. Wang, Y. Gu, G. Wu, J. R. Woodward, Robust scheduling for multiple agile earth ob- servation satellites under cloud coverage uncertainty, Computers & Industrial Engineering 156 (2021) 107292. doi: 10.1016/j.cie.2021.107292

    work page doi:10.1016/j.cie.2021.107292 2021

  21. [23]

    C. He, Y. Dong, H. Li, Y. Liew, Reasoning-based scheduling method for agile earth observation satellite with multi-subsystem coupling, Remote Sensing 15 (2023) 1577. doi:10.3390/rs15061577

    work page doi:10.3390/rs15061577 2023

  22. [24]

    C. A. Rigo, L. O. Seman, E. Camponogara, E. Morsch Filho, E. A. Bezerra, P. Munari, A branch-and-price algorithm for nanosatellite task scheduling to improve mission quality- of-service, European Journal of Operational Research 303 (2022) 168–183. doi: 10.1016/ j.ejor.2022.02.040

    2022

  23. [25]

    X. Wang, R. Leus, C. Han, Fixed interval scheduling of multiple earth observation satel- lites with multiple observations, in: 2018 9th International Conference on Mechanical and Aerospace Engineering (ICMAE), IEEE, 2018, pp. 28–33. doi: 10.1109/ICMAE.2018. 8467667

    work page doi:10.1109/icmae.2018 2018

  24. [26]

    Camponogara, L

    E. Camponogara, L. O. Seman, C. A. Rigo, E. Morsch Filho, B. F. Ribeiro, E. A. Bezerra, A continuous-time formulation for optimal task scheduling and quality-of- service assurance in nanosatellites, Computers & Operations Research 147 (2022) 105945. doi:10.1016/j.cor.2022.105945

    work page doi:10.1016/j.cor.2022.105945 2022

  25. [27]

    L. O. Seman, C. A. Rigo, E. Camponogara, P. Munari, E. A. Bezerra, Improving energy aware nanosatellite task scheduling by a branch-cut-and-price algorithm, Computers & Operations Research 158 (2023) 106292. doi: 10.1016/j.cor.2023.106292

    work page doi:10.1016/j.cor.2023.106292 2023

  26. [28]

    Tharmarasa, T

    R. Tharmarasa, T. Kirubarajan, J. Berger, M. C. Florea, Mixed open-and-closed loop satellite task planning, in: 2019 22th International Conference on Information Fusion (FU- SION), IEEE, Ottawa, ON, Canada, 2019, pp. 1–8. doi: 10.23919/FUSION43075.2019. 9011405

    work page doi:10.23919/fusion43075.2019 2019

  27. [29]

    G. Wu, Z. Xiang, Y. Wang, Y. Gu, W. Pedrycz, Improved adaptive large neighborhood search algorithm based on the two-stage framework for scheduling multiple super-agile satellites, IEEE Transactions on Aerospace and Electronic Systems 60 (2024) 7185–7200. doi:10.1109/TAES.2024.3416427. 64

    work page doi:10.1109/taes.2024.3416427 2024

  28. [30]

    Barkaoui, J

    M. Barkaoui, J. Berger, A new hybrid genetic algorithm for the collection scheduling problem for a satellite constellation, Journal of the Operational Research Society 71 (2020) 1390–1410. doi: 10.1080/01605682.2019.1609891

    work page doi:10.1080/01605682.2019.1609891 2020

  29. [31]

    Chang, Z

    Z. Chang, Z. Zhou, L. Xing, F. Yao, Integrated scheduling problem for earth observa- tion satellites based on three modeling frameworks: An adaptive bi-objective memetic algorithm, Memetic Computing 13 (2021) 203–226. doi: 10.1007/s12293-021-00333-w

    work page doi:10.1007/s12293-021-00333-w 2021

  30. [32]

    G. Wu, Q. Luo, X. Du, Y. Chen, P. N. Suganthan, X. Wang, Ensemble of metaheuristic and exact algorithm based on the divide-and-conquer framework for multisatellite obser- vation scheduling, IEEE Transactions on Aerospace and Electronic Systems 58 (2022) 4396–4408. doi: 10.1109/TAES.2022.3160993

    work page doi:10.1109/taes.2022.3160993 2022

  31. [33]

    J. Qi, M. Hu, L. Xing, A decompose-and-learn multi-objective algorithm for scheduling large-scale earth observation satellites, Swarm and Evolutionary Computation 92 (2025) 101792. doi: 10.1016/j.swevo.2024.101792

    work page doi:10.1016/j.swevo.2024.101792 2025

  32. [34]

    L. Liu, Z. Dong, H. Su, D. Yu, A study of distributed earth observation satellites mission scheduling method based on game-negotiation mechanism, Sensors 21 (2021) 6660. doi: 10. 3390/s21196660

    2021

  33. [35]

    H. Fan, Z. Yang, X. Zhang, S. Wu, J. Long, L. Liu, A novel multi-satellite and multi- task scheduling method based on task network graph aggregation, Expert Systems with Applications 205 (2022) 117565. doi: 10.1016/j.eswa.2022.117565

    work page doi:10.1016/j.eswa.2022.117565 2022

  34. [36]

    H. Sun, W. Xia, Z. Wang, X. Hu, Agile earth observation satellite scheduling algorithm for emergency tasks based on multiple strategies, Journal of Systems Science and Systems Engineering 30 (2021) 626–646. doi: 10.1007/s11518-021-5506-4

    work page doi:10.1007/s11518-021-5506-4 2021

  35. [37]

    Stollenwerk, V

    T. Stollenwerk, V. Michaud, E. Lobe, M. Picard, A. Basermann, T. Botter, Agile earth ob- servation satellite scheduling with a quantum annealer, IEEE Transactions on Aerospace and Electronic Systems 57 (2021) 3520–3528. doi: 10.1109/TAES.2021.3088490

    work page doi:10.1109/taes.2021.3088490 2021

  36. [38]

    Rainjonneau, I

    S. Rainjonneau, I. Tokarev, S. Iudin, S. Rayaprolu, K. Pinto, D. Lemtiuzhnikova, M. Koblan, E. Barashov, M. Kordzanganeh, M. Pflitsch, A. Melnikov, Quantum al- gorithms applied to satellite mission planning for earth observation, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 16 (2023) 7062–7075. doi:10.1109/JSTARS.2023.3287154

    work page doi:10.1109/jstars.2023.3287154 2023

  37. [39]

    X. Sun, Y. Ren, L. Yu, Adaptive-strategies-based quantum genetic algorithm for agile earth observation satellite scheduling problem, IEEE Aerospace and Electronic Systems Magazine 40 (2025) 4–15. doi: 10.1109/MAES.2025.3547993

    work page doi:10.1109/maes.2025.3547993 2025

  38. [40]

    X. Sun, Y. Ren, L. Yu, Multi-adaptive strategies-based higher-order quantum genetic algorithm for agile remote sensing satellite scheduling problem, Sensors 24 (2024) 4938. doi:10.3390/s24154938. 65

    work page doi:10.3390/s24154938 2024

  39. [41]

    Marchioli, M

    V. Marchioli, M. Boggio, D. Volpe, L. Massotti, C. Novara, Quantum optimization for closed-loop scheduling of earth observation satellite formation, SN Computer Science 6 (2025) 739. doi: 10.1007/s42979-025-04252-2

    work page doi:10.1007/s42979-025-04252-2 2025

  40. [43]

    Herrmann, H

    A. Herrmann, H. Schaub, A comparative analysis of reinforcement learning algorithms for earth-observing satellite scheduling, Frontiers in Space Technologies 4 (2023) 1263489. doi:10.3389/frspt.2023.1263489

    work page doi:10.3389/frspt.2023.1263489 2023

  41. [44]

    Y. Song, J. Ou, W. Pedrycz, P. N. Suganthan, X. Wang, L. Xing, Y. Zhang, Generalized model and deep reinforcement learning-based evolutionary method for multitype satellite observation scheduling, IEEE Transactions on Systems, Man, and Cybernetics: Systems 54 (2024) 2576–2589. doi: 10.1109/TSMC.2023.3345928

    work page doi:10.1109/tsmc.2023.3345928 2024

  42. [45]

    Z. Wen, L. Li, J. Song, S. Zhang, H. Hu, Scheduling single-satellite observation and transmission tasks by using hybrid actor-critic reinforcement learning, Advances in Space Research 71 (2023) 3883–3896. doi: 10.1016/j.asr.2022.10.024

    work page doi:10.1016/j.asr.2022.10.024 2023

  43. [46]

    Z. Wen, Y. Liu, S. Zhang, H. Hu, Scheduling observation tasks for large-scale satellite constellation, Journal of Physics: Conference Series 2746 (2024) 012040. doi: 10.1088/ 1742-6596/2746/1/012040

    2024

  44. [47]

    Z. Li, X. Zhu, C. Liu, J. Song, Y. Liu, C. Yin, W. Sun, Dynamic task scheduling optimiza- tion by rolling horizon deep reinforcement learning for distributed satellite system, Expert Systems with Applications 289 (2025) 128350. doi: 10.1016/j.eswa.2025.128350

    work page doi:10.1016/j.eswa.2025.128350 2025

  45. [48]

    B. Li, M. Chen, L. Xing, Y. Chen, Y. Chen, Optimizing time-dependent multi-agile earth observation satellite scheduling problem using deep Q-learning and ensemble heuristics, Information Sciences 712 (2025) 122140. doi: 10.1016/j.ins.2025.122140

    work page doi:10.1016/j.ins.2025.122140 2025

  46. [49]

    Z. Liu, W. Xiong, Z. Jia, C. Han, Two-stage deep reinforcement learning method for agile optical satellite scheduling problem, Complex & Intelligent Systems 11 (2025) 35. doi:10.1007/s40747-024-01667-x

    work page doi:10.1007/s40747-024-01667-x 2025

  47. [50]

    G. Li, X. Li, J. Li, J. Chen, X. Shen, PTMB: An online satellite task scheduling framework based on pre-trained markov decision process for multi-task scenario, Knowledge-Based Systems 284 (2024) 111339. doi: 10.1016/j.knosys.2023.111339

    work page doi:10.1016/j.knosys.2023.111339 2024

  48. [51]

    Y. Liu, Z. Wen, S. Zhang, H. Hu, Learning-based constellation scheduling for time- sensitive space multi-target collaborative observation, Advances in Space Research 73 (2024) 4751–4766. doi: 10.1016/j.asr.2024.02.013

    work page doi:10.1016/j.asr.2024.02.013 2024

  49. [52]

    W. Yao, X. Shen, G. Zhang, Z. Lu, J. Wang, Y. Song, Z. Li, A spiking neural network based proximal policy optimization method for multi-point imaging mission scheduling 66 of earth observation satellite, Swarm and Evolutionary Computation 94 (2025) 101867. doi:10.1016/j.swevo.2025.101867

    work page doi:10.1016/j.swevo.2025.101867 2025

  50. [53]

    X. Chen, T. Tian, G. Dai, M. Wang, Z. Song, L. Xing, Deep reinforcement learning- based resource allocation method for multi-satellite scheduling, Computers & Operations Research 181 (2025) 107088. doi: 10.1016/j.cor.2025.107088

    work page doi:10.1016/j.cor.2025.107088 2025

  51. [54]

    X. Chen, T. Tian, G. Dai, M. Wang, Z. Song, W. Zheng, Q. Zhou, A conflict rain- bow DQN-based two-stage optimization framework for multiple agile satellites schedul- ing, IEEE Transactions on Aerospace and Electronic Systems 61 (2025) 7251–7263. doi:10.1109/TAES.2025.3538476

    work page doi:10.1109/taes.2025.3538476 2025

  52. [55]

    L. He, X. Liu, G. Laporte, Y. Chen, Y. Chen, An improved adaptive large neighbor- hood search algorithm for multiple agile satellites scheduling, Computers & Operations Research 100 (2018) 12–25. doi: 10.1016/j.cor.2018.06.020

    work page doi:10.1016/j.cor.2018.06.020 2018

  53. [56]

    Y. Chen, M. Xu, X. Shen, G. Zhang, Z. Lu, J. Xu, A multi-objective modeling method of multi-satellite imaging task planning for large regional mapping. remote sens. 2020; 12: 344, Remote Sensing 12 (2020) 344. doi: 10.3390/rs12030344

    work page doi:10.3390/rs12030344 2020

  54. [57]

    Y. Chen, X. Shen, G. Zhang, Z. Lu, Large-scale multi-objective imaging satellite task planning algorithm for vast area mapping, Remote Sensing 15 (2023) 4178. doi: 10.3390/ rs15174178

    2023

  55. [59]

    X. Wu, Y. Yang, Y. Xie, Q. Ma, Z. Zhang, Multiregion mission planning by satellite swarm using simulated annealing and neighborhood search, IEEE Transactions on Aerospace and Electronic Systems 60 (2023) 1416–1439. doi: 10.1109/TAES.2023.3337066

    work page doi:10.1109/taes.2023.3337066 2023

  56. [60]

    X. Zeng, R. Yuan, L. Yang, X. Huang, S. Li, Long-term multi-region observation schedul- ing for large-scale constellations via two-stage hybrid planning, Aerospace Science and Technology 169 (2025) 111358. doi: 10.1016/j.ast.2025.111358

    work page doi:10.1016/j.ast.2025.111358 2025

  57. [62]

    X. Han, M. Yang, S. Wang, T. Chao, Continuous monitoring scheduling for moving targets by earth observation satellites, Aerospace Science and Technology 140 (2023) 108422. doi: 10.1016/j.ast.2023.108422

    work page doi:10.1016/j.ast.2023.108422 2023

  58. [63]

    Y. Cong, X. Mei, S. Sun, T. Liu, G. Guan, C. Wei, Autonomous collaborative observation method for time-sensitive moving target tracking by satellite swarms, Advances in Space Research 75 (2025) 5615–5629. doi: 10.1016/j.asr.2025.01.012. 67

    work page doi:10.1016/j.asr.2025.01.012 2025

  59. [64]

    X. Wang, G. Song, R. Leus, C. Han, Robust earth observation satellite scheduling with uncertainty of cloud coverage, IEEE Transactions on Aerospace and Electronic Systems 56 (2019) 2450–2461. doi: 10.1109/TAES.2019.2947978

    work page doi:10.1109/taes.2019.2947978 2019

  60. [65]

    C. Han, Y. Gu, G. Wu, X. Wang, Simulated annealing-based heuristic for multiple agile satellites scheduling under cloud coverage uncertainty, IEEE Transactions on Systems, Man, and Cybernetics: Systems 53 (2022) 2863–2874. doi: 10.1109/TSMC.2022.3220534

    work page doi:10.1109/tsmc.2022.3220534 2022

  61. [66]

    L. He, B. Liang, J. Li, M. Sheng, Joint observation and transmission scheduling in agile satellite networks, IEEE Transactions on Mobile Computing 21 (2022) 4381–4396. doi:10.1109/TMC.2021.3076088

    work page doi:10.1109/tmc.2021.3076088 2022

  62. [67]

    G. Yu, K. Zhang, Research on the integrated scheduling of imaging and data transmission for earth observation satellites, Algorithms 18 (2025) 418. doi: 10.3390/a18070418

    work page doi:10.3390/a18070418 2025

  63. [69]

    J. Wang, X. Zhu, L. T. Yang, J. Zhu, M. Ma, Towards dynamic real-time scheduling for multiple earth observation satellites, Journal of Computer and System Sciences 81 (2015) 110–124. doi: 10.1016/j.jcss.2014.06.016

    work page doi:10.1016/j.jcss.2014.06.016 2015

  64. [70]

    Chang, Z

    Z. Chang, Z. Zhou, Three multi-objective memetic algorithms for observation schedul- ing problem of active-imaging agile earth observation satellites, Annals of Operations Research 346 (2025) 861–893. doi: 10.1007/s10479-024-06156-5

    work page doi:10.1007/s10479-024-06156-5 2025

  65. [71]

    H. Li, Y. Li, Y. Liu, K. Zhang, X. Li, Y. Li, S. Zhao, A multi-objective dynamic mission- scheduling algorithm considering perturbations for earth observation satellites, Aerospace 11 (2024) 643. doi: 10.3390/aerospace11080643

    work page doi:10.3390/aerospace11080643 2024

  66. [72]

    L. Ren, X. Ning, Z. Wang, A competitive markov decision process model and a recursive reinforcement-learning algorithm for fairness scheduling of agile satellites, Computers & Industrial Engineering 169 (2022) 108242. doi: 10.1016/j.cie.2022.108242

    work page doi:10.1016/j.cie.2022.108242 2022

  67. [73]

    X. Li, C. Sun, H. Fan, J. Yang, Remote-sensing satellite mission scheduling optimisation method under dynamic mission priorities, Mathematics 12 (2024) 1704. doi: 10.3390/ math12111704

    2024

  68. [74]

    Cho, J.-H

    D.-H. Cho, J.-H. Kim, H.-L. Choi, J. Ahn, Optimization-based scheduling method for agile earth-observing satellite constellation, Journal of Aerospace Information Systems 15 (2018) 611–626. doi: 10.2514/1.I010620

    work page doi:10.2514/1.i010620 2018

  69. [75]

    Bonnet, M.-P

    J. Bonnet, M.-P. Gleizes, E. Kaddoum, S. Rainjonneau, G. Flandin, Multi-satellite mis- sion planning using a self-adaptive multi-agent system, in: 2015 IEEE 9th International Conference on Self-Adaptive and Self-Organizing Systems, IEEE, Cambridge, MA, USA, 2015, pp. 11–20. doi: 10.1109/SASO.2015.9. 68

    work page doi:10.1109/saso.2015.9 2015

  70. [76]

    Povéda, O

    G. Povéda, O. Regnier-Coudert, F. Teichteil-Königsbuch, G. Dupont, A. Arnold, J. Guerra, M. Picard, Evolutionary approaches to dynamic earth observation satel- lites mission planning under uncertainty, in: Proceedings of the Genetic and Evolu- tionary Computation Conference, ACM, Prague, Czech Republic, 2019, pp. 1302–1310. doi:10.1145/3321707.3321859

    work page doi:10.1145/3321707.3321859 2019

  71. [77]

    Cividanes, M

    F. Cividanes, M. Ferreira, F. Kucinskis, An extended HTN language for onboard planning and acting applied to a goal-based autonomous satellite, IEEE Aerospace and Electronic Systems Magazine 36 (2021) 32–50. doi: 10.1109/MAES.2021.3070857

    work page doi:10.1109/maes.2021.3070857 2021

  72. [78]

    Hilton, K

    S. Hilton, K. Thangavel, A. Gardi, R. Sabatini, Intelligent mission planning for au- tonomous distributed satellite systems, Acta Astronautica 225 (2024) 857–869. doi: 10. 1016/j.actaastro.2024.08.050

    2024

  73. [79]

    Z. Liu, W. Xiong, M. Xiong, A large-scale scheduling method for multiple agile optical satellites, Computer Modeling in Engineering & Sciences 136 (2023) 1143–1163. doi: 10. 32604/cmes.2023.025452

    work page arXiv 2023

  74. [80]

    IEEE Geosci Remote Sens Lett 14(8):1288–1292

    W. Huang, H. Wang, J. Wu, H. Hou, J. Li, Z. Li, Y. Song, A reinforcement learning- enhanced dung beetle optimization approach for agile earth observation satellite schedul- ing, IEEE Geoscience and Remote Sensing Letters 22 (2025) 1–5. doi: 10.1109/LGRS. 2025.3527925

    work page doi:10.1109/lgrs 2025

  75. [81]

    D. Eddy, M. Kochenderfer, Markov decision processes for multi-objective satellite task planning, in: 2020 IEEE Aerospace Conference, IEEE, Big Sky, MT, USA, 2020, pp. 1–12. doi: 10.1109/AERO47225.2020.9172258

    work page doi:10.1109/aero47225.2020.9172258 2020

  76. [82]

    H. Wang, W. Huang, S. Magnússon, T. Lindgren, R. Wang, Y. Song, A strategy fusion- based multiobjective optimization approach for agile earth observation satellite scheduling problem, IEEE Transactions on Geoscience and Remote Sensing 62 (2024) 1–14. doi: 10. 1109/TGRS.2024.3472749

    work page arXiv 2024

  77. [83]

    Secker, K

    J. Secker, K. Biron, D. Dessureault, P. Lamontagne, R. Rear, Automated collection planning for civilian and commercial satellite imagery, and definition and exploitation of the collection asset specification data structure, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 18 (2025) 9764–9797. doi: 10.1109/ JSTARS.2025.3555925

    work page arXiv 2025

  78. [84]

    Hosseinabadi, M

    S. Hosseinabadi, M. Ranjbar, S. Ramyar, M. Amel-Monirian, Scheduling a constellation of agile earth observation satellites with preemption, Journal of Quality Engineering and Production Optimization 2 (2017) 47–64. doi: 10.22070/JQEPO.2017.1776.1037

    work page doi:10.22070/jqepo.2017.1776.1037 2017

  79. [85]

    H. Li, Y. Liu, B. Deng, Y. Li, X. Li, Y. Li, T. Zhang, S. Zhao, A two-stage schedul- ing algorithm based on pointer network with attention mechanism for micro-nano earth observation satellite constellation, Chinese Journal of Aeronautics 38 (2025) 103567. doi:10.1016/j.cja.2025.103567. 69

    work page doi:10.1016/j.cja.2025.103567 2025

  80. [86]

    Herrmann, J

    A. Herrmann, J. V. Carneiro, H. Schaub, Reinforcement learning for the multi-satellite earth-observing scheduling problem, in: M. Sandnas, D. B. Spencer (Eds.), Proceedings of the 44th Annual American Astronautical Society Guidance, Navigation, and Control Conference, 2022, volume 179, Springer International Publishing, Cham, 2024, pp. 1351–

    2022

Showing first 80 references.