pith. sign in

arxiv: 2604.24217 · v1 · submitted 2026-04-27 · 📡 eess.SY · cs.SY

Toward Low-Altitude Embodied Intelligence: A Sensing-Communication-Computation-Control Closed-Loop Perspective

Jihao Luo , Zesong Fei , Xinyi Wang , Shuntian Tang , Zilong Liu , Yiqing Zhou This is my paper

Pith reviewed 2026-05-08 01:56 UTC · model grok-4.3

classification 📡 eess.SY cs.SY
keywords low-altitude embodied intelligenceUAV networksclosed-loop controlsensing-communication-computationautonomous droneslow-altitude economyembodied AI
0
0 comments X p. Extension

The pith

Low-altitude embodied intelligence integrates sensing, communication, computation, and control into a closed loop for UAVs to respond timely and safely in complex environments.

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

The paper argues that low-altitude embodied intelligence (LAEI) arises when UAVs combine sensing, communication, computation, and control in a tight closed loop. This integration allows the vehicles to interact with unknown surroundings in real time rather than relying on pre-planned maps or separate modules. A sympathetic reader would care because current UAV systems often suffer from delays when these functions run independently, limiting their use in dynamic urban or disaster zones. The work shows how coordinated SC³ capabilities support missions such as communication relay while mapping the area and adjusting flight paths on the fly. It also maps out the technical challenges that must be solved to make such loops practical.

Core claim

LAEI networks integrate sensing, communication, computation, and control (SC³) into a closed loop to enable timely, effective, and safe UAV responses in complex or unknown environments. The architecture supports diverse low-altitude scenarios, with key techniques for information exchange and decision feedback, illustrated by a case study of a UAV operating in an unknown urban area.

What carries the argument

The SC³ closed loop, which tightly couples sensing, communication, computation, and control to create continuous feedback for UAV decision-making.

Load-bearing premise

The four SC³ functions can be integrated tightly enough in real hardware and software to deliver closed-loop benefits without prohibitive latency, energy, or reliability problems.

What would settle it

An experiment where a UAV with integrated SC³ loop fails to avoid obstacles or complete a mission in an unknown area due to communication delays or computation bottlenecks.

Figures

Figures reproduced from arXiv: 2604.24217 by Jihao Luo, Shuntian Tang, Xinyi Wang, Yiqing Zhou, Zesong Fei, Zilong Liu.

Figure 1
Figure 1. Figure 1: System architecture and operating mechanism for SC view at source ↗
Figure 2
Figure 2. Figure 2: Illustrations of two JSARC modes in the LAEI networks. view at source ↗
Figure 3
Figure 3. Figure 3: Illustrations of hierarchical computation orchestration in LAEI view at source ↗
Figure 4
Figure 4. Figure 4: Case study results of the S Fig. 4. Case study results of the SC view at source ↗
read the original abstract

The rapid growth of the low-altitude economy drives increasingly autonomous unmanned aerial vehicle (UAV) operations, giving rise to low-altitude embodied intelligence (LAEI), in which sensing, communication, computation, and control (SC$^3$) are tightly integrated to enable closed-loop interaction, ensuring timely, effective, and safe responses in complex or unknown environments. This article systematically explores the LAEI networks, from its fundamental architecture to the diverse scenarios that it can support. We examine key enabling techniques that sustain timely information exchange and effective decision feedback within the $\text{SC}^3$ closed loop. A representative low-altitude UAV mission in an unknown urban area is presented as a case study, where the UAV provides communication services and performs environmental sensing to inform closed-loop control, illustrating how coordinated $\text{SC}^3$ capabilities enable efficient and responsive operation. By identifying major challenges and outlining future research directions, this work serves as a cornerstone for developing next-generation low-altitude intelligent systems.

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

0 major / 3 minor

Summary. The manuscript defines low-altitude embodied intelligence (LAEI) as the tight integration of sensing, communication, computation, and control (SC³) into a closed-loop architecture for UAVs, enabling timely and safe operation in complex environments. It systematically examines the LAEI network architecture, supported scenarios, enabling techniques for information exchange and decision feedback, a qualitative case study of a UAV providing communication and sensing services in an unknown urban area to inform closed-loop control, and concludes by outlining open challenges and future directions.

Significance. If the proposed SC³ closed-loop integration proves feasible, the work could provide a valuable unifying perspective for research on autonomous UAV systems in the emerging low-altitude economy. The manuscript explicitly frames integration difficulties as open problems and supplies a high-level architecture plus illustrative case study, which are strengths for a perspective paper and can guide subsequent empirical studies. No quantitative performance claims or formal proofs are made, so the contribution is primarily conceptual and organizational rather than demonstrative.

minor comments (3)
  1. Abstract: The phrase 'LAEI networks' is used before the architecture is described in detail; a brief parenthetical clarification of the term at first use would improve immediate readability for readers outside the subfield.
  2. Case study section: The description remains entirely qualitative with no high-level latency, energy, or reliability estimates drawn from literature or simple models; adding one or two illustrative numbers would make the closed-loop benefit more concrete without altering the perspective nature of the paper.
  3. Notation: SC³ appears both as SC^3 and as text{SC}^3 in different places; consistent use of the math-mode form throughout would eliminate minor typographic inconsistency.

Simulated Author's Rebuttal

0 responses · 0 unresolved

We thank the referee for the positive assessment of our perspective paper and the recommendation for minor revision. The referee's summary accurately reflects the manuscript's focus on the SC³ closed-loop architecture for low-altitude embodied intelligence, its architecture, scenarios, enabling techniques, case study, and open challenges. As no specific major comments were provided, we will incorporate minor revisions to improve clarity, flow, and presentation where appropriate.

Circularity Check

0 steps flagged

No significant circularity: descriptive perspective paper with no derivations or predictions

full rationale

The manuscript is explicitly framed as a perspective paper. It defines LAEI via the SC³ closed-loop integration, surveys architectures/scenarios/enabling techniques, offers a qualitative case study, and lists open challenges. No equations, fitted parameters, quantitative predictions, formal theorems, or empirical results appear. The central claim is definitional and architectural; it does not reduce to any self-referential input, self-citation chain, or renamed known result. All load-bearing statements remain independent of the paper's own outputs.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 1 invented entities

The framework rests on the domain assumption that SC³ components can be integrated into a functional closed loop with acceptable performance; no free parameters or new physical entities are introduced.

axioms (1)
  • domain assumption Sensing, communication, computation, and control can be tightly coupled in UAV hardware and software to form a responsive closed loop.
    Invoked throughout the architecture description and case study as the basis for timely responses.
invented entities (1)
  • Low-altitude embodied intelligence (LAEI) no independent evidence
    purpose: A unifying label for SC³-integrated UAV systems operating in low-altitude environments.
    New term coined in the paper to organize the perspective; no independent falsifiable evidence provided.

pith-pipeline@v0.9.0 · 5491 in / 1304 out tokens · 67388 ms · 2026-05-08T01:56:54.194642+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

15 extracted references · 3 canonical work pages

  1. [1]

    Air-ground integrated sensing and communications: Opportunities and challenges,

    Z. Fei, X. Wang, N. Wu, J. Huang, and J. A. Zhang, “Air-ground integrated sensing and communications: Opportunities and challenges,” IEEE Commun. Mag., vol. 61, no. 5, pp. 55–61, Feb. 2023

    2023

  2. [2]

    Wireless communications with unmanned aerial vehicles: opportunities and challenges,

    Y . Zeng, R. Zhang, and T. J. Lim, “Wireless communications with unmanned aerial vehicles: opportunities and challenges,”IEEE Commun. Mag., vol. 54, no. 5, pp. 36–42, May 2016

    2016

  3. [3]

    Trajectory design for UA V-based low-altitude wireless networks in unknown environments: A digital twin-assisted TD3 approach,

    J. Luo, Z. Fei, X. Wang, L. Zhao, Y . Cui, G. Zhu, and D. Niyato, “Trajectory design for UA V-based low-altitude wireless networks in unknown environments: A digital twin-assisted TD3 approach,”arXiv preprint arXiv:2510.24255, 2025

    work page arXiv 2025

  4. [4]

    Em- bodied artificial intelligence-enabled internet of vehicles: Challenges and solutions,

    M. Chen, C. Wang, X. He, F. Zhu, L. Wang, and A. V . Vasilakos, “Em- bodied artificial intelligence-enabled internet of vehicles: Challenges and solutions,”IEEE Veh. Technol. Mag., vol. 20, no. 2, pp. 63–70, Mar. 2025

    2025

  5. [5]

    Joint user scheduling, power allocation, and trajectory design for joint synthetic aperture radar and communication UA V systems,

    Z. Liu, Z. Fei, X. Wang, P. Liu, S. Xu, J. Zhou, and W. Yuan, “Joint user scheduling, power allocation, and trajectory design for joint synthetic aperture radar and communication UA V systems,”IEEE Trans. Veh. Technol., vol. 74, no. 2, pp. 3006–3016, Oct. 2025

    2025

  6. [6]

    Coverage path planning for multi-view SAR-UA V observation system under energy constraint,

    D. Song, X. Zhang, Z. Yu, and K. Qin, “Coverage path planning for multi-view SAR-UA V observation system under energy constraint,” inIGARSS 2025 - 2025 IEEE International Geoscience and Remote Sensing Symposium, 2025, pp. 5482–5486

    2025

  7. [7]

    A phase error reverse recovery method for bistatic forward-looking SAR based on ground combined beam coordinate,

    Y . Lou, M. Xing, M. Zhang, P. Ma, and H. Yu, “A phase error reverse recovery method for bistatic forward-looking SAR based on ground combined beam coordinate,”IEEE Trans. Geosci. Remote Sens., vol. 63, pp. 1–15, Nov. 2025

    2025

  8. [8]

    Affine frequency division multiplexing for next generation wireless communications,

    A. Bemani, N. Ksairi, and M. Kountouris, “Affine frequency division multiplexing for next generation wireless communications,”IEEE Trans. Wireless Commun., vol. 22, no. 11, pp. 8214–8229, Mar. 2023

    2023

  9. [9]

    Doppler-resilient LEO satellite OFDM transmission with affine frequency domain pilot,

    S. Tang, X. Wu, X. Wang, L. Zhao, G. Yang, Z. Liu, F. Liu, and Z. Fei, “Doppler-resilient LEO satellite OFDM transmission with affine frequency domain pilot,”arXiv preprint arXiv:2601.01956, 2026

    work page arXiv 2026

  10. [10]

    Reduction of Complex Dynamics in Far-from- equilibrium Systems: Nambu Non-equilibrium Thermodynamics

    S. Tang, Z. Fei, X. Wang, D. Zhou, Z. Wei, and C. Masouros, “A novel symbol level precoding based AFDM transmission framework: Offloading equalization burden to transmitter side,”arXiv:2508.12215, Aug. 2025. [Online]. Available: https://doi.org/10.48550/arXiv.2508. 12215

    work page doi:10.48550/arxiv.2508 2025

  11. [11]

    Joint beam- forming and offloading design for integrated sensing, communication, and computation system,

    P. Liu, Z. Fei, X. Wang, Y . Zhou, Y . Zhang, and F. Liu, “Joint beam- forming and offloading design for integrated sensing, communication, and computation system,”IEEE Trans. Veh. Technol., vol. 74, no. 9, pp. 14 933–14 937, Apr. 2025

    2025

  12. [12]

    Towards intelligent edge sensing for ISCC network: Joint multi-tier DNN partitioning and beamforming design,

    P. Liu, Z. Fei, X. Wang, X. Li, W. Yuan, Y . Li, C. Hu, and D. Niyato, “Towards intelligent edge sensing for ISCC network: Joint multi-tier DNN partitioning and beamforming design,”IEEE Trans. Wireless Commun., pp. 1–1, Nov. 2025

    2025

  13. [13]

    TD3-based trajectory design for UA V-assisted communication in unknown environment,

    J. Luo, L. Zhao, C. Yin, X. Wang, and Z. Fei, “TD3-based trajectory design for UA V-assisted communication in unknown environment,” in 2025 IEEE/CIC International Conference on Communications in China (ICCC), 2025, pp. 1–6

    2025

  14. [14]

    Joint task offloading and resource allocation in multi-UA V multi-server systems: An attention-based deep reinforcement learning approach,

    G. Wu, Z. Liu, M. Fan, and K. Wu, “Joint task offloading and resource allocation in multi-UA V multi-server systems: An attention-based deep reinforcement learning approach,”IEEE Trans. Veh. Technol., vol. 73, no. 8, pp. 11 964–11 978, Mar. 2024

    2024

  15. [15]

    Trajectory design for UA V-based internet of things data collection: A deep reinforcement learning approach,

    Y . Wang, Z. Gao, J. Zhang, X. Cao, D. Zheng, Y . Gao, D. W. K. Ng, and M. Di Renzo, “Trajectory design for UA V-based internet of things data collection: A deep reinforcement learning approach,”IEEE Internet Things J., vol. 9, no. 5, pp. 3899–3912, Mar. 2022

    2022