pith. sign in

arxiv: 2604.18961 · v1 · submitted 2026-04-21 · 💻 cs.RO · cs.CV

AI-Enabled Image-Based Hybrid Vision/Force Control of Tendon-Driven Aerial Continuum Manipulators

Shayan Sepahvand , Farrokh Janabi-Sharifi , Farhad Aghili This is my paper

Pith reviewed 2026-05-10 03:08 UTC · model grok-4.3

classification 💻 cs.RO cs.CV
keywords hybrid vision/force controltendon-driven continuum manipulatorsaerial robotsneural network controlvisual servoingsliding mode controlforce sensingimage-based control
0
0 comments X

The pith

An AI-enabled controller uses neural networks to achieve stable hybrid vision and force control for tendon-driven aerial continuum manipulators during physical contact.

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

The paper presents a control framework that lets tendon-driven aerial continuum robots interact autonomously with a static environment while keeping image features stable and tracking a desired contact force. It combines cascaded fast fixed-time sliding mode control with a radial basis function neural network that learns vision and force uncertainties online without any offline training. A graph neural network extracts line features from the eye-in-hand camera images to support visual servoing. The approach is built on constant-strain modeling of the arm as a coupled system in SE(3). Comparative simulations and experiments show it performs robustly against rigid-arm methods across different starting conditions and feature-extraction choices.

Core claim

The developed strategy combines the cascaded fast fixed-time sliding mode control and a radial basis function neural network to cope with the uncertainties in the image acquired by the eye-in-hand monocular camera and the measurements from the force sensing apparatus. This ensures rapid, online learning of the vision- and force-related uncertainties without requiring offline training. Features are extracted via a graph neural network architecture in a visual servoing framework using line features to concurrently track the desired normal interaction force during contact and regulate the image feature error.

What carries the argument

Cascaded fast fixed-time sliding mode control integrated with radial basis function neural network for online uncertainty compensation, plus graph neural network line-feature extraction, all resting on constant-strain SE(3) modeling of the coupled tendon-driven arm.

If this is right

  • The system achieves simultaneous force tracking and image-feature regulation without separate offline training phases.
  • Rapid online adaptation handles uncertainties from both the monocular camera and force sensor during interaction.
  • Comparative tests indicate greater robustness than rigid-arm aerial manipulation controllers across varied scenarios.
  • The framework supports autonomous physical tasks while stabilizing visual servoing errors.
  • Graph neural network feature extraction replaces heuristic line detectors and contributes directly to force control.

Where Pith is reading between the lines

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

  • The same online-learning structure might extend to tasks with slowly moving targets if the constant-strain model remains valid.
  • Replacing the graph neural network with other modern feature extractors could be tested directly for gains in extreme lighting.
  • Because the controller already separates vision and force uncertainty learning, adding torque or joint-angle sensing would be a straightforward next measurement.
  • Aerial deployment could reduce ground-robot reach limitations in inspection or assembly where flexible arms are useful.

Load-bearing premise

The constant-strain modeling accurately represents the arm dynamics during contact and the graph neural network reliably extracts line features under varying lighting and motion blur.

What would settle it

Experiments showing large persistent errors in force tracking or image-feature regulation when lighting changes or motion blur occurs would falsify the claim that the online neural learning and feature extraction suffice.

Figures

Figures reproduced from arXiv: 2604.18961 by Farhad Aghili, Farrokh Janabi-Sharifi, Shayan Sepahvand.

Figure 1
Figure 1. Figure 1: The schematic representation of the TD-ACM and the [PITH_FULL_IMAGE:figures/full_fig_p003_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: The block diagram of the proposed control scheme. [PITH_FULL_IMAGE:figures/full_fig_p004_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: The components of the experimental setup. [PITH_FULL_IMAGE:figures/full_fig_p007_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Simulation results: (a) and (b) line feature evolution; [PITH_FULL_IMAGE:figures/full_fig_p008_4.png] view at source ↗
Figure 6
Figure 6. Figure 6: Simulated responses: (a) and (b) line features; (c) [PITH_FULL_IMAGE:figures/full_fig_p008_6.png] view at source ↗
Figure 8
Figure 8. Figure 8: Contactless experimental tests: (a, b) the first initial [PITH_FULL_IMAGE:figures/full_fig_p009_8.png] view at source ↗
Figure 7
Figure 7. Figure 7: 3D visualization of the TD-ACM. The dashed blue [PITH_FULL_IMAGE:figures/full_fig_p009_7.png] view at source ↗
Figure 9
Figure 9. Figure 9: Contactless experiment results for the second sce [PITH_FULL_IMAGE:figures/full_fig_p010_9.png] view at source ↗
Figure 10
Figure 10. Figure 10: Contact experiment results: (a, b) first ground test [PITH_FULL_IMAGE:figures/full_fig_p010_10.png] view at source ↗
Figure 11
Figure 11. Figure 11: The interaction wrench for the first contact experi [PITH_FULL_IMAGE:figures/full_fig_p011_11.png] view at source ↗
Figure 12
Figure 12. Figure 12: Camera views from the ground contact tests: (a) first [PITH_FULL_IMAGE:figures/full_fig_p011_12.png] view at source ↗
read the original abstract

This paper presents an AI-enabled cascaded hybrid vision/force control framework for tendon-driven aerial continuum manipulators based on constant-strain modeling in $SE(3)$ as a coupled system. The proposed controller is designed to enable autonomous, physical interaction with a static environment while stabilizing the image feature error. The developed strategy combines the cascaded fast fixed-time sliding mode control and a radial basis function neural network to cope with the uncertainties in the image acquired by the eye-in-hand monocular camera and the measurements from the force sensing apparatus. This ensures rapid, online learning of the vision- and force-related uncertainties without requiring offline training. Furthermore, the features are extracted via a state-of-the-art graph neural network architecture employed by a visual servoing framework using line features, rather than relying on heuristic geometric line extractors, to concurrently contribute to tracking the desired normal interaction force during contact and regulating the image feature error. A comparative study benchmarks the proposed controller against established rigid-arm aerial manipulation methods, evaluating robustness across diverse scenarios and feature extraction strategies. The simulation and experimental results showcase the effectiveness of the proposed methodology under various initial conditions and demonstrate robust performance in executing manipulation tasks.

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 / 2 minor

Summary. The manuscript proposes an AI-enabled cascaded hybrid vision/force control framework for tendon-driven aerial continuum manipulators. It relies on constant-strain modeling in SE(3) treated as a coupled system to derive the dynamics. The controller combines cascaded fast fixed-time sliding mode control with a radial basis function neural network (RBFNN) for online compensation of uncertainties arising from eye-in-hand monocular vision and force sensing. Line features are extracted using a graph neural network (GNN) within a visual servoing loop. The approach targets autonomous physical interaction with static environments while regulating image-feature errors and normal contact forces. Effectiveness is asserted via comparative simulations and experiments against rigid-arm aerial manipulation baselines under varied initial conditions and scenarios.

Significance. If the modeling assumptions and stability properties hold, the work would advance aerial manipulation by extending hybrid vision/force control to continuum arms, which offer greater compliance than rigid manipulators. The synthesis of fixed-time SMC for rapid convergence, RBFNN for online uncertainty adaptation without offline training, and GNN-based feature extraction for robustness to lighting and blur constitutes a coherent integration of classical control and learning-based methods. The explicit comparative benchmarking against established rigid-arm approaches is a clear strength that helps situate the contribution. The result could enable more dexterous tasks in unstructured settings, provided the unmodeled dynamics under contact remain dominated by the adaptation.

major comments (2)
  1. [Modeling section] Modeling section (constant-strain SE(3) coupled dynamics): The central derivation of the hybrid controller and its stability properties rests on the constant-strain assumption. External contact forces on tendon-driven continuum arms typically produce non-uniform strain along the backbone, introducing unmodeled dynamics. The manuscript must either supply quantitative bounds on the resulting modeling error during physical interaction or demonstrate that the RBFNN adaptation reliably dominates these terms; otherwise the claimed rapid stabilization of image-feature error and normal-force tracking cannot be guaranteed.
  2. [Experimental and simulation results section] Experimental and simulation results section: While robustness across scenarios is asserted, the reported outcomes lack tabulated quantitative metrics (e.g., RMS tracking errors, settling times, force overshoot) with standard deviations or statistical significance tests. Without these, it is difficult to substantiate the superiority claims over the rigid-arm baselines or to confirm that the online learning indeed achieves the stated rapid compensation.
minor comments (2)
  1. [Abstract] The abstract would be strengthened by including one or two concrete performance figures (e.g., convergence time or error reduction) rather than qualitative statements of effectiveness.
  2. [Controller design] Notation for the cascaded sliding surfaces and the RBFNN weight-update laws should be cross-referenced explicitly to the vision and force subsystems to improve readability.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive and detailed comments, which have helped us improve the manuscript. We provide point-by-point responses to the major comments below, with indications of the revisions made.

read point-by-point responses

  1. Referee: [Modeling section] Modeling section (constant-strain SE(3) coupled dynamics): The central derivation of the hybrid controller and its stability properties rests on the constant-strain assumption. External contact forces on tendon-driven continuum arms typically produce non-uniform strain along the backbone, introducing unmodeled dynamics. The manuscript must either supply quantitative bounds on the resulting modeling error during physical interaction or demonstrate that the RBFNN adaptation reliably dominates these terms; otherwise the claimed rapid stabilization of image-feature error and normal-force tracking cannot be guaranteed.

    Authors: We acknowledge that the constant-strain assumption represents an approximation and that non-uniform strain can arise under external contact, potentially introducing unmodeled dynamics. The RBFNN is explicitly incorporated for online compensation of such uncertainties and disturbances without offline training. In the revised manuscript, we have expanded the modeling and stability sections to include additional discussion of this assumption's limitations, along with analysis showing that the adaptation law and fixed-time sliding-mode terms can dominate bounded modeling errors. The experimental results further demonstrate effective performance under contact. However, supplying explicit quantitative bounds on the modeling error would require a variable-strain model and additional theoretical/experimental work beyond the scope of the current study; we have noted this as a limitation and future direction. revision: partial

  2. Referee: [Experimental and simulation results section] Experimental and simulation results section: While robustness across scenarios is asserted, the reported outcomes lack tabulated quantitative metrics (e.g., RMS tracking errors, settling times, force overshoot) with standard deviations or statistical significance tests. Without these, it is difficult to substantiate the superiority claims over the rigid-arm baselines or to confirm that the online learning indeed achieves the stated rapid compensation.

    Authors: We agree that tabulated quantitative metrics with statistical measures would strengthen the results section. In the revised manuscript, we have added new tables in both the simulation and experimental results sections reporting RMS errors for image-feature tracking and force regulation, settling times, and force overshoot. These include mean values and standard deviations computed over multiple trials under varied initial conditions. We have also incorporated statistical significance tests (e.g., t-tests) comparing the proposed controller against the rigid-arm baselines to better substantiate the performance claims and the rapid compensation achieved by the online RBFNN learning. revision: yes

Circularity Check

0 steps flagged

No circularity: synthesis of established control and learning methods on stated modeling assumption

full rationale

The paper states its constant-strain SE(3) modeling assumption upfront and then synthesizes a cascaded fast fixed-time SMC with RBFNN for online uncertainty compensation plus GNN-based line feature extraction. No equation or performance claim reduces by construction to a fitted parameter or self-citation chain; the online adaptation is presented as a standard RBFNN property applied to the given model rather than a derived result that presupposes its own outputs. The comparative benchmarking and stability claims rest on external techniques (SMC, RBFNN, GNN) whose independence is not contradicted in the provided text.

Axiom & Free-Parameter Ledger

0 free parameters · 2 axioms · 0 invented entities

The central claim rests on the constant-strain SE(3) kinematic model being sufficiently accurate for control design and on the assumption that online RBFNN learning converges fast enough to compensate image and force uncertainties without destabilizing the closed loop. No explicit free parameters or invented entities are named in the abstract.

axioms (2)
  • domain assumption Constant-strain assumption in SE(3) accurately represents tendon-driven continuum arm kinematics and dynamics during contact.
    Invoked in the first sentence of the abstract as the modeling basis for the coupled system.
  • domain assumption Graph neural network extracts reliable line features from monocular images under motion and lighting variations without offline training.
    Stated as the feature extraction method that contributes to both force tracking and image regulation.

pith-pipeline@v0.9.0 · 5517 in / 1617 out tokens · 51269 ms · 2026-05-10T03:08:07.822884+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

40 extracted references · 40 canonical work pages

  1. [1]

    Past, present, and future of aerial robotic manipulators,

    A. Ollero, M. Tognon, A. Suarez, D. Lee, and A. Franchi, “Past, present, and future of aerial robotic manipulators,”IEEE Transactions on Robotics, vol. 38, no. 1, pp. 626–645, 2022

    work page 2022

  2. [2]

    Coupled dynamic modeling and control of aerial continuum manipulation systems,

    Z. Samadikhoshkho, S. Ghorbani, and F. Janabi-Sharifi, “Coupled dynamic modeling and control of aerial continuum manipulation systems,”Applied Sciences, vol. 11, no. 19, 2021

    work page 2021

  3. [3]

    Modeling and control of aerial continuum manipulation systems: A flying continuum robot paradigm,

    Z. Samadikhoshkho, S. Ghorbani, and F. Janabi-Sharifi, “Modeling and control of aerial continuum manipulation systems: A flying continuum robot paradigm,”IEEE Access, vol. 8, pp. 176883–176894, 2020

    work page 2020

  4. [4]

    High-performance coupled kinematics of aerial continuum manipulation systems for control applications,

    N. Amiri and F. Janabi-Sharifi, “High-performance coupled kinematics of aerial continuum manipulation systems for control applications,” Robotics and Autonomous Systems, vol. 192, p. 105021, 2025

    work page 2025

  5. [5]

    A dexterous and compliant aerial continuum manipulator for cluttered and constrained environments,

    R. Peng, Y . Wang, M. Lu, and P. Lu, “A dexterous and compliant aerial continuum manipulator for cluttered and constrained environments,” Nature Communications, vol. 16, p. 889, Jan 2025

    work page 2025

  6. [6]

    Compliant aerial manipulators: Toward a new generation of aerial robotic workers,

    T. Bartelds, A. Capra, S. Hamaza, S. Stramigioli, and M. Fumagalli, “Compliant aerial manipulators: Toward a new generation of aerial robotic workers,”IEEE Robotics and Automation Letters, vol. 1, no. 1, pp. 477–483, 2016

    work page 2016

  7. [7]

    Robust control and recursive modelling approach for hexarotor manipulator,

    H. Zamoum, Y . Bouzid, and M. Guiatni, “Robust control and recursive modelling approach for hexarotor manipulator,”Proceedings of the Institution of Mechanical Engineers, Part I: Journal of Systems and Control Engineering, vol. 237, no. 8, pp. 1389–1410, 2023

    work page 2023

  8. [8]

    A hybrid modelling approach for aerial manipulators,

    P. Kremer, J. L. Sanchez-Lopez, and H. V oos, “A hybrid modelling approach for aerial manipulators,”Journal of Intelligent & Robotic Systems, vol. 105, p. 74, Jul 2022

    work page 2022

  9. [9]

    Flying vines: Design, modeling, and control of a soft aerial robotic arm,

    R. Jitosho, C. E. Winston, S. Yang, J. Li, M. Ahlquist, N. J. Woehrle, C. K. Liu, and A. M. Okamura, “Flying vines: Design, modeling, and control of a soft aerial robotic arm,”IEEE Robotics and Automation Letters, vol. 10, no. 10, pp. 10514–10521, 2025

    work page 2025

  10. [10]

    Dual-arm aerial continuum manipulation systems: modeling, pre-grasp planning, and control,

    S. Ghorbani, Z. Samadikhoshkho, and F. Janabi-Sharifi, “Dual-arm aerial continuum manipulation systems: modeling, pre-grasp planning, and control,”Nonlinear Dynamics, vol. 111, pp. 7339–7355, Apr 2023

    work page 2023

  11. [11]

    Physical-virtual impedance con- trol in ultralightweight and compliant dual-arm aerial manipulators,

    A. Suarez, G. Heredia, and A. Ollero, “Physical-virtual impedance con- trol in ultralightweight and compliant dual-arm aerial manipulators,” IEEE Robotics and Automation Letters, vol. 3, no. 3, pp. 2553–2560, 2018

    work page 2018

  12. [12]

    Adaptive stiffness estimation impedance control for achieving sustained contact in aerial manipulation,

    L. Markovi ´c, M. Car, M. Orsag, and S. Bogdan, “Adaptive stiffness estimation impedance control for achieving sustained contact in aerial manipulation,” in2021 IEEE International Conference on Robotics and Automation (ICRA), pp. 117–123, 2021

    work page 2021

  13. [13]

    Direct force feedback control and online multi-task optimization for aerial manipulators,

    G. Nava, Q. Sabl ´e, M. Tognon, D. Pucci, and A. Franchi, “Direct force feedback control and online multi-task optimization for aerial manipulators,”IEEE Robotics and Automation Letters, vol. 5, no. 2, pp. 331–338, 2020

    work page 2020

  14. [14]

    Aerial manipulation using hybrid force and position nmpc applied to aerial writing,

    D. Tzoumanikas, F. Graule, Q. Yan, D. Shah, M. Popovic, and S. Leutenegger, “Aerial manipulation using hybrid force and position nmpc applied to aerial writing,”arXiv preprint arXiv:2006.02116, 2020

    work page arXiv 2006

  15. [15]

    Image- based visual servo control for aerial manipulation using a fully-actuated uav,

    G. He, Y . Jangir, J. Geng, M. Mousaei, D. Bai, and S. Scherer, “Image- based visual servo control for aerial manipulation using a fully-actuated uav,” in2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 5042–5049, 2023

    work page 2023

  16. [16]

    Corke,Vision-Based Control, ch

    P. Corke,Vision-Based Control, ch. 16. Springer Berlin Heidelberg, 2023

    work page 2023

  17. [17]

    Comparison of basic visual servoing methods,

    F. Janabi-Sharifi, L. Deng, and W. J. Wilson, “Comparison of basic visual servoing methods,”IEEE/ASME Transactions on Mechatronics, vol. 16, no. 5, pp. 967–983, 2011

    work page 2011

  18. [18]

    Robust image-based visual servoing of an aerial robot using self- organizing neural networks,

    S. Sepahvand, F. Janabi-Sharifi, H. Masnavi, F. Aghili, and N. Amiri, “Robust image-based visual servoing of an aerial robot using self- organizing neural networks,”International Journal of Control, Automa- tion and Systems, vol. 22, pp. 3762–3776, Dec 2024

    work page 2024

  19. [19]

    Image-based time-varying contact force control of aerial manipulator using robust impedance filter,

    J. Byun, J. Kim, D. Eom, D. Lee, C. Kim, and H. J. Kim, “Image-based time-varying contact force control of aerial manipulator using robust impedance filter,”IEEE Robotics and Automation Letters, vol. 9, no. 5, pp. 4854–4861, 2024

    work page 2024

  20. [20]

    Image-based visual impedance force control for contact aerial manipulation,

    M. Xu, A. Hu, and H. Wang, “Image-based visual impedance force control for contact aerial manipulation,”IEEE Transactions on Au- tomation Science and Engineering, vol. 20, no. 1, pp. 518–527, 2023

    work page 2023

  21. [21]

    Dynamic image-based impedance control of aerial manipula- tor for sliding inspection,

    Y . Wu, Y . Chen, G. Zeng, C. Shang, Z. Miao, H. Wang, Y . Wang, and Q. Shen, “Dynamic image-based impedance control of aerial manipula- tor for sliding inspection,”IEEE/ASME Transactions on Mechatronics, vol. 29, no. 6, pp. 4075–4086, 2024

    work page 2024

  22. [22]

    Autonomous con- trol design of an unmanned aerial manipulator for contact inspection,

    J. Zeng, H. Zhong, Y . Wang, S. Fan, and H. Zhang, “Autonomous con- trol design of an unmanned aerial manipulator for contact inspection,” Robotica, vol. 41, no. 4, p. 1145–1158, 2023

    work page 2023

  23. [23]

    Keypoint detection tech- nique for image-based visual servoing of manipulators,

    N. Amiri, G. Wang, and F. Janabi-Sharifi, “Keypoint detection tech- nique for image-based visual servoing of manipulators,” in2024 IEEE 20th International Conference on Automation Science and Engineering (CASE), pp. 3557–3562, 2024

    work page 2024

  24. [24]

    Point-line feature-based vslam systems: A survey,

    H. Qu, Z. Hu, Y . Zhao, J. Lu, K. Ding, G. Liu, Y . Chen, and C. Shao, “Point-line feature-based vslam systems: A survey,”Expert Systems with Applications, vol. 289, p. 127574, 2025

    work page 2025

  25. [25]

    Gluestick: Robust image matching by sticking points and lines together,

    R. Pautrat, I. Su ´arez, Y . Yu, M. Pollefeys, and V . Larsson, “Gluestick: Robust image matching by sticking points and lines together,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 9706–9716, 2023

    work page 2023

  26. [26]

    Discrete cosserat approach for multisection soft manipulator dynamics,

    F. Renda, F. Boyer, J. Dias, and L. Seneviratne, “Discrete cosserat approach for multisection soft manipulator dynamics,”IEEE Transac- tions on Robotics, vol. 34, no. 6, pp. 1518–1533, 2018

    work page 2018

  27. [27]

    Dynamic modeling of tendon-driven co-manipulative continuum robots,

    A. Jalali and F. Janabi-Sharifi, “Dynamic modeling of tendon-driven co-manipulative continuum robots,”IEEE Robotics and Automation Letters, vol. 7, no. 2, pp. 1643–1650, 2022

    work page 2022

  28. [28]

    Se(3)-equivariant robot learning and con- trol: A tutorial survey,

    J. Seo, S. Yoo, J. Chang, H. An, H. Ryu, S. Lee, A. Kruthiventy, J. Choi, and R. Horowitz, “Se(3)-equivariant robot learning and con- trol: A tutorial survey,”International Journal of Control, Automation and Systems, vol. 23, pp. 1271–1306, May 2025

    work page 2025

  29. [29]

    Robust cascade vision/force control of industrial robots utilizing continuous integral sliding-mode 12 control method,

    B. Ahmadi, W.-F. Xie, and E. Zakeri, “Robust cascade vision/force control of industrial robots utilizing continuous integral sliding-mode 12 control method,”IEEE/ASME Transactions on Mechatronics, vol. 27, no. 1, pp. 524–536, 2022

    work page 2022

  30. [30]

    Apostol,Mathematical Analysis

    T. Apostol,Mathematical Analysis. Addison-Wesley series in mathe- matics, Addison-Wesley, 1974

    work page 1974

  31. [31]

    Dynamics and control of soft robots with implicit strain parametrization,

    F. Renda, A. Mathew, and D. F. Talegon, “Dynamics and control of soft robots with implicit strain parametrization,”IEEE Robotics and Automation Letters, vol. 9, no. 3, pp. 2782–2789, 2024

    work page 2024

  32. [32]

    Superpoint: Self- supervised interest point detection and description,

    D. DeTone, T. Malisiewicz, and A. Rabinovich, “Superpoint: Self- supervised interest point detection and description,” in2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 337–33712, 2018

    work page 2018

  33. [33]

    Impact analysis for the planning of targeted non-slippage impacts of robot manipulators,

    A. Kirner and C. Ott, “Impact analysis for the planning of targeted non-slippage impacts of robot manipulators,”IEEE Robotics and Automation Letters, vol. 9, no. 3, pp. 2750–2757, 2024

    work page 2024

  34. [34]

    Finite-time stability of continuous autonomous systems,

    S. P. Bhat and D. S. Bernstein, “Finite-time stability of continuous autonomous systems,”SIAM Journal on Control and Optimization, vol. 38, no. 3, pp. 751–766, 2000

    work page 2000

  35. [35]

    Nonlinear feedback design for fixed-time stabilization of linear control systems,

    A. Polyakov, “Nonlinear feedback design for fixed-time stabilization of linear control systems,”IEEE Transactions on Automatic Control, vol. 57, no. 8, pp. 2106–2110, 2012

    work page 2012

  36. [36]

    Non-singular fixed-time terminal sliding mode control of non- linear systems,

    Z. Zuo, “Non-singular fixed-time terminal sliding mode control of non- linear systems,”IET Control Theory & Applications, vol. 9, no. 4, pp. 545–552, 2015

    work page 2015

  37. [37]

    Siciliano, L

    B. Siciliano, L. Sciavicco, L. Villani, and G. Oriolo,Robotics: Modelling, Planning and Control. Springer Publishing Company, Incorporated, 1st ed., 2008

    work page 2008

  38. [38]

    Elm-based adaptive faster fixed-time control of robotic manipulator systems,

    M. Gao, L. Ding, and X. Jin, “Elm-based adaptive faster fixed-time control of robotic manipulator systems,”IEEE Transactions on Neural Networks and Learning Systems, vol. 34, no. 8, pp. 4646–4658, 2023

    work page 2023

  39. [39]

    Vision-guided aerial manipulation using a multirotor with a robotic arm,

    S. Kim, H. Seo, S. Choi, and H. J. Kim, “Vision-guided aerial manipulation using a multirotor with a robotic arm,”IEEE/ASME Transactions on Mechatronics, vol. 21, no. 4, pp. 1912–1923, 2016

    work page 1912

  40. [40]

    Intelligent interaction control for aerial manipulator: integrating visual servoing and continuous characteristic model,

    B. Xiu, J. Yun, Y . Yang, J. Liu, T. Wu, and Z. Li, “Intelligent interaction control for aerial manipulator: integrating visual servoing and continuous characteristic model,”Nonlinear Dynamics, vol. 114, p. 23, Dec 2025

    work page 2025