He3-Seeker: Robotic Information Planning for Lunar Helium-3 Distribution Mapping

Chengdeng Cao; Dong Li; Long Chen; Siyu Teng; Yang Gao; Yuchen Li; Yujie Zheng

arxiv: 2606.28746 · v1 · pith:7ZU2P2FZnew · submitted 2026-06-27 · 💻 cs.RO

He3-Seeker: Robotic Information Planning for Lunar Helium-3 Distribution Mapping

Dong Li , Yujie Zheng , Chengdeng Cao , Siyu Teng , Yuchen Li , Yang Gao , Long Chen This is my paper

Pith reviewed 2026-06-30 09:57 UTC · model grok-4.3

classification 💻 cs.RO

keywords helium-3 mappinglunar explorationrobotic information planningactive sensingresource distributionsimulation evaluationautonomous navigation

0 comments

The pith

He3-Seeker actively maps lunar helium-3 by directing a robot to drill, sample, and analyze at information-rich sites.

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

The paper establishes that an active robotic exploration system called He3-Seeker can map lunar helium-3 distributions more rapidly and with higher fidelity than traditional remote sensing approaches. It does so by formalizing the problem and implementing a framework that uses robotic information planning to select optimal locations for multi-point drilling, sampling, and on-site analysis. Evaluation relies on reference data derived from orbital measurements, and simulations confirm the method's effectiveness for resource exploration tasks.

Core claim

He3-Seeker is an active robotic exploration method for helium-3 distribution mapping. The framework is built on multi-point drilling, sampling, and in situ analysis, with robotic information planning guiding autonomous navigation and active sensing decisions. A method generates reference helium-3 distribution data from low-resolution orbital remote sensing measurements for evaluation, and simulation experiments show that the approach produces rapid and high-fidelity maps.

What carries the argument

Robotic information planning (RIP) that selects navigation and sensing actions to maximize information about helium-3 distribution.

If this is right

Provides a formal definition of the active helium-3 exploration problem.
Guides a robot through multi-point drilling, sampling, and in situ analysis using information planning.
Generates reference distribution data from orbital measurements for algorithm evaluation.
Demonstrates rapid and high-fidelity mapping in simulation experiments.

Where Pith is reading between the lines

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

The same planning approach could direct sampling for other lunar surface resources if adapted to their measurement signatures.
Deployment on physical rovers would need to account for terrain mobility limits and sensor noise not present in the simulations.
Public release of the code allows others to test the method against new orbital data sets or modified planning objectives.

Load-bearing premise

The reference helium-3 distribution data generated from low-resolution orbital remote sensing measurements is accurate enough to serve as ground truth for evaluating the active exploration algorithm.

What would settle it

Direct helium-3 concentration measurements from a future landed mission that differ substantially from the distributions produced by He3-Seeker in the same regions would falsify the high-fidelity claim.

Figures

Figures reproduced from arXiv: 2606.28746 by Chengdeng Cao, Dong Li, Long Chen, Siyu Teng, Yang Gao, Yuchen Li, Yujie Zheng.

**Figure 1.** Figure 1: Schematic Diagram of Robotic Lunar Helium-3 Distribution Exploration. The exploration rover, equipped with an integrated drilling-and-sampling payload alongside an onboard compositional analysis system, addresses a critical question: how to dynamically map the high-precision dense spatial distribution of helium-3 within the target region within a significantly shortened timeframe? relies heavily on indire… view at source ↗

**Figure 2.** Figure 2: Overview of the He3-Seeker Framework. (Top) The systemic architecture of He3-Seeker, which guides a rover equipped with single-point helium-3 measurement capability to navigate and conduct multi-point sampling for dense lunar helium-3 distribution mapping. (Bottom) The generation of a dense lunar helium-3 reference map utilized for algorithmic evaluation and testing. sampling locations {x1, x2, . . . , xN … view at source ↗

**Figure 3.** Figure 3: The reference data of helium-3 distribution and the [PITH_FULL_IMAGE:figures/full_fig_p005_3.png] view at source ↗

**Figure 5.** Figure 5: Path planning results for the two scenarios using [PITH_FULL_IMAGE:figures/full_fig_p006_5.png] view at source ↗

**Figure 4.** Figure 4: Comparison between RRT* (ours) and RRT (baseline) [PITH_FULL_IMAGE:figures/full_fig_p006_4.png] view at source ↗

read the original abstract

Lunar helium-3 is a highly valuable strategic resource, pivotal to the advancement of both deep-space exploration and space mining. Existing lunar helium-3 exploration methodologies rely primarily on indirect measurements via remote sensing, which are often characterized by limited precision, low reliability, and insufficient spatial resolution. In this paper, we introduce He3-Seeker, an active robotic exploration method for helium-3 distribution mapping. First, we provide a formal definition of the active helium-3 exploration problem. Subsequently, we developed the He3-Seeker framework, which is conceptually based on multi-point drilling, sampling, and in situ analysis. In particular, we use robotic information planning (RIP) to guide autonomous robot navigation and active sensing. Additionally, to thoroughly evaluate the proposed algorithm, we introduce a reliable method for generating reference data of lunar helium-3 distribution based on low-resolution orbital remote sensing measurements. Simulation experiments verify that He3-Seeker achieves both rapid and high-fidelity mapping of helium-3 distribution, providing a reliable solution for resource exploration tasks. Our code and simulation environment will be publicly accessible at https://github.com/OpenSpace-Lab/He3-Seeker.

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.

Desk Editor's Note private letter to a colleague

This applies robotic information planning to lunar He-3 mapping with a new reference-data generator, but the simulation claims rest on unvalidated synthetic ground truth.

read the letter

The main takeaway is that He3-Seeker takes existing robotic information planning methods and applies them to active sensing for helium-3 on the moon, adding a formal problem definition and a procedure to turn low-resolution orbital data into reference maps for simulation testing.

What stands out as new is the named framework and the explicit problem formulation around multi-point drilling and in-situ analysis. The plan to release code and the simulation environment is useful; it gives others a starting point to reproduce or adapt the planner. The overall pipeline from remote sensing to robot navigation is laid out clearly enough for someone already working in planetary robotics.

The evaluation is the weaker part. The reference helium-3 distributions are generated from the paper's own method applied to orbital measurements, with no cross-check against independent solar-wind models, regolith maps, or other published sources. That means the reported rapid and high-fidelity results are only relative to this internal synthetic field. If the generation step introduces systematic bias, the planner's performance numbers lose some of their weight. The abstract does not include specific error metrics or baseline comparisons, so the full paper would need to show those numbers and any sensitivity checks.

This paper is aimed at researchers in space robotics or in-situ resource utilization who want a concrete example of information-driven exploration. A reader already familiar with RIP would see a domain application rather than a new algorithm, but the reproducibility step makes it worth looking at. It deserves peer review because the application is timely and the code release lowers the barrier for follow-up work, even if the validation needs tightening.

Referee Report

2 major / 1 minor

Summary. The paper introduces He3-Seeker, an active robotic exploration framework for mapping lunar helium-3 distribution. It formally defines the active exploration problem, develops a robotic information planning (RIP) approach based on multi-point drilling, sampling, and in-situ analysis to guide autonomous navigation and sensing, and presents a method to generate reference helium-3 distribution data from low-resolution orbital remote sensing measurements. Simulation experiments are reported to verify that the method achieves rapid and high-fidelity mapping, with code and the simulation environment to be released publicly.

Significance. If the central claims hold after addressing validation concerns, the work could offer a practical active-sensing approach for in-situ lunar resource mapping that improves on passive remote sensing. The commitment to public code release supports reproducibility and is a clear strength.

major comments (2)

[evaluation section] Reference data generation procedure (evaluation section): the method for producing reference helium-3 maps from low-resolution orbital data is presented without cross-validation against independent sources such as published solar-wind flux models or regolith-thickness maps. Because the simulation fidelity metrics are computed only relative to this synthetic field, the claim that experiments verify 'high-fidelity' mapping rests on an untested assumption that is load-bearing for the verification result.
[simulation experiments section] Simulation experiments section: the abstract asserts verification of rapid and high-fidelity mapping, yet the provided description supplies no quantitative error metrics, convergence rates, or explicit formulation of the RIP planning objective (e.g., information gain versus cost). Without these details the strength of the empirical support cannot be assessed.

minor comments (1)

[problem definition] Notation for the active exploration problem definition should be introduced with explicit symbols and constraints before the RIP algorithm description to improve readability.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive comments on the evaluation and simulation sections. We address each point below and will revise the manuscript accordingly to strengthen the validation and empirical details.

read point-by-point responses

Referee: [evaluation section] Reference data generation procedure (evaluation section): the method for producing reference helium-3 maps from low-resolution orbital data is presented without cross-validation against independent sources such as published solar-wind flux models or regolith-thickness maps. Because the simulation fidelity metrics are computed only relative to this synthetic field, the claim that experiments verify 'high-fidelity' mapping rests on an untested assumption that is load-bearing for the verification result.

Authors: We agree that the absence of explicit cross-validation is a limitation in the current presentation. The reference data generation extrapolates helium-3 abundance from low-resolution orbital measurements using physical models of solar wind implantation and regolith properties. In revision, we will add comparisons against published solar-wind flux models and available regolith-thickness maps to provide independent validation of the synthetic field, thereby supporting the fidelity claims with additional evidence. revision: yes
Referee: [simulation experiments section] Simulation experiments section: the abstract asserts verification of rapid and high-fidelity mapping, yet the provided description supplies no quantitative error metrics, convergence rates, or explicit formulation of the RIP planning objective (e.g., information gain versus cost). Without these details the strength of the empirical support cannot be assessed.

Authors: We acknowledge that the simulation experiments section requires more explicit quantitative reporting. The RIP objective is defined as maximizing expected information gain (via entropy reduction on the helium-3 distribution) while penalizing drilling and navigation costs, but this formulation and the associated metrics were not detailed sufficiently in the experiments. In the revision, we will include the mathematical formulation of the planning objective, RMSE and other error metrics between the estimated and reference maps, and convergence behavior (e.g., mapping fidelity vs. number of samples) to enable proper evaluation of the results. revision: yes

Circularity Check

0 steps flagged

No significant circularity in derivation or verification chain

full rationale

The paper defines an active exploration problem, introduces the He3-Seeker RIP-based planner, and separately introduces a reference-data generation procedure from orbital measurements. The simulation verification compares planner output to this reference, but the provided text contains no equations, fitted parameters, or self-citations that reduce the reported mapping performance to the planner inputs or to the reference generator by construction. The reference method is presented as an independent evaluation tool rather than a fitted or self-referential quantity, so the central claim remains self-contained against the stated inputs.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Abstract-only review supplies no explicit free parameters, axioms, or invented entities; the reference-data generation step is treated as an unexamined modeling choice.

pith-pipeline@v0.9.1-grok · 5753 in / 969 out tokens · 25205 ms · 2026-06-30T09:57:03.133365+00:00 · methodology

discussion (0)

Reference graph

Works this paper leans on

22 extracted references · 1 canonical work pages

[1]

China’s present and future lunar exploration program,

C. Li, C. Wang, Y . Wei, and Y . Lin, “China’s present and future lunar exploration program,”Science, vol. 365, no. 6450, pp. 238–239, 2019

2019
[2]

The artemis program: An overview of nasa’s activ- ities to return humans to the moon,

M. Smith, D. Craig, N. Herrmann, E. Mahoney, J. Krezel, N. McIntyre, and K. Goodliff, “The artemis program: An overview of nasa’s activ- ities to return humans to the moon,” inIEEE Aerospace Conference, 2020, pp. 1–10

2020
[3]

Quantitative estimation of helium-3 spatial distribution in the lunar regolith layer,

W. Fa and Y .-Q. Jin, “Quantitative estimation of helium-3 spatial distribution in the lunar regolith layer,”Icarus, vol. 190, no. 1, pp. 15–23, 2007

2007
[4]

Lunar helium-3 fuel for nuclear fusion: Technology, economics, and resources,

T. Simko and M. Gray, “Lunar helium-3 fuel for nuclear fusion: Technology, economics, and resources,”World Future Review, vol. 6, no. 2, pp. 158–171, 2014

2014
[5]

Moon- based ground penetrating radar derivation of the helium-3 reservoir in the regolith at the chang’e-3 landing site,

C. Ding, Q. Li, J. Xu, Z. Lei, J. Li, Y . Su, and S. Huang, “Moon- based ground penetrating radar derivation of the helium-3 reservoir in the regolith at the chang’e-3 landing site,”IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 16, pp. 2764–2776, 2023

2023
[6]

The apollo swc experiment: results, conclusions, consequences,

J. Geiss, F. B ¨uhler, H. Cerutti, P. Eberhardt, C. Filleux, J. Meister, and P. Signer, “The apollo swc experiment: results, conclusions, consequences,”Space Science Reviews, vol. 110, no. 3, pp. 307–335, 2004

2004
[7]

Major lunar crustal terranes: Surface expressions and crust-mantle origins,

B. L. Jolliff, J. J. Gillis, L. A. Haskin, R. L. Korotev, and M. A. Wieczorek, “Major lunar crustal terranes: Surface expressions and crust-mantle origins,”Journal of Geophysical Research: Planets, vol. 105, no. E2, pp. 4197–4216, 2000

2000
[8]

He, ne, and ar isotope systematics in chang’e-5 plagioclase reveal diffusive loss and reirradiation processes,

X. Zhang, F. Su, G. Avice, D. V . Bekaert, T. Obase, Y . Otsuki, F. M. Stuart, Y . Zhang, J. Nie, X. Liet al., “He, ne, and ar isotope systematics in chang’e-5 plagioclase reveal diffusive loss and reirradiation processes,”Earth and Planetary Science Letters, vol. 671, p. 119666, 2025

2025
[9]

The viper mission, a resource-mapping mission on another celestial body,

K. E. Smith, A. Colaprete, D. Lim, and D. Andrews, “The viper mission, a resource-mapping mission on another celestial body,” in SRR XXII MEETING Colorado School of Mines, 2022

2022
[10]

Simulated real-time lunar volatiles prospecting with a rover-borne neutron spectrometer,

R. C. Elphic, J. L. Heldmann, M. M. Marinova, A. Colaprete, E. L. Fritzler, R. E. McMurray, S. Morse, T. L. Roush, C. R. Stoker, M. C. Deanset al., “Simulated real-time lunar volatiles prospecting with a rover-borne neutron spectrometer,”Advances in Space Research, vol. 55, no. 10, pp. 2438–2450, 2015

2015
[11]

Lunar iron and titanium abundance algorithms based on final processing of clementine ultraviolet-visible images,

P. G. Lucey, D. T. Blewett, and B. L. Jolliff, “Lunar iron and titanium abundance algorithms based on final processing of clementine ultraviolet-visible images,”Journal of Geophysical Research: Planets, vol. 105, no. E8, pp. 20 297–20 305, 2000

2000
[12]

Global elemental maps of the moon: The lunar prospector gamma-ray spectrometer,

D. Lawrence, W. Feldman, B. Barraclough, A. Binder, R. Elphic, S. Maurice, and D. Thomsen, “Global elemental maps of the moon: The lunar prospector gamma-ray spectrometer,”Science, vol. 281, no. 5382, pp. 1484–1489, 1998

1998
[13]

Lunar penetrating radar onboard the chang’e-3 mission,

G.-Y . Fang, B. Zhou, Y .-C. Ji, Q.-Y . Zhang, S.-X. Shen, Y .-X. Li, H.-F. Guan, C.-J. Tang, Y .-Z. Gao, W. Luet al., “Lunar penetrating radar onboard the chang’e-3 mission,”Research in Astronomy and Astrophysics, vol. 14, no. 12, pp. 1607–1622, 2014

2014
[14]

Ak: Attentive kernel for informa- tion gathering,

W. Chen, R. Khardon, and L. Liu, “Ak: Attentive kernel for informa- tion gathering,” inRobotics: Science and Systems (RSS), 2022

2022
[15]

Poam: probabilistic online attentive mapping for efficient robotic information gathering,

W. Chen, L. Liu, and R. Khardon, “Poam: probabilistic online attentive mapping for efficient robotic information gathering,” inRobotics: Science and Systems (RSS), 2024

2024
[16]

Multi-agent off-world exploration for sparse evidence discovery via gaussian belief mapping and dual-domain coverage,

Z. Qiao, T. Hu, T.-M. Nguyen, and S. Yuan, “Multi-agent off-world exploration for sparse evidence discovery via gaussian belief mapping and dual-domain coverage,”arXiv preprint arXiv:2603.07650, 2026

work page arXiv 2026
[17]

Informative path planning for scalar dy- namic reconstruction using coregionalized gaussian processes and a spatiotemporal kernel,

L. Booth and S. Carpin, “Informative path planning for scalar dy- namic reconstruction using coregionalized gaussian processes and a spatiotemporal kernel,” inIEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2023, pp. 8112–8119

2023
[18]

Robotic active information gathering for spatial field reconstruction with rapidly-exploring ran- dom trees and online learning of gaussian processes,

A. Viseras, D. Shutin, and L. Merino, “Robotic active information gathering for spatial field reconstruction with rapidly-exploring ran- dom trees and online learning of gaussian processes,”Sensors, vol. 19, no. 5, p. 1016, 2019

2019
[19]

The compositions of the lunar crust and upper mantle: Spectral analysis of the inner rings of lunar impact basins,

M. Lemelin, P. G. Lucey, K. Miljkovi ´c, L. R. Gaddis, T. Hare, and M. Ohtake, “The compositions of the lunar crust and upper mantle: Spectral analysis of the inner rings of lunar impact basins,”Planetary and Space Science, vol. 165, pp. 230–243, 2019

2019
[20]

Mapping the feo and tio2 content of the lunar surface with multispectral imagery,

P. G. Lucey, D. T. Blewett, and B. R. Hawke, “Mapping the feo and tio2 content of the lunar surface with multispectral imagery,”Journal of Geophysical Research: Planets, vol. 103, no. E2, pp. 3679–3699, 1998

1998
[21]

Sampling-based algorithms for optimal motion planning,

S. Karaman and E. Frazzoli, “Sampling-based algorithms for optimal motion planning,”The International Journal of Robotics Research, vol. 30, no. 7, pp. 846–894, 2011

2011
[22]

Randomized kinodynamic plan- ning,

S. M. LaValle and J. J. Kuffner Jr, “Randomized kinodynamic plan- ning,”The International Journal of Robotics Research, vol. 20, no. 5, pp. 378–400, 2001

2001

[1] [1]

China’s present and future lunar exploration program,

C. Li, C. Wang, Y . Wei, and Y . Lin, “China’s present and future lunar exploration program,”Science, vol. 365, no. 6450, pp. 238–239, 2019

2019

[2] [2]

The artemis program: An overview of nasa’s activ- ities to return humans to the moon,

M. Smith, D. Craig, N. Herrmann, E. Mahoney, J. Krezel, N. McIntyre, and K. Goodliff, “The artemis program: An overview of nasa’s activ- ities to return humans to the moon,” inIEEE Aerospace Conference, 2020, pp. 1–10

2020

[3] [3]

Quantitative estimation of helium-3 spatial distribution in the lunar regolith layer,

W. Fa and Y .-Q. Jin, “Quantitative estimation of helium-3 spatial distribution in the lunar regolith layer,”Icarus, vol. 190, no. 1, pp. 15–23, 2007

2007

[4] [4]

Lunar helium-3 fuel for nuclear fusion: Technology, economics, and resources,

T. Simko and M. Gray, “Lunar helium-3 fuel for nuclear fusion: Technology, economics, and resources,”World Future Review, vol. 6, no. 2, pp. 158–171, 2014

2014

[5] [5]

Moon- based ground penetrating radar derivation of the helium-3 reservoir in the regolith at the chang’e-3 landing site,

C. Ding, Q. Li, J. Xu, Z. Lei, J. Li, Y . Su, and S. Huang, “Moon- based ground penetrating radar derivation of the helium-3 reservoir in the regolith at the chang’e-3 landing site,”IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 16, pp. 2764–2776, 2023

2023

[6] [6]

The apollo swc experiment: results, conclusions, consequences,

J. Geiss, F. B ¨uhler, H. Cerutti, P. Eberhardt, C. Filleux, J. Meister, and P. Signer, “The apollo swc experiment: results, conclusions, consequences,”Space Science Reviews, vol. 110, no. 3, pp. 307–335, 2004

2004

[7] [7]

Major lunar crustal terranes: Surface expressions and crust-mantle origins,

B. L. Jolliff, J. J. Gillis, L. A. Haskin, R. L. Korotev, and M. A. Wieczorek, “Major lunar crustal terranes: Surface expressions and crust-mantle origins,”Journal of Geophysical Research: Planets, vol. 105, no. E2, pp. 4197–4216, 2000

2000

[8] [8]

He, ne, and ar isotope systematics in chang’e-5 plagioclase reveal diffusive loss and reirradiation processes,

X. Zhang, F. Su, G. Avice, D. V . Bekaert, T. Obase, Y . Otsuki, F. M. Stuart, Y . Zhang, J. Nie, X. Liet al., “He, ne, and ar isotope systematics in chang’e-5 plagioclase reveal diffusive loss and reirradiation processes,”Earth and Planetary Science Letters, vol. 671, p. 119666, 2025

2025

[9] [9]

The viper mission, a resource-mapping mission on another celestial body,

K. E. Smith, A. Colaprete, D. Lim, and D. Andrews, “The viper mission, a resource-mapping mission on another celestial body,” in SRR XXII MEETING Colorado School of Mines, 2022

2022

[10] [10]

Simulated real-time lunar volatiles prospecting with a rover-borne neutron spectrometer,

R. C. Elphic, J. L. Heldmann, M. M. Marinova, A. Colaprete, E. L. Fritzler, R. E. McMurray, S. Morse, T. L. Roush, C. R. Stoker, M. C. Deanset al., “Simulated real-time lunar volatiles prospecting with a rover-borne neutron spectrometer,”Advances in Space Research, vol. 55, no. 10, pp. 2438–2450, 2015

2015

[11] [11]

Lunar iron and titanium abundance algorithms based on final processing of clementine ultraviolet-visible images,

P. G. Lucey, D. T. Blewett, and B. L. Jolliff, “Lunar iron and titanium abundance algorithms based on final processing of clementine ultraviolet-visible images,”Journal of Geophysical Research: Planets, vol. 105, no. E8, pp. 20 297–20 305, 2000

2000

[12] [12]

Global elemental maps of the moon: The lunar prospector gamma-ray spectrometer,

D. Lawrence, W. Feldman, B. Barraclough, A. Binder, R. Elphic, S. Maurice, and D. Thomsen, “Global elemental maps of the moon: The lunar prospector gamma-ray spectrometer,”Science, vol. 281, no. 5382, pp. 1484–1489, 1998

1998

[13] [13]

Lunar penetrating radar onboard the chang’e-3 mission,

G.-Y . Fang, B. Zhou, Y .-C. Ji, Q.-Y . Zhang, S.-X. Shen, Y .-X. Li, H.-F. Guan, C.-J. Tang, Y .-Z. Gao, W. Luet al., “Lunar penetrating radar onboard the chang’e-3 mission,”Research in Astronomy and Astrophysics, vol. 14, no. 12, pp. 1607–1622, 2014

2014

[14] [14]

Ak: Attentive kernel for informa- tion gathering,

W. Chen, R. Khardon, and L. Liu, “Ak: Attentive kernel for informa- tion gathering,” inRobotics: Science and Systems (RSS), 2022

2022

[15] [15]

Poam: probabilistic online attentive mapping for efficient robotic information gathering,

W. Chen, L. Liu, and R. Khardon, “Poam: probabilistic online attentive mapping for efficient robotic information gathering,” inRobotics: Science and Systems (RSS), 2024

2024

[16] [16]

Multi-agent off-world exploration for sparse evidence discovery via gaussian belief mapping and dual-domain coverage,

Z. Qiao, T. Hu, T.-M. Nguyen, and S. Yuan, “Multi-agent off-world exploration for sparse evidence discovery via gaussian belief mapping and dual-domain coverage,”arXiv preprint arXiv:2603.07650, 2026

work page arXiv 2026

[17] [17]

Informative path planning for scalar dy- namic reconstruction using coregionalized gaussian processes and a spatiotemporal kernel,

L. Booth and S. Carpin, “Informative path planning for scalar dy- namic reconstruction using coregionalized gaussian processes and a spatiotemporal kernel,” inIEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2023, pp. 8112–8119

2023

[18] [18]

Robotic active information gathering for spatial field reconstruction with rapidly-exploring ran- dom trees and online learning of gaussian processes,

A. Viseras, D. Shutin, and L. Merino, “Robotic active information gathering for spatial field reconstruction with rapidly-exploring ran- dom trees and online learning of gaussian processes,”Sensors, vol. 19, no. 5, p. 1016, 2019

2019

[19] [19]

The compositions of the lunar crust and upper mantle: Spectral analysis of the inner rings of lunar impact basins,

M. Lemelin, P. G. Lucey, K. Miljkovi ´c, L. R. Gaddis, T. Hare, and M. Ohtake, “The compositions of the lunar crust and upper mantle: Spectral analysis of the inner rings of lunar impact basins,”Planetary and Space Science, vol. 165, pp. 230–243, 2019

2019

[20] [20]

Mapping the feo and tio2 content of the lunar surface with multispectral imagery,

P. G. Lucey, D. T. Blewett, and B. R. Hawke, “Mapping the feo and tio2 content of the lunar surface with multispectral imagery,”Journal of Geophysical Research: Planets, vol. 103, no. E2, pp. 3679–3699, 1998

1998

[21] [21]

Sampling-based algorithms for optimal motion planning,

S. Karaman and E. Frazzoli, “Sampling-based algorithms for optimal motion planning,”The International Journal of Robotics Research, vol. 30, no. 7, pp. 846–894, 2011

2011

[22] [22]

Randomized kinodynamic plan- ning,

S. M. LaValle and J. J. Kuffner Jr, “Randomized kinodynamic plan- ning,”The International Journal of Robotics Research, vol. 20, no. 5, pp. 378–400, 2001

2001