pith. sign in

arxiv: 2602.07924 · v2 · submitted 2026-02-08 · 💻 cs.RO · cs.AI· math.OC

Optimized Human-Robot Co-Dispatch Planning for Petro-Site Surveillance under Varying Criticalities

Nur Ahmad Khatim , Mansur Arief This is my paper

Pith reviewed 2026-05-16 06:21 UTC · model grok-4.3

classification 💻 cs.RO cs.AImath.OC
keywords human-robot teamingfacility locationpetroleum infrastructuresurveillance planningautonomous systemscritical infrastructure protection
0
0 comments X

The pith

Human-robot supervision ratios can shift from 1:3 to 1:10 in petroleum site planning while preserving full critical infrastructure coverage and cutting costs.

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

The paper formulates a new variant of the facility location problem that plans the placement of human-robot teams for surveillance at petroleum facilities. It layers in constraints for different levels of site criticality, fixed ratios of human oversight to robot units, and minimum usage requirements for the teams. Across scenarios that move from conservative to more autonomous operations, the optimized plans show large cost drops with no sacrifice in complete coverage. Small instances are solved exactly, while a fast heuristic handles bigger cases. The work positions careful co-dispatch planning as essential for reliable yet affordable protection of critical sites.

Core claim

The Human-Robot Co-Dispatch Facility Location Problem (HRCD-FLP) is defined as a capacitated facility location model that adds tiered criticality classes for infrastructure, hard human-robot supervision ratio limits, and minimum utilization rules. When command-center selections are optimized under three technology-maturity scenarios, relaxing the supervision ratio from 1:3 to 1:10 produces marked cost reductions while still covering every critical petroleum site.

What carries the argument

The Human-Robot Co-Dispatch Facility Location Problem (HRCD-FLP), a capacitated facility-location formulation that enforces tiered criticality, supervision-ratio ceilings, and minimum utilization on human-robot teams.

If this is right

  • Command-center locations chosen under higher autonomy deliver the same coverage at substantially lower total cost.
  • Exact solvers give both optimal cost and short run times on small problem sizes.
  • The heuristic returns usable plans for large instances in under three minutes.
  • Systems-level optimization of human-robot ratios supports both lower expense and sustained mission reliability.

Where Pith is reading between the lines

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

  • The same structure could be adapted to other critical-infrastructure domains by redefining the criticality tiers and utilization floors.
  • Real incident logs could be used to test whether the assumed ratios actually prevent coverage gaps during live operations.
  • Adding time-varying threat levels would let the model decide when to increase human involvement dynamically.

Load-bearing premise

The selected supervision ratios and criticality tiers match the real limits that operators face in the field.

What would settle it

Field deployment of the 1:10-ratio plan followed by direct measurement of whether every critical site remains continuously covered and response times stay within acceptable bounds.

Figures

Figures reproduced from arXiv: 2602.07924 by Mansur Arief, Nur Ahmad Khatim.

Figure 1
Figure 1. Figure 1: Conceptual architecture of the HRCD-FLP framework. [PITH_FULL_IMAGE:figures/full_fig_p003_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Distribution of Command Center Levels across Scenarios [PITH_FULL_IMAGE:figures/full_fig_p008_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Facility Resource Allocation (Exact Method) [PITH_FULL_IMAGE:figures/full_fig_p008_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Facility Resource Allocation (Heuristic Method) [PITH_FULL_IMAGE:figures/full_fig_p008_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Conservative Scenario Breakdown Method: Exact Open Facilities: 4/15 Demand Sites: 50 Total Robot (⬢): 229 Total Human (◉): 127 ⬢12 ◉7 ⬢74 ◉40 ⬢92 ◉40 ⬢51 ◉40 Method: Heuristic Open Facilities: 4/15 Demand Sites: 50 Total Robot (⬢): 229 Total Human (◉): 127 Unused Candidate High Level CC Medium Level CC Low Level CC High-Critical Site Standard Site Low-Critical Site ⬢53 ◉32 ⬢53 ◉20 ⬢73 ◉39 ⬢50 ◉36 [PITH_FU… view at source ↗
Figure 6
Figure 6. Figure 6: Balanced Scenario Breakdown Method: Exact Open Facilities: 3/15 Demand Sites: 50 Total Robot (⬢): 256 Total Human (◉): 98 ⬢40 ◉20 ⬢125 ◉39 ⬢91 ◉39 Method: Heuristic Open Facilities: 4/15 Demand Sites: 50 Total Robot (⬢): 258 Total Human (◉): 98 Unused Candidate High Level CC Medium Level CC Low Level CC High-Critical Site Standard Site Low-Critical Site ⬢51 ◉16 ⬢70 ◉13 ⬢83 ◉35 ⬢54 ◉34 [PITH_FULL_IMAGE:fig… view at source ↗
Figure 7
Figure 7. Figure 7: Future Scenario Breakdown [PITH_FULL_IMAGE:figures/full_fig_p009_7.png] view at source ↗
read the original abstract

Securing petroleum infrastructure requires balancing autonomous system efficiency with human judgment for threat escalation, a challenge unaddressed by classical facility location models assuming homogeneous resources. This paper formulates the Human-Robot Co-Dispatch Facility Location Problem (HRCD-FLP), a capacitated facility location variant incorporating tiered infrastructure criticality, human-robot supervision ratio constraints, and minimum utilization requirements. We evaluate command center selection across three technology maturity scenarios. Results show transitioning from conservative (1:3 human-robot supervision) to future autonomous operations (1:10) yields significant cost reduction while maintaining complete critical infrastructure coverage. For small problems, exact methods dominate in both cost and computation time; for larger problems, the proposed heuristic achieves feasible solutions in under 3 minutes with approximately 14% optimality gap where comparison is possible. From systems perspective, our work demonstrate that optimized planning for human-robot teaming is key to achieve both cost-effective and mission-reliable deployments.

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

3 major / 1 minor

Summary. The manuscript formulates the Human-Robot Co-Dispatch Facility Location Problem (HRCD-FLP), a capacitated facility location variant that incorporates tiered infrastructure criticality, human-robot supervision ratio constraints (1:3 conservative vs. 1:10 autonomous), and minimum utilization requirements. It evaluates command center selection for petroleum site surveillance across three technology maturity scenarios, claiming that the transition from 1:3 to 1:10 supervision yields significant cost reductions while maintaining complete critical infrastructure coverage. Exact methods are reported to dominate for small problems, while a proposed heuristic solves larger instances in under 3 minutes with an approximate 14% optimality gap.

Significance. If the modeling assumptions and computational results hold under validation, the work offers a practical optimization framework for human-robot teaming in critical infrastructure surveillance. It quantifies cost benefits of increased autonomy while preserving coverage guarantees, which could inform deployment planning in the energy sector and highlight the value of co-dispatch models over homogeneous resource assumptions.

major comments (3)
  1. [Problem formulation] Problem formulation section: The supervision ratios (1:3 and 1:10) and tiered criticality levels are used as hard constraints without any cited empirical source (e.g., operational logs, regulatory standards, or expert elicitation), sensitivity analysis, or justification; this directly underpins the central cost-reduction and 100% coverage claims, so the results risk being artifacts of unvalidated parameter choices.
  2. [Results] Results and abstract: The reported 14% optimality gap for the heuristic is stated at a high level with no accompanying details on instance sizes, exact solver baselines, gap calculation method, or feasibility under varying ratios; without this, the performance claims for larger problems cannot be assessed.
  3. [Model description] Model description: No explicit mathematical formulation (objective function, decision variables, or full constraint set for HRCD-FLP) is provided in the abstract or summary sections, preventing verification that the supervision and utilization constraints indeed guarantee complete coverage independent of the chosen ratios.
minor comments (1)
  1. [Abstract] Abstract: Minor grammatical issue ('our work demonstrate' should read 'our work demonstrates').

Simulated Author's Rebuttal

3 responses · 0 unresolved

We thank the referee for their thorough review and constructive comments on our manuscript. We have carefully considered each point and made revisions to strengthen the paper. Below, we provide point-by-point responses to the major comments.

read point-by-point responses

  1. Referee: [Problem formulation] Problem formulation section: The supervision ratios (1:3 and 1:10) and tiered criticality levels are used as hard constraints without any cited empirical source (e.g., operational logs, regulatory standards, or expert elicitation), sensitivity analysis, or justification; this directly underpins the central cost-reduction and 100% coverage claims, so the results risk being artifacts of unvalidated parameter choices.

    Authors: The supervision ratios are intended to represent different technology maturity scenarios for human-robot teaming, with 1:3 reflecting current conservative practices and 1:10 projecting future autonomous capabilities. While we did not cite specific empirical sources in the original submission, in the revised manuscript we have added citations to relevant industry standards and reports on surveillance automation (such as those from the American Petroleum Institute and robotics deployment studies). Additionally, we have included a sensitivity analysis on the supervision ratios to show that the cost reduction and coverage claims hold across a range of values. revision: yes

  2. Referee: [Results] Results and abstract: The reported 14% optimality gap for the heuristic is stated at a high level with no accompanying details on instance sizes, exact solver baselines, gap calculation method, or feasibility under varying ratios; without this, the performance claims for larger problems cannot be assessed.

    Authors: We agree that more details are required for proper assessment. The revised results section now includes a detailed table with instance characteristics (e.g., number of petroleum sites ranging from 50 to 500, command center candidates), the baseline exact solver (Gurobi 10.0), the optimality gap calculation method (as (heuristic objective - best known solution)/best known solution), and separate results for both supervision ratios. This demonstrates that the heuristic provides feasible solutions with gaps around 14% for large instances solvable by the exact method within time limits. revision: yes

  3. Referee: [Model description] Model description: No explicit mathematical formulation (objective function, decision variables, or full constraint set for HRCD-FLP) is provided in the abstract or summary sections, preventing verification that the supervision and utilization constraints indeed guarantee complete coverage independent of the chosen ratios.

    Authors: The full mathematical model is presented in Section 3 of the manuscript, with the objective function minimizing the weighted sum of facility opening and operational costs, binary variables for opening command centers and assigning sites, and constraints enforcing coverage of all critical sites, supervision ratio limits, and minimum utilization. To improve accessibility, we have revised the abstract to briefly outline the key constraints and added a pointer to the model section in the introduction summary. The coverage constraint is independent of the supervision ratio, which only scales the human resource requirements. revision: partial

Circularity Check

0 steps flagged

No circularity: cost results are direct outputs of optimization under explicit input parameters

full rationale

The HRCD-FLP is formulated as a standard capacitated facility location model whose supervision ratios (1:3 vs 1:10) and tiered criticality levels are declared as hard constraints and demand weights. The reported cost reductions and 100% coverage are obtained by solving the resulting integer program (or heuristic) for those fixed parameter values across scenarios. This is a forward computation, not a derivation that reduces to the inputs by construction. No self-definitional equations, fitted inputs renamed as predictions, or load-bearing self-citations appear in the derivation chain. The model is self-contained against its stated assumptions.

Axiom & Free-Parameter Ledger

1 free parameters · 1 axioms · 0 invented entities

The central claim rests on the validity of the HRCD-FLP formulation and the three technology-maturity scenarios; supervision ratios function as scenario inputs rather than data-fitted parameters.

free parameters (1)
  • Human-robot supervision ratios
    Defined as 1:3 for conservative and 1:10 for future scenarios to evaluate cost impacts; treated as exogenous inputs.
axioms (1)
  • domain assumption Command center selection can be modeled as a capacitated facility location problem with added human-robot constraints
    Core modeling choice underlying the HRCD-FLP definition.

pith-pipeline@v0.9.0 · 5465 in / 1323 out tokens · 35992 ms · 2026-05-16T06:21:13.462300+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

36 extracted references · 36 canonical work pages

  1. [1]

    Oil and gas infrastructure: A technical overview,

    T. C. Coburn, “Oil and gas infrastructure: A technical overview,”The Oxford Handbook of Energy Politics, pp. 99–124, 2020

    work page 2020

  2. [2]

    Transporting oil and gas: Us infrastructure challenges,

    A. B. Klass and D. Meinhardt, “Transporting oil and gas: Us infrastructure challenges,”Iowa L. Rev., vol. 100, p. 947, 2014

    work page 2014

  3. [3]

    Dietl,The Global Game of Oil Pipelines

    G. Dietl,The Global Game of Oil Pipelines. Routledge India, 2021

    work page 2021

  4. [4]

    Main security threats to oil and gas infrastructure,

    O. Pashchenko, V . Khomenko, B. Ratov, Y . Koroviaka, and V . Rastsvi- etaiev, “Main security threats to oil and gas infrastructure,” inCritical Infrastructure Protection in Response to Terrorist Attacks. IOS Press, 2024, pp. 109–116

    work page 2024

  5. [5]

    Securing oil and gas infrastructure,

    S. Bajpai and J. Gupta, “Securing oil and gas infrastructure,”Journal of Petroleum Science and Engineering, vol. 55, no. 1-2, pp. 174–186, 2007

    work page 2007

  6. [6]

    Cybersecurity challenges in the offshore oil and gas industry: An industrial cyber-physical systems (icps) perspective,

    A. S. Mohammed, P. Reinecke, P. Burnap, O. Rana, and E. Anthi, “Cybersecurity challenges in the offshore oil and gas industry: An industrial cyber-physical systems (icps) perspective,”ACM Transac- tions on Cyber-Physical Systems (TCPS), vol. 6, no. 3, pp. 1–27, 2022

    work page 2022

  7. [7]

    The state of ransomware in critical infrastructure 2024,

    Sophos, “The state of ransomware in critical infrastructure 2024,” Sophos News Blog, July 2024. [Online]. Available: https://www.sophos.com/en-us/blog/the-state-of-ransomware-in-criti cal-infrastructure-2024

    work page 2024

  8. [8]

    A system for human-robot teaming through end-user programming and shared autonomy,

    M. Hagenow, E. Senft, R. Radwin, M. Gleicher, M. Zinn, and B. Mutlu, “A system for human-robot teaming through end-user programming and shared autonomy,” inProceedings of the 2024 ACM/IEEE International Conference on Human-Robot Interaction, 2024, pp. 231–239

    work page 2024

  9. [9]

    Signifi- cant advancements in uav technology for reliable oil and gas pipeline monitoring,

    I. Aromoye, H. Lo, P. Sebastian, E. Ghulam, and S. Ayinla, “Signifi- cant advancements in uav technology for reliable oil and gas pipeline monitoring,”Computer Modeling in Engineering & Sciences, vol. 142, no. 2, pp. 1155–1197, 2025

    work page 2025

  10. [10]

    Nebula: Quest for robotic autonomy in challenging environments; team costar at the darpa subterranean challenge,

    A. Agha, K. Otsu, B. Morrell, D. D. Fan, R. Thakker, A. Santamaria- Navarro, S.-K. Kim, A. Bouman, X. Lei, J. Edlundet al., “Neb- ula: Quest for robotic autonomy in challenging environments; team COSTAR at the DARPA subterranean challenge,”arXiv preprint arXiv:2103.11470, 2021

    work page arXiv 2021

  11. [11]

    Classifying conceptual models applied to develop an autonomous snow-plowing system,

    T. Langen, G. Muller, and K. Falk, “Classifying conceptual models applied to develop an autonomous snow-plowing system,” in3rd INCOSE International Conference on Human Systems Integration (HSI), 2024

    work page 2024

  12. [12]

    Wiley, 2023

    INCOSE,Systems Engineering Handbook: A Guide for System Life Cycle Processes and Activities, 5th ed. Wiley, 2023

    work page 2023

  13. [13]

    Combining user centered design and system engineering to the design of a generic ai-based assistant,

    K. Amokrane, V . Rousseaux, M. Dussartre, M. Zouinar, and N. Renoir, “Combining user centered design and system engineering to the design of a generic ai-based assistant,” in3rd INCOSE International Conference on Human Systems Integration (HSI), 2024

    work page 2024

  14. [14]

    Covering models and optimization techniques for emergency response facility location and planning: a review,

    X. Li, Z. Zhao, X. Zhu, and T. Wyatt, “Covering models and optimization techniques for emergency response facility location and planning: a review,”Mathematical Methods of Operations Research, vol. 74, no. 3, pp. 281–310, 2011

    work page 2011

  15. [15]

    A human–security robot interaction literature review,

    X. Ye and L. P. Robert, “A human–security robot interaction literature review,”ACM Transactions on Human-Robot Interaction, vol. 14, no. 2, pp. 1–36, 2024

    work page 2024

  16. [16]

    A plan to protect critical infrastructure from 21st century threats,

    Cybersecurity and Infrastructure Security Agency, “A plan to protect critical infrastructure from 21st century threats,” CISA Blog, May 2024, u.S. Department of Homeland Security. [Online]. Available: https://www.cisa.gov/news-events/news/plan-protect-critical-infrastru cture-21st-century-threats

    work page 2024

  17. [17]

    2025 ransomware report: Ransomware attacks on oil and gas surge 935%,

    Zscaler ThreatLabz, “2025 ransomware report: Ransomware attacks on oil and gas surge 935%,” July 2025. [Online]. Available: https://www.zscaler.com/mx/press/ransomware-surges-attempts-spike -146-amid-aggressive-extortion-tactics

    work page 2025

  18. [18]

    Human–robot teaming challenges for the military and first response,

    J. A. Adams, J. Scholtz, and A. Sciarretta, “Human–robot teaming challenges for the military and first response,”Annual Review of Control, Robotics, and Autonomous Systems, vol. 7, pp. 149–173, 2024

    work page 2024

  19. [19]

    Keeping the human in the loop: are autonomous decisions inevitable?

    J. Pöhler, N. Flegel, T. Mentler, and K. Van Laerhoven, “Keeping the human in the loop: are autonomous decisions inevitable?”i-com, vol. 24, no. 1, pp. 9–25, 2025

    work page 2025

  20. [20]

    Identifying critical infrastructure: the median and covering facility interdiction problems,

    R. L. Church, M. P. Scaparra, and R. S. Middleton, “Identifying critical infrastructure: the median and covering facility interdiction problems,”Annals of the Association of American Geographers, vol. 94, no. 3, pp. 491–502, 2004

    work page 2004

  21. [21]

    Coordinated multi-robot shared auton- omy based on scheduling and demonstrations,

    M. Hagenow, E. Senft, N. Orr, R. Radwin, M. Gleicher, B. Mutlu, D. P. Losey, and M. Zinn, “Coordinated multi-robot shared auton- omy based on scheduling and demonstrations,”IEEE Robotics and Automation Letters, vol. 8, no. 12, pp. 8335–8342, 2023

    work page 2023

  22. [22]

    Concepts and applications of backup coverage,

    K. Hogan and C. Revelle, “Concepts and applications of backup coverage,”Management science, vol. 32, no. 11, pp. 1434–1444, 1986

    work page 1986

  23. [23]

    Network and discrete location: models, algorithms and applications,

    M. Daskin, “Network and discrete location: models, algorithms and applications,”Journal of the Operational Research Society, vol. 48, no. 7, pp. 763–764, 1997. KHATIM & ARIEF (2026): OPTIMIZED HUMAN-ROBOT CO-DISPATCH PLANNING FOR PETRO-SITE SURVEILLANCE UNDER V ARYING CRITICALITIES 11

    work page 1997

  24. [24]

    A bilevel mixed-integer program for critical infrastructure protection planning,

    M. P. Scaparra and R. L. Church, “A bilevel mixed-integer program for critical infrastructure protection planning,”Computers & Opera- tions Research, vol. 35, no. 6, pp. 1905–1923, 2008

    work page 1905

  25. [25]

    Integrated oil companies and the quest for energy transition,

    M. Alsuwailem and B. Williams-Rioux, “Integrated oil companies and the quest for energy transition,” inSPE Annual Technical Conference and Exhibition. SPE, 2022, p. D011S017R001

    work page 2022

  26. [26]

    Managing security threats through touchless security technologies: An overview of the integration of facial recognition technology in the UAE oil and gas industry,

    S. H. Al Zaabi and R. Zamri, “Managing security threats through touchless security technologies: An overview of the integration of facial recognition technology in the UAE oil and gas industry,” Sustainability, vol. 14, no. 22, p. 14915, 2022

    work page 2022

  27. [27]

    Optimum locations of switching centers and the absolute centers and medians of a graph,

    S. L. Hakimi, “Optimum locations of switching centers and the absolute centers and medians of a graph,”Operations research, vol. 12, no. 3, pp. 450–459, 1964

    work page 1964

  28. [28]

    The location of emergency service facilities,

    C. Toregas, R. Swain, C. ReVelle, and L. Bergman, “The location of emergency service facilities,”Operations research, vol. 19, no. 6, pp. 1363–1373, 1971

    work page 1971

  29. [29]

    The maximal covering location problem,

    R. Church and C. ReVelle, “The maximal covering location problem,” inPapers of the regional science association, vol. 32, no. 1. Springer- Verlag Berlin/Heidelberg, 1974, pp. 101–118

    work page 1974

  30. [30]

    The maximum coverage location problem,

    N. Megiddo, E. Zemel, and S. L. Hakimi, “The maximum coverage location problem,”SIAM Journal on Algebraic Discrete Methods, vol. 4, no. 2, pp. 253–261, 1983

    work page 1983

  31. [31]

    A bi-level model and heuristic techniques with various neighborhood strategies for covering interdiction problem with fortification,

    A. Ghaderi, Z. Hosseinzadeh Bandbon, and A. Mahmoodi, “A bi-level model and heuristic techniques with various neighborhood strategies for covering interdiction problem with fortification,”Soft Computing, vol. 28, no. 17, pp. 9921–9947, 2024

    work page 2024

  32. [32]

    Covering problems in facility location: A review,

    R. Z. Farahani, N. Asgari, N. Heidari, M. Hosseininia, and M. Goh, “Covering problems in facility location: A review,”Computers & Industrial Engineering, vol. 62, no. 1, pp. 368–407, 2012

    work page 2012

  33. [33]

    Human performance issues and user interface design for teleoperated robots,

    J. Y . Chen, E. C. Haas, and M. J. Barnes, “Human performance issues and user interface design for teleoperated robots,”IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Re- views), vol. 37, no. 6, pp. 1231–1245, 2007

    work page 2007

  34. [34]

    The influence of robot appearance on assessment,

    K. S. Haring, K. Watanabe, and C. Mougenot, “The influence of robot appearance on assessment,” in2013 8th ACM/IEEE International Conference on Human-Robot Interaction (HRI). IEEE, 2013, pp. 131–132

    work page 2013

  35. [35]

    Warehousing in the e- commerce era: A survey,

    N. Boysen, R. De Koster, and F. Weidinger, “Warehousing in the e- commerce era: A survey,”European Journal of Operational Research, vol. 277, no. 2, pp. 396–411, 2019

    work page 2019

  36. [36]

    Surveillance and security: protecting electricity utilities and other critical infrastructures,

    A. Gouglidis, B. Green, D. Hutchison, A. Alshawish, and H. de Meer, “Surveillance and security: protecting electricity utilities and other critical infrastructures,”Energy Informatics, vol. 1, no. 1, p. 15, 2018

    work page 2018