pith. sign in

arxiv: 2604.08009 · v1 · submitted 2026-04-09 · 💻 cs.RO

AgiPIX: Bridging Simulation and Reality in Indoor Aerial Inspection

Sasanka Kuruppu Arachchige , Juan Jose Garcia , Changda Tian , Lauri Suomela , Panos Trahanias , Adriana Tapus , Joni-Kristian K\"am\"ar\"ainen This is my paper

Pith reviewed 2026-05-10 17:29 UTC · model grok-4.3

classification 💻 cs.RO
keywords aerial roboticssimulation to real transferindoor inspectionROS2digital twinautonomous dronesasset inspection
0
0 comments X

The pith

AgiPIX is an open hardware-software platform that bridges simulation and real-world indoor aerial inspection through zero-shot transfer of autonomy components.

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

The paper introduces Agipix, a compact platform combining hardware, containerized software, and a photorealistic digital twin for autonomous indoor flights. It aims to solve the challenge of transferring algorithms from simulation to reality without adaptation, enabling faster development for tasks like critical asset inspection. A sympathetic reader would care because existing platforms often require extensive tuning, slowing progress in robotics for hazardous environments. The demonstrations show successful trajectory tracking and exploration using onboard sensors in industrial settings.

Core claim

Agipix features a hardware-synchronized active-sensing platform with onboard compute, a modular ROS2 autonomy stack in containers, and a photorealistic digital twin, together enabling rapid iteration via zero-shot transfer between simulation and real flights, as shown in trajectory tracking and exploration tasks.

What carries the argument

The photorealistic digital twin combined with containerized ROS~2 autonomy stack that supports direct transfer without fine-tuning.

If this is right

  • Developers can test and refine autonomy algorithms in simulation before direct deployment on real hardware.
  • Trajectory tracking and exploration can be performed reliably using onboard sensing in industrial indoor environments.
  • The open release of designs, assets, and software supports community reproducibility and extension.
  • Rapid iteration reduces the time needed to develop solutions for indoor aerial autonomy challenges.

Where Pith is reading between the lines

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

  • Other robotics teams could replicate the platform to accelerate their own sim-to-real projects in inspection tasks.
  • This approach might generalize to other sensor-rich environments beyond industrial indoors.
  • Long-term, it could lower barriers for deploying autonomous drones in critical infrastructure monitoring.

Load-bearing premise

The photorealistic digital twin accurately captures the real hardware dynamics, sensor behavior, and environment sufficiently to support zero-shot transfer of autonomy components without additional adaptation or fine-tuning.

What would settle it

Demonstrating that the autonomy components transferred from the digital twin perform significantly worse on real hardware than in simulation, requiring adaptation to achieve similar performance.

Figures

Figures reproduced from arXiv: 2604.08009 by Adriana Tapus, Changda Tian, Joni-Kristian K\"am\"ar\"ainen, Juan Jose Garcia, Lauri Suomela, Panos Trahanias, Sasanka Kuruppu Arachchige.

Figure 1
Figure 1. Figure 1: AgiPIX is an open platform for indoor aerial autonomy and critical asset inspection. Left: Mapping result and a PoV [PITH_FULL_IMAGE:figures/full_fig_p001_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Comparison of consumer and research platforms by onboard compute, agility, and sensing. Criteria include openness, [PITH_FULL_IMAGE:figures/full_fig_p003_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: System overview of the AgiPIX stack. AgiAUTO runs modular ROS 2 components on the companion computer. [PITH_FULL_IMAGE:figures/full_fig_p004_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: USB 3.0, CAN, UART, RS-232, and SPI interfaces [PITH_FULL_IMAGE:figures/full_fig_p004_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: This is the complete overview of the AgiUI where the user can see different perspectives of the robots it is controlling, [PITH_FULL_IMAGE:figures/full_fig_p006_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Trajectory-tracking comparison of Ground Truth, Ag [PITH_FULL_IMAGE:figures/full_fig_p006_6.png] view at source ↗
Figure 9
Figure 9. Figure 9: Percentage of free, occupied, and unmapped volume [PITH_FULL_IMAGE:figures/full_fig_p007_9.png] view at source ↗
Figure 8
Figure 8. Figure 8: Representative ENRICH 2025 mapping output. [PITH_FULL_IMAGE:figures/full_fig_p007_8.png] view at source ↗
Figure 11
Figure 11. Figure 11: AgiPIX supports heterogeneous hardware deploy [PITH_FULL_IMAGE:figures/full_fig_p008_11.png] view at source ↗
read the original abstract

Autonomous indoor flight for critical asset inspection presents fundamental challenges in perception, planning, control, and learning. Despite rapid progress, there is still a lack of a compact, active-sensing, open-source platform that is reproducible across simulation and real-world operation. To address this gap, we present Agipix, a co-designed open hardware and software platform for indoor aerial autonomy and critical asset inspection. Agipix features a compact, hardware-synchronized active-sensing platform with onboard GPU-accelerated compute that is capable of agile flight; a containerized ROS~2-based modular autonomy stack; and a photorealistic digital twin of the hardware platform together with a reliable UI. These elements enable rapid iteration via zero-shot transfer of containerized autonomy components between simulation and real flights. We demonstrate trajectory tracking and exploration performance using onboard sensing in industrial indoor environments. All hardware designs, simulation assets, and containerized software are released openly together with documentation.

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 / 1 minor

Summary. The manuscript introduces AgiPIX, a co-designed open hardware and software platform for autonomous indoor aerial inspection and critical asset monitoring. It consists of a compact drone with hardware-synchronized active sensing and onboard GPU compute, a containerized ROS 2 modular autonomy stack, and a photorealistic digital twin of the platform and environment. The central claim is that these components enable rapid iteration via zero-shot transfer of containerized autonomy code between simulation and real flights, with demonstrations of trajectory tracking and exploration performance using onboard sensing in industrial indoor environments. All hardware designs, simulation assets, and software are released openly.

Significance. If the zero-shot transfer claim holds with quantitative validation, the platform would offer a valuable, reproducible open-source resource for the robotics community to develop and test perception, planning, and control algorithms for agile indoor flight without repeated sim-to-real tuning. The open release of hardware, simulation models, and containerized code is a clear strength that supports reproducibility and extension.

major comments (2)
  1. [Abstract] Abstract: The claims of 'zero-shot transfer of containerized autonomy components' and 'demonstrate trajectory tracking and exploration performance using onboard sensing' are presented without any quantitative metrics, error analysis, closed-loop comparisons between simulation and reality, or details on how the digital twin's fidelity was validated.
  2. [Demonstrations section] Demonstrations section: No evidence is provided that the photorealistic digital twin accurately captures hardware dynamics (e.g., aerodynamics, motor response), sensor behavior (noise, latency, synchronization), or environment to support identical code execution without adaptation; the central zero-shot claim therefore rests on an unverified assumption.
minor comments (1)
  1. [Overall] The manuscript would benefit from additional figures or tables comparing simulation and real-world trajectories or sensor data to improve clarity of the transfer results.

Simulated Author's Rebuttal

2 responses · 1 unresolved

We thank the referee for their constructive feedback, which highlights important areas for strengthening the presentation of our zero-shot transfer claims. We address each major comment below, indicating planned revisions where evidence can be added from existing work and noting limitations where new experiments would be required.

read point-by-point responses

  1. Referee: [Abstract] Abstract: The claims of 'zero-shot transfer of containerized autonomy components' and 'demonstrate trajectory tracking and exploration performance using onboard sensing' are presented without any quantitative metrics, error analysis, closed-loop comparisons between simulation and reality, or details on how the digital twin's fidelity was validated.

    Authors: We agree the abstract would be improved by including quantitative support. The manuscript's demonstrations section shows the same containerized ROS 2 autonomy stack executing trajectory tracking and exploration tasks in both the digital twin and real flights without code changes. In revision we will update the abstract to report specific metrics from those experiments (e.g., position RMSE for tracking and coverage percentages for exploration) and add a concise statement on the digital twin validation steps already performed, such as visual environment matching and basic sensor timing checks. revision: yes

  2. Referee: [Demonstrations section] Demonstrations section: No evidence is provided that the photorealistic digital twin accurately captures hardware dynamics (e.g., aerodynamics, motor response), sensor behavior (noise, latency, synchronization), or environment to support identical code execution without adaptation; the central zero-shot claim therefore rests on an unverified assumption.

    Authors: The referee is correct that the current text does not supply quantitative fidelity validation for aerodynamics, motor dynamics, or detailed sensor noise/latency models. The demonstrations rest on the practical observation that identical containerized components produce comparable behavior in simulation and reality for the tested tasks. We will revise the demonstrations section to include all available supporting data on sensor synchronization, latency measurements, and environment reconstruction accuracy. We will also explicitly state the modeling assumptions and limitations regarding full aerodynamic and motor-response fidelity. revision: partial

standing simulated objections not resolved
  • Quantitative validation of hardware dynamics (aerodynamics and motor response) matching between the digital twin and physical platform, as this would require additional system-identification experiments not conducted in the original work.

Circularity Check

0 steps flagged

No circularity: platform description paper with no derivations or self-referential claims.

full rationale

The paper presents an open hardware/software platform (AgiPIX) and its photorealistic digital twin for indoor aerial inspection, claiming that the co-design enables zero-shot transfer of containerized autonomy components. No mathematical derivations, equations, fitted parameters, or 'predictions' appear in the provided abstract or description. Core claims are descriptive and empirical (design features, demonstrations of trajectory tracking and exploration), not derived from prior results by construction. No load-bearing self-citations, uniqueness theorems, or ansatzes are invoked to justify the central claims. The work is self-contained as an engineering contribution open to external validation of sim-to-real fidelity; it does not reduce any result to its own inputs.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

No free parameters, axioms, or invented entities; the contribution is an engineering platform description rather than a theoretical derivation.

pith-pipeline@v0.9.0 · 5492 in / 1067 out tokens · 67509 ms · 2026-05-10T17:29:09.686453+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

48 extracted references · 48 canonical work pages

  1. [1]

    Toward fully auto- mated inspection of critical assets supported by autonomous mobile robots, vision sensors, and artificial intelligence,

    J. Sanchez-Cubillo, J. Del Ser, and J. L. Martin, “Toward fully auto- mated inspection of critical assets supported by autonomous mobile robots, vision sensors, and artificial intelligence,”Sensors, vol. 24, no. 12, p. 3721, 2024

    work page 2024

  2. [2]

    Cerberus in the darpa subterranean challenge,

    M. Tranzatto, T. Miki, M. Dharmadhikari, L. Bernreiter, M. Kulkarni, F. Mascarich, O. Andersson, S. Khattak, M. Hutter, R. Siegwart, and K. Alexis, “Cerberus in the darpa subterranean challenge,”Science Robotics, vol. 7, no. 66, p. eabp9742, 2022

    work page 2022

  3. [3]

    Enrich – the european robotics hackathon

    European Robotics, “Enrich – the european robotics hackathon.” https: //enrich.european-robotics.eu/, 2025. Accessed: 2026-02-03

    work page 2025

  4. [4]

    Ag- ilicious: Open-source and open-hardware agile quadrotor for vision- based flight,

    P. Foehn, E. Kaufmann, A. Romero, R. Penicka, S. Sun, L. Bauersfeld, T. Laengle, G. Cioffi, Y . Song, A. Loquercio, and D. Scaramuzza, “Ag- ilicious: Open-source and open-hardware agile quadrotor for vision- based flight,”Science Robotics, vol. 7, no. 67, p. eabl6259, 2022

    work page 2022

  5. [5]

    Swarm of micro flying robots in the wild,

    X. Zhou, X. Wen, Z. Wang, Y . Gao, H. Li, Q. Wang, T. Yang, H. Lu, Y . Cao, C. Xu, and F. Gao, “Swarm of micro flying robots in the wild,”Science Robotics, vol. 7, no. 66, p. eabm5954, 2022

    work page 2022

  6. [6]

    Isaac sim – robotics simulation and synthetic data gener- ation

    NVIDIA, “Isaac sim – robotics simulation and synthetic data gener- ation.” https://developer.nvidia.com/isaac/sim, 2026. Accessed: 2026- 02-03

    work page 2026

  7. [7]

    Matrice 400 technical specifications

    DJI, “Matrice 400 technical specifications.” https://enterprise.dji.com/ matrice-400/specs, 2026. Accessed: 2026-02-03

    work page 2026

  8. [8]

    Skydio x10 technical specifications

    Skydio, Inc., “Skydio x10 technical specifications.” https://www. skydio.com/x10/technical-specs, 2026. Accessed: 2026-02-03

    work page 2026

  9. [9]

    Elios 3 – indoor lidar drone for industry 4.0

    Flyability, “Elios 3 – indoor lidar drone for industry 4.0.” https://www. flyability.com/elios-3, 2022. Accessed: 2026-02-03

    work page 2022

  10. [10]

    Crazyflie 2.0 quadrotor as a platform for research and education in robotics and control engineering,

    W. Giernacki, M. Skwierczy ´nski, W. Witwicki, P. Wro ´nski, and P. Kozierski, “Crazyflie 2.0 quadrotor as a platform for research and education in robotics and control engineering,” inInternational Conference on Methods and Models in Automation and Robotics (MMAR), pp. 37–42, 2017

    work page 2017

  11. [11]

    Fast, autonomous flight in gps-denied and cluttered environments,

    K. Mohta, M. Watterson, Y . Mulgaonkar, S. Liu, C. Qu, A. Makineni, K. Saulnier, K. Sun, A. Zhu, J. Delmerico, K. Karydis, N. Atanasov, G. Loianno, D. Scaramuzza, K. Daniilidis, C. J. Taylor, and V . Kumar, “Fast, autonomous flight in gps-denied and cluttered environments,” J. Field Robot., vol. 35, no. 1, pp. 101–120, 2018

    work page 2018

  12. [12]

    Borinot: An open thrust- torque-controlled robot for agile aerial-contact motion research,

    J. Mart ´ı-Saumell, H. Duarte, P. Grosch, J. Andrade-Cetto, A. Santamaria-Navarro, and J. Sol `a, “Borinot: An open thrust- torque-controlled robot for agile aerial-contact motion research,” 2023

    work page 2023

  13. [13]

    The MRS UA V system: Pushing the frontiers of reproducible research, real-world deployment, and education with autonomous unmanned aerial vehicles,

    T. Baca, M. Petrlik, M. Vrba, V . Spurny, R. Penicka, D. Hert, and M. Saska, “The MRS UA V system: Pushing the frontiers of reproducible research, real-world deployment, and education with autonomous unmanned aerial vehicles,”J. Intell. Rob. Syst., vol. 102, p. 26, Apr. 2021

    work page 2021

  14. [14]

    Omninxt: A fully open-source and compact aerial robot with omnidirectional visual perception,

    P. Liu, C. Feng, Y . Xu, Y . Ning, H. Xu, and S. Shen, “Omninxt: A fully open-source and compact aerial robot with omnidirectional visual perception,” in2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 10605–10612, IEEE, 2024

    work page 2024

  15. [15]

    Px4: A node-based multithreaded open source robotics framework for deeply embedded platforms,

    L. Meier, D. Honegger, and M. Pollefeys, “Px4: A node-based multithreaded open source robotics framework for deeply embedded platforms,” in2015 IEEE International Conference on Robotics and Automation (ICRA), pp. 6235–6240, 2015

    work page 2015

  16. [16]

    Lio-sam: Tightly-coupled lidar inertial odometry via smoothing and mapping,

    T. Shan, B. Englot, D. Meyers, W. Wang, C. Ratti, and D. Rus, “Lio-sam: Tightly-coupled lidar inertial odometry via smoothing and mapping,” in2020 IEEE/RSJ international conference on intelligent robots and systems (IROS), pp. 5135–5142, IEEE, 2020

    work page 2020

  17. [17]

    Fast-lio2: Fast direct lidar-inertial odometry,

    W. Xu, Y . Cai, D. He, J. Lin, and F. Zhang, “Fast-lio2: Fast direct lidar-inertial odometry,”IEEE Transactions on Robotics, vol. 38, no. 4, pp. 2053–2073, 2022

    work page 2053

  18. [18]

    Direct lidar-inertial odome- try: Lightweight lio with continuous-time motion correction,

    K. Chen, R. Nemiroff, and B. T. Lopez, “Direct lidar-inertial odome- try: Lightweight lio with continuous-time motion correction,” in2023 IEEE International Conference on Robotics and Automation (ICRA), pp. 3983–3989, 2023

    work page 2023

  19. [19]

    Adaptive-lio: Enhancing robustness and precision through environmental adaptation in lidar inertial odometry,

    C. Zhao, K. Hu, J. Xu, L. Zhao, B. Han, K. Wu, M. Tian, and S. Yuan, “Adaptive-lio: Enhancing robustness and precision through environmental adaptation in lidar inertial odometry,”IEEE Internet of Things Journal, 2024

    work page 2024

  20. [20]

    Robust navigation based on an interacting multiple-model filtering framework using multiple tracking cameras,

    S. Kuruppu Arachchige and K. Lee, “Robust navigation based on an interacting multiple-model filtering framework using multiple tracking cameras,” inAIAA SCITECH 2024 Forum, p. 1175, 2024

    work page 2024

  21. [21]

    Minimum snap trajectory generation and control for quadrotors,

    D. Mellinger and V . Kumar, “Minimum snap trajectory generation and control for quadrotors,” in2011 IEEE International Conference on Robotics and Automation (ICRA), pp. 2520–2525, 2011

    work page 2011

  22. [22]

    Vision-aided uav navigation and dynamic obstacle avoidance using gradient-based b- spline trajectory optimization,

    Z. Xu, Y . Xiu, X. Zhan, B. Chen, and K. Shimada, “Vision-aided uav navigation and dynamic obstacle avoidance using gradient-based b- spline trajectory optimization,” in2023 IEEE International Conference on Robotics and Automation (ICRA), pp. 1214–1220, IEEE, 2023

    work page 2023

  23. [23]

    Ego-planner: An esdf- free gradient-based local planner for quadrotors,

    X. Zhou, Z. Wang, H. Ye, C. Xu, and F. Gao, “Ego-planner: An esdf- free gradient-based local planner for quadrotors,”IEEE Robotics and Automation Letters, vol. 6, no. 2, pp. 478–485, 2020

    work page 2020

  24. [24]

    On-manifold model predictive control for trajectory tracking on robotic systems,

    G. Lu, W. Xu, and F. Zhang, “On-manifold model predictive control for trajectory tracking on robotic systems,”IEEE Transactions on Industrial Electronics, vol. 70, no. 9, pp. 9192–9202, 2023

    work page 2023

  25. [25]

    Learning perception-aware agile flight in cluttered environments,

    Y . Song, K. Shi, R. Penicka, and D. Scaramuzza, “Learning perception-aware agile flight in cluttered environments,” 2022

    work page 2022

  26. [26]

    Navrl: Learning safe flight in dynamic environments,

    Z. Xu, X. Han, H. Shen, H. Jin, and K. Shimada, “Navrl: Learning safe flight in dynamic environments,”IEEE Robotics and Automation Letters, vol. 10, no. 4, pp. 3668–3675, 2025

    work page 2025

  27. [27]

    Synthetic vs. real training data for visual navigation,

    L. Suomela, S. K. Arachchige, G. F. Torres, H. Edelman, and J.-K. K¨am¨ar¨ainen, “Synthetic vs. real training data for visual navigation,” arXiv preprint arXiv:2509.11791, 2025

    work page arXiv 2025

  28. [28]

    Data scaling for navigation in unknown environments,

    L. Suomela, N. Takahata, S. K. Arachchige, H. Edelman, and J.-K. K¨am¨ar¨ainen, “Data scaling for navigation in unknown environments,” arXiv preprint arXiv:2601.09444, 2026

    work page arXiv 2026

  29. [29]

    Rotors— a modular gazebo mav simulator framework,

    F. Furrer, M. Burri, M. W. Achtelik, and R. Siegwart, “Rotors— a modular gazebo mav simulator framework,” inRobot Operating System (ROS): The Complete Reference (Volume 1)(A. Koubaa, ed.), pp. 595–625, Springer International Publishing, 2016

    work page 2016

  30. [30]

    Airsim: High-fidelity visual and physical simulation for autonomous vehicles,

    S. Shah, D. Dey, C. Lovett, and A. Kapoor, “Airsim: High-fidelity visual and physical simulation for autonomous vehicles,” inField and service robotics: Results of the 11th international conference, pp. 621– 635, Springer, 2017

    work page 2017

  31. [31]

    Flightmare: A flexible quadrotor simulator,

    Y . Song, S. Naji, E. Kaufmann, A. Loquercio, and D. Scaramuzza, “Flightmare: A flexible quadrotor simulator,” inConference on Robot Learning, pp. 1147–1157, PMLR, 2021

    work page 2021

  32. [32]

    Pegasus simulator: An isaac sim framework for multiple aerial vehicles simulation,

    M. Jacinto, J. Pinto, J. Patrikar, J. Keller, R. Cunha, S. Scherer, and A. Pascoal, “Pegasus simulator: An isaac sim framework for multiple aerial vehicles simulation,” in2024 International Conference on Unmanned Aircraft Systems (ICUAS), pp. 917–922, 2024

    work page 2024

  33. [33]

    Effect of interface design on cognitive workload in unmanned aerial vehicle control,

    W. Zhang, Y . Liu, and D. B. Kaber, “Effect of interface design on cognitive workload in unmanned aerial vehicle control,”International Journal of Human-Computer Studies, vol. 189, p. 103287, 2024

    work page 2024

  34. [34]

    Improving human ground control performance in unmanned aerial systems,

    M. Di Gregorio, M. Romano, M. Sebillo, G. Vitiello, and A. V ozella, “Improving human ground control performance in unmanned aerial systems,”Future Internet, vol. 13, no. 8, p. 188, 2021

    work page 2021

  35. [35]

    Survey on human-drone interaction,

    S. Hayat, E. Yanmaz, and R. Muzaffar, “Survey on human-drone interaction,”IEEE Access, vol. 4, pp. 8376–8399, 2016

    work page 2016

  36. [36]

    A visually elicited escape response in the fly that does not use the giant fiber pathway,

    M. H. Holmqvist, “A visually elicited escape response in the fly that does not use the giant fiber pathway,”Visual neuroscience, vol. 11, no. 6, pp. 1149–1161, 1994

    work page 1994

  37. [37]

    mqtt client: Ros 2 mqtt client library

    R. A. U. Institute for Automotive Engineering (ika), “mqtt client: Ros 2 mqtt client library..” https://github.com/ika-rwth-aachen/mqtt client,

    work page

  38. [38]

    Accessed: 2026-02-09

    work page 2026

  39. [39]

    Px4 ros 2 user guide

    P. D. Team, “Px4 ros 2 user guide..” https://docs.px4.io/main/en/ros2/ user guide, 2026. Accessed: 2026-02-09

    work page 2026

  40. [40]

    Px4 ros 2 control interface

    P. D. Team, “Px4 ros 2 control interface..” https://docs.px4.io/main/ en/ros2/px4 ros2 control interface, 2026. Accessed: 2026-02-09

    work page 2026

  41. [41]

    Lv-dot: Lidar-visual dynamic obstacle detection and tracking for autonomous robot navigation,

    Z. Xu, H. Shen, X. Han, H. Jin, K. Ye, and K. Shimada, “Lv-dot: Lidar-visual dynamic obstacle detection and tracking for autonomous robot navigation,”arXiv preprint arXiv:2502.20607, 2025

    work page arXiv 2025

  42. [42]

    agi logger: Robust ros 2 data logging for agipix platform

    S. Kuruppu Arachchige, “agi logger: Robust ros 2 data logging for agipix platform..” https://github.com/SasaKuruppuarachchi/agi logger,

    work page

  43. [43]

    Accessed: 2026-02-09

    Version v1.0.0. Accessed: 2026-02-09

    work page 2026

  44. [44]

    Foxglove – the observability stack for physical ai

    I. Foxglove Technologies, “Foxglove – the observability stack for physical ai..” https://foxglove.dev/, 2026. Accessed: 2026-02-03

    work page 2026

  45. [45]

    Cloudstation: A cloud-based ground control station for drones,

    L. Hu, O. Pathak, Z. He, H. Lee, M. Bedwany, J. Mica, and P. J. Burke, “Cloudstation: A cloud-based ground control station for drones,”IEEE Journal on Miniaturization for Air and Space Systems, vol. 2, no. 1, pp. 36–42, 2021

    work page 2021

  46. [46]

    Exploring cognitive load dynam- ics in human-machine interaction for teleoperation: A user-centric perspective on remote operation system design,

    H. Garc ´ıa-C´ardenas and Tapus, “Exploring cognitive load dynam- ics in human-machine interaction for teleoperation: A user-centric perspective on remote operation system design,” in2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 12204–12211, 2024

    work page 2024

  47. [47]

    Autonomous uav exploration of dynamic environments via incremental sampling and probabilistic roadmap,

    Z. Xu, D. Deng, and K. Shimada, “Autonomous uav exploration of dynamic environments via incremental sampling and probabilistic roadmap,”IEEE Robotics and Automation Letters, vol. 6, no. 2, pp. 2729–2736, 2021

    work page 2021

  48. [48]

    Low-cost rapid-development air-ground robotic solution for nuclear power plant inspection,

    C. Tian, S. K. Arachchige, H. Li, J. J. G. Cardenas, H. Raei, E. Dincer, A. Kenan, P. Bremner, M. Giuliani, G. Neumann,et al., “Low-cost rapid-development air-ground robotic solution for nuclear power plant inspection,” inIEEE International Symposium on Safety, Security, and Rescue Robotics, 2025

    work page 2025