pith. sign in

arxiv: 2605.18486 · v1 · pith:3VHBUOKNnew · submitted 2026-05-18 · 📡 eess.SP

Movable Antenna-Enabled Integrated Sensing and Communication in Low-Altitude UAV Networks

Bin Li , Pengcheng Rao , Xuedong Zhang , Xinyi Wang This is my paper

Pith reviewed 2026-05-20 08:32 UTC · model grok-4.3

classification 📡 eess.SP
keywords movable antennasUAV networksintegrated sensing and communicationtrajectory optimizationbeamforminguser associationreinforcement learning
0
0 comments X

The pith

UAVs equipped with movable antenna arrays outperform fixed-antenna UAVs in integrated sensing and communication by increasing total data rates while satisfying sensing SNR constraints.

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

This paper studies a system where multiple low-altitude UAVs use movable antenna arrays to perform both wireless communication to ground users and sensing tasks at the same time. To handle moving users and flying UAVs in three dimensions, the work jointly optimizes UAV flight paths, which users connect to each UAV, the physical positions of the antennas, and the signal beamforming. The optimization is split into a clustering step using HDBSCAN to group users and suggest UAV directions, followed by a soft actor-critic reinforcement learning algorithm to adjust the rest under power and sensing quality limits. Simulations indicate that the movable antennas allow higher total data rates than fixed arrays while still satisfying the sensing requirements.

Core claim

By equipping UAVs with movable antenna arrays in a multi-UAV ISAC setup and jointly optimizing trajectories, user associations via HDBSCAN clustering, antenna positions, and beamforming with soft actor-critic reinforcement learning, the system maximizes the sum data rate subject to power and sensing SNR constraints, with simulations showing performance gains over fixed-antenna baselines.

What carries the argument

Movable antenna arrays whose positions are optimized jointly with UAV trajectories and beamforming vectors using a hierarchical clustering step followed by soft actor-critic learning.

Load-bearing premise

The simulation of dynamic user roaming and three-dimensional UAV deployment, together with the chosen power and sensing-SNR constraints, is representative enough that the observed rate gains will translate to real-world deployments.

What would settle it

A field test with physical UAVs and movable antennas in a low-altitude environment with roaming ground users that fails to show higher communication rates than fixed-antenna UAVs under the same power and sensing SNR constraints.

Figures

Figures reproduced from arXiv: 2605.18486 by Bin Li, Pengcheng Rao, Xinyi Wang, Xuedong Zhang.

Figure 1
Figure 1. Figure 1: Illustration of the UAV-enabled ISAC system. [PITH_FULL_IMAGE:figures/full_fig_p004_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Sum rate under different schemes. gain brought by the clustering mechanism within the overall framework. Scheme 2: All UAVs are equipped with FA arrays with uniform inter-element spacing, and no clustering algorithm is used for air–ground association. This scheme is introduced to highlight the performance improvement achieved by the MA array design in the considered scenario. Scheme 3: The MA array configu… view at source ↗
Figure 5
Figure 5. Figure 5: Cumulative reward under different algorithms. [PITH_FULL_IMAGE:figures/full_fig_p010_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Sum rate under different number of users. [PITH_FULL_IMAGE:figures/full_fig_p010_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Sum rate with respect to changes in the sensing [PITH_FULL_IMAGE:figures/full_fig_p011_7.png] view at source ↗
read the original abstract

This paper investigates a multiple unmanned aerial vehicle (UAV)-assisted integrated sensing and communication (ISAC) system equipped with movable antenna (MA) arrays. To align with practical scenarios, we simulate the dynamic roaming of ground users and the three-dimensional deployment of UAVs in the airspace. We aim to maximize the total data rate by jointly optimizing key operational variables, including UAV trajectories, user association, antenna positions, and beamforming. This formulated problem is subject to constraints on transmission power and the sensing signal-to-noise ratio. To address the challenge of dynamically unknown state transitions due to user mobility, the original problem is decomposed into two steps and solved using different algorithms. First, we utilize the hierarchical density-based spatial clustering of applications with noise (HDBSCAN) algorithm to address the ground-to-air association problem, periodically updating clusters and re-associating during training. The clustering hotspots are used to suggest flight directions for the UAVs. Second, we develop the soft actor-critic algorithm to solve the joint optimization problem of UAV trajectories, antenna positions, and beamforming. Experimental results demonstrate that UAVs equipped with MA arrays outperform those with traditional fixed antenna arrays in ISAC systems, and the proposed optimization strategy effectively enhances communication rates while ensuring sensing performance.

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

1 major / 2 minor

Summary. The paper investigates a multi-UAV ISAC system equipped with movable antenna (MA) arrays. It simulates dynamic ground-user roaming and 3D UAV deployment to maximize the aggregate communication rate by jointly optimizing UAV trajectories, user association, MA positions, and beamforming vectors, subject to transmit-power and sensing-SNR constraints. The optimization is decomposed into a two-stage procedure: HDBSCAN is used for periodic clustering and ground-to-air association, after which a soft actor-critic agent solves the joint trajectory/position/beamforming problem. Simulation results are presented to support the claim that MA-equipped UAVs outperform conventional fixed-antenna arrays while satisfying the sensing requirement.

Significance. If the reported rate gains prove robust, the work illustrates a concrete benefit of movable antennas for ISAC in mobile UAV networks and demonstrates a practical RL-based approach to handling unknown mobility-induced state transitions. The explicit separation of clustering and continuous control is a useful architectural choice for this class of problems.

major comments (1)
  1. [Simulation Results] Simulation Results section: The central claim that MA arrays outperform fixed arrays rests on simulation results obtained under a fixed user-mobility model, channel-fading statistics, and UAV altitude distribution. No sensitivity sweeps or ablation studies are reported that vary these parameters while keeping the same power and sensing-SNR constraints. Because the outperformance is the primary empirical support for the paper’s contribution, the absence of such checks makes it impossible to determine whether the gains are intrinsic to MA or artifacts of the chosen simulation regime.
minor comments (2)
  1. [Abstract] The abstract states that the two-stage algorithm “effectively enhances communication rates” but supplies no numerical values, confidence intervals, or explicit baseline comparisons; adding at least one quantitative highlight would strengthen the summary.
  2. [Notation] Notation for antenna-position vectors and beamforming matrices should be introduced once and used consistently; occasional re-definition of symbols across sections reduces readability.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for the constructive feedback on our manuscript. The major comment raises a valid point about the need for greater robustness checks in the simulation results, which we address below. We outline our planned revisions to strengthen the empirical support for the benefits of movable antenna arrays.

read point-by-point responses

  1. Referee: [Simulation Results] Simulation Results section: The central claim that MA arrays outperform fixed arrays rests on simulation results obtained under a fixed user-mobility model, channel-fading statistics, and UAV altitude distribution. No sensitivity sweeps or ablation studies are reported that vary these parameters while keeping the same power and sensing-SNR constraints. Because the outperformance is the primary empirical support for the paper’s contribution, the absence of such checks makes it impossible to determine whether the gains are intrinsic to MA or artifacts of the chosen simulation regime.

    Authors: We acknowledge that the absence of explicit sensitivity sweeps limits the ability to fully assess robustness. Our original simulations employed representative parameters drawn from practical low-altitude UAV scenarios, including user roaming speeds of 1–5 m/s, Rician fading with a K-factor of 5, and UAV altitudes between 50–150 m, all while enforcing the transmit-power and sensing-SNR constraints. However, we agree that additional verification is warranted. In the revised manuscript we will expand the Simulation Results section to include sensitivity sweeps over user-mobility models, channel-fading statistics, and UAV altitude distributions, together with ablation studies that isolate the contribution of movable-antenna positioning. These new experiments will keep the power and sensing-SNR constraints unchanged and will demonstrate that the rate gains remain consistent across the tested regimes, thereby supporting that the improvements are intrinsic to the MA-enabled architecture rather than artifacts of a single simulation setting. revision: yes

Circularity Check

0 steps flagged

No circularity: simulation results from standard algorithms

full rationale

The paper formulates an optimization problem for UAV trajectories, antenna positions, and beamforming under power and sensing-SNR constraints, then decomposes it into HDBSCAN clustering for user association followed by soft actor-critic RL for joint optimization. Performance claims rest on simulation comparisons of movable vs. fixed arrays in a dynamic roaming model. No equations, fitted parameters, or self-citations are shown that reduce claimed rate gains or outperformance to quantities defined by the same inputs. The chain is self-contained simulation output rather than analytical derivation that loops back by construction.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

The abstract provides no explicit free parameters, axioms, or invented entities; the work rests on standard wireless-channel and reinforcement-learning assumptions that are not enumerated here.

pith-pipeline@v0.9.0 · 5761 in / 1141 out tokens · 34738 ms · 2026-05-20T08:32:16.897900+00:00 · methodology

discussion (0)

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

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

36 extracted references · 36 canonical work pages

  1. [1]

    Trajectory and beamforming optimiza- tion in UA V-enabled ISAC system,

    Q. Gao, R. Zhong, and Y . Liu, “Trajectory and beamforming optimiza- tion in UA V-enabled ISAC system,” inProc. IEEE GLOBECOM, 2024, pp. 1527–1532

    work page 2024

  2. [2]

    NOMA for integrating sensing and communications toward 6G: A multiple access perspective,

    X. Mu, Z. Wang, and Y . Liu, “NOMA for integrating sensing and communications toward 6G: A multiple access perspective,”IEEE Wireless Commun., vol. 31, no. 3, pp. 316–323, 2024

    work page 2024

  3. [3]

    Integrated sensing and communications: Toward dual-functional wire- less networks for 6G and beyond,

    F. Liu, Y . Cui, C. Masouros, J. Xu, T. X. Han, Y . C. Eldar, and S. Buzzi, “Integrated sensing and communications: Toward dual-functional wire- less networks for 6G and beyond,”IEEE J. Sel. Areas Commun., vol. 40, no. 6, pp. 1728–1767, 2022

    work page 2022

  4. [4]

    Exploiting multi-layer refracting RIS-assisted receiver for HAP-SWIPT networks,

    K. Anet al., “Exploiting multi-layer refracting RIS-assisted receiver for HAP-SWIPT networks,”IEEE Trans. Wireless Commun., vol. 23, no. 10, pp. 12638–12657, 2024

    work page 2024

  5. [5]

    Energy-efficient hybrid beamforming for multilayer RIS-assisted secure integrated terrestrial-aerial networks,

    Y . Sunet al., “Energy-efficient hybrid beamforming for multilayer RIS-assisted secure integrated terrestrial-aerial networks,”IEEE Trans. Commun., vol. 70, no. 6, pp. 4189–4210, 2022

    work page 2022

  6. [6]

    MARL-based UA V trajectory and beamforming optimization for ISAC system,

    Q. Gao, R. Zhong, H. Shin, and Y . Liu, “MARL-based UA V trajectory and beamforming optimization for ISAC system,”IEEE Internet Things J., vol. 11, no. 24, pp. 40 492–40 505, 2024

    work page 2024

  7. [7]

    Refracting RIS-aided hybrid satellite-terrestrial relay networks: Joint beamforming design and optimization,

    Z. Lin, H. Niu, K. An, Y . Wang, G. Zheng, and S. Chatzinotas, “Refracting RIS-aided hybrid satellite-terrestrial relay networks: Joint beamforming design and optimization,”IEEE Trans. Aerosp. Electron. Syst., vol. 58, no. 4, pp. 3717–3724, 2022

    work page 2022

  8. [8]

    Learning-based resource allocation strategy for industrial IoT in UA V-enabled MEC systems,

    L. Sun, L. Wan, and X. Wang, “Learning-based resource allocation strategy for industrial IoT in UA V-enabled MEC systems,”IEEE Trans Ind. Informat., vol. 17, no. 7, pp. 5031–5040, 2021

    work page 2021

  9. [9]

    URLLC-oriented joint power control and resource allocation in UA V-assisted networks,

    K. Chen, Y . Wang, J. Zhao, X. Wang, and Z. Fei, “URLLC-oriented joint power control and resource allocation in UA V-assisted networks,” IEEE Internet Things J., vol. 8, no. 12, pp. 10103–10116, 2021

    work page 2021

  10. [10]

    Movable- antenna-enhanced wireless-powered mobile-edge computing systems,

    P. Chen, Y . Yang, B. Lyu, Z. Yang, and A. Jamalipour, “Movable- antenna-enhanced wireless-powered mobile-edge computing systems,” IEEE Internet Things J., vol. 11, no. 21, pp. 35 505–35 518, 2024

    work page 2024

  11. [11]

    Multiuser commu- nications with movable-antenna base station: Joint antenna positioning, receive combining, and power control,

    Z. Xiao, X. Pi, L. Zhu, X. Xia, and R. Zhang, “Multiuser commu- nications with movable-antenna base station: Joint antenna positioning, receive combining, and power control,”IEEE Trans. Wireless Commun., vol. 23, no. 12, pp. 19744–19759, 2024. 12

    work page 2024

  12. [12]

    Movable antennas for wireless commu- nication: Opportunities and challenges,

    L. Zhu, W. Ma, and R. Zhang, “Movable antennas for wireless commu- nication: Opportunities and challenges,”IEEE Commun. Mag., vol. 62, no. 6, pp. 114–120, 2024

    work page 2024

  13. [13]

    Modeling and performance analysis for movable antenna enabled wireless communications,

    L. Zhu, W. Ma, R. Zhang, and B. Ning, “Modeling and performance analysis for movable antenna enabled wireless communications,”IEEE Trans. Wireless Commun., vol. 23, no. 6, pp. 6234–6250, 2024

    work page 2024

  14. [14]

    Movable-antenna enhanced multiuser communication via antenna position optimization,

    L. Zhu, W. Ma, B. Ning, and R. Zhang, “Movable-antenna enhanced multiuser communication via antenna position optimization,”IEEE Trans. Wireless Commun., vol. 23, no. 7, pp. 7214–7229, 2024

    work page 2024

  15. [15]

    Movable antenna array for improving AA V relaying networks,

    W. Zhou, D. Yang, Y . Xu, L. Xiao, F. Wu, and T. Zhang, “Movable antenna array for improving AA V relaying networks,”IEEE Wireless Commun. Lett., vol. 14, no. 12, pp. 4127–4131, 2025

    work page 2025

  16. [16]

    Compressed sensing based channel estimation for movable antenna communications,

    W. Ma, L. Zhu, and R. Zhang, “Compressed sensing based channel estimation for movable antenna communications,”IEEE Commun. Lett., vol. 27, no. 10, pp. 2747–2751, 2023

    work page 2023

  17. [17]

    Beamforming design and trajectory optimization for UA V-empowered adaptable integrated sensing and communication,

    C. Deng, X. Fang, and X. Wang, “Beamforming design and trajectory optimization for UA V-empowered adaptable integrated sensing and communication,”IEEE Trans. Wireless Commun., vol. 22, no. 11, pp. 8512–8526, 2023

    work page 2023

  18. [18]

    Trajectory de- sign and power control for joint radar and communication enabled multi- UA V cooperative detection systems,

    T. Zhang, K. Zhu, S. Zheng, D. Niyato, and N. C. Luong, “Trajectory de- sign and power control for joint radar and communication enabled multi- UA V cooperative detection systems,”IEEE Trans. Commun., vol. 71, no. 1, pp. 158–172, 2023

    work page 2023

  19. [19]

    When UA Vs meet ISAC: Real- time trajectory design for secure communications,

    J. Wu, W. Yuan, and L. Hanzo, “When UA Vs meet ISAC: Real- time trajectory design for secure communications,”IEEE Trans. Veh. Technol., vol. 72, no. 12, pp. 16766–16771, 2023

    work page 2023

  20. [20]

    Cooperative trajectory planning and resource allocation for UA V-enabled integrated sensing and communication systems,

    Y . Pan, R. Li, X. Da, H. Hu, M. Zhang, D. Zhai, K. Cumanan, and O. A. Dobre, “Cooperative trajectory planning and resource allocation for UA V-enabled integrated sensing and communication systems,”IEEE Trans. Veh. Technol., vol. 73, no. 5, pp. 6502–6516, 2024

    work page 2024

  21. [21]

    Joint user associ- ation and UA V location optimization for UA V-aided communications,

    X. Xi, X. Cao, P. Yang, J. Chen, T. Quek, and D. Wu, “Joint user associ- ation and UA V location optimization for UA V-aided communications,” IEEE Wireless Commun. Lett., vol. 8, no. 6, pp. 1688–1691, 2019

    work page 2019

  22. [22]

    Joint user association and de- ployment optimization for delay-minimized UA V-aided MEC networks,

    Z. Han, T. Zhou, T. Xu, and H. Hu, “Joint user association and de- ployment optimization for delay-minimized UA V-aided MEC networks,” IEEE Wireless Commun. Lett., vol. 12, no. 10, pp. 1791–1795, 2023

    work page 2023

  23. [23]

    Pair scheduling and beamforming in STAR-RIS empowered ISAC networks,

    Y . Xu, F. Wu, Y . Zou, D. Yang, and Y . Liu, “Pair scheduling and beamforming in STAR-RIS empowered ISAC networks,”IEEE Trans. Veh. Technol., vol. 73, no. 11, pp. 17732–17736, 2024

    work page 2024

  24. [24]

    Multi-agent deep reinforcement learning for joint decoupled user association and trajectory design in full-duplex multi-UA V networks,

    C. Dai, K. Zhu, and E. Hossain, “Multi-agent deep reinforcement learning for joint decoupled user association and trajectory design in full-duplex multi-UA V networks,”IEEE Trans. Mobile Comput., vol. 22, no. 10, pp. 6056–6070, 2023

    work page 2023

  25. [25]

    Flexible beamforming for movable antenna-enabled integrated sensing and com- munication,

    W. Lyu, S. Yang, Y . Xiu, Z. Zhang, C. Assi, and C. Yuen, “Flexible beamforming for movable antenna-enabled integrated sensing and com- munication,” inProc. IEEE ICCT, 2024, pp. 1315–1320

    work page 2024

  26. [26]

    Fluid antenna system liberating multiuser MIMO for ISAC via deep reinforcement learning,

    C. Wang, G. Li, H. Zhang, K.-K. Wong, Z. Li, D. W. K. Ng, and C.-B. Chae, “Fluid antenna system liberating multiuser MIMO for ISAC via deep reinforcement learning,”IEEE Trans. Wireless Commun., vol. 23, no. 9, pp. 10879–10894, 2024

    work page 2024

  27. [27]

    Antenna position and beamforming optimization for movable antenna enabled ISAC: Optimal solutions and efficient algorithms,

    L. Chen, M.-M. Zhao, M.-J. Zhao, and R. Zhang, “Antenna position and beamforming optimization for movable antenna enabled ISAC: Optimal solutions and efficient algorithms,”IEEE Trans. Signal Process., vol. 73, pp. 3812–3828, 2025

    work page 2025

  28. [28]

    Movable-antenna array empowered ISAC systems for low-altitude economy,

    Z. Kuang, W. Liu, C. Wang, Z. Jin, J. Ren, X. Zhang, and Y . Shen, “Movable-antenna array empowered ISAC systems for low-altitude economy,” inProc. IEEE/CIC ICCC, 2024, pp. 776–781

    work page 2024

  29. [29]

    Predictive posi- tion control for movable antenna arrays in UA V communications: A spatio-temporal transformer-LSTM framework,

    K. Yu, K. Li, X. Liu, Q. Zhang, and Z. Feng, “Predictive posi- tion control for movable antenna arrays in UA V communications: A spatio-temporal transformer-LSTM framework,” arXiv preprint, arXiv:2508.10720, 2025

    work page arXiv 2025

  30. [30]

    A joint UA V trajectory, user association, and beamforming design strategy for multi-UA V-assisted ISAC systems,

    R. Zhang, Y . Zhang, R. Tang, H. Zhao, Q. Xiao, and C. Wang, “A joint UA V trajectory, user association, and beamforming design strategy for multi-UA V-assisted ISAC systems,”IEEE Internet Things J., vol. 11, no. 18, pp. 29360–29374, 2024

    work page 2024

  31. [31]

    An intelligent softwarized resource management and allocation framework for services with personalized intentions in 6G-enabled IoT networks,

    H. Cao, M. Alrashoud, T. Mohamed, and L. Yang, “An intelligent softwarized resource management and allocation framework for services with personalized intentions in 6G-enabled IoT networks,”IEEE Internet Things J., vol. 13, no. 5, pp. 8261–8274, 2026

    work page 2026

  32. [32]

    Integrated sensing and communications for low-altitude economy: A deep reinforcement learn- ing approach,

    X. Ye, Y . Mao, X. Yu, S. Sun, L. Fu, and J. Xu, “Integrated sensing and communications for low-altitude economy: A deep reinforcement learn- ing approach,”IEEE Trans. Wireless Commun., vol. 25, pp. 351–367, 2026

    work page 2026

  33. [33]

    A focal quotient gradient system method for deep neural network training,

    C. Lv, X.-L. Lv, Z. Wang,et al., “A focal quotient gradient system method for deep neural network training,”Appl. Soft Computing, vol. 184, no. 113704, 2025

    work page 2025

  34. [34]

    Joint computing, pushing, and caching optimization for mobile-edge computing networks via soft actor–critic learning,

    X. Gao, Y . Sun, H. Chen, X. Xu, and S. Cui, “Joint computing, pushing, and caching optimization for mobile-edge computing networks via soft actor–critic learning,”IEEE Internet Things J., vol. 11, no. 6, pp. 9269–9281, 2024

    work page 2024

  35. [35]

    Soft actor–critic algorithm featured residential demand response strategic bidding for load aggregators,

    Z. Zhang, Z. Chen, and W.-J. Lee, “Soft actor–critic algorithm featured residential demand response strategic bidding for load aggregators,” IEEE Trans. Ind. Appl., vol. 58, no. 4, pp. 4298–4308, 2022

    work page 2022

  36. [36]

    UA V-assisted real-time video transmission for vehicles: A soft ac- tor–critic DRL approach,

    D. Wu, L. Wang, M. Liang, Y . Kang, Q. Jiao, Y . Cheng, and J. Li, “UA V-assisted real-time video transmission for vehicles: A soft ac- tor–critic DRL approach,”IEEE Internet Things J., vol. 11, no. 8, pp. 14710–14726, 2024

    work page 2024