pith. sign in

arxiv: 2503.21491 · v1 · submitted 2025-03-27 · 💻 cs.RO · cs.SY· eess.SY

Data-Driven Contact-Aware Control Method for Real-Time Deformable Tool Manipulation: A Case Study in the Environmental Swabbing

Siavash Mahmoudi , Amirreza Davar , Dongyi Wang This is my paper

Pith reviewed 2026-05-22 22:33 UTC · model grok-4.3

classification 💻 cs.RO cs.SYeess.SY
keywords deformable object manipulationKoopman operator controlLQRcontact force regulationtactile sensingenvironmental swabbingfood safetyrobotic manipulation
0
0 comments X

The pith

A state-adaptive Koopman LQR framework allows robots to manipulate deformable tools like swabs in real time by linearizing their dynamics and adapting to contact changes.

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

The paper introduces the SA-KLQR control method to handle the challenges of deforming tools in contact with environments, using a case study of swab sampling for food safety. It applies the Koopman operator to turn nonlinear tool behaviors into linear ones for LQR control and adds adaptation for varying states of deformation and force. Tactile sensing regulates the tool's angle, pressure, and coverage while a force sensor prevents unwanted pivoting. A reader would care because this data-driven approach could let robots perform precise tasks with soft tools where traditional modeling fails due to unpredictable interactions.

Core claim

The SA-KLQR framework linearizes nonlinear dynamics of a deformable tool using the Koopman operator and adapts to state-dependent variations in deformation and contact forces, allowing accurate estimation and regulation of contact angle, pressure, and surface coverage in real-time environmental swabbing without an explicit physics model of the interaction.

What carries the argument

The State-Adaptive Koopman LQR (SA-KLQR) framework, which combines Koopman-based linearization with a state-adaptive layer to manage changes in tool deformation and contact forces during manipulation.

If this is right

  • Accurate contact angle estimation and regulation is achieved during dynamic interactions with the surface.
  • Robust trajectory tracking and reliable force regulation is demonstrated in the swab sampling experiments.
  • Tool pivoting and deformation is mitigated through monitoring of force distribution on the contact pad.
  • Compliance with food safety standards is supported by controlled surface coverage in the task.

Where Pith is reading between the lines

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

  • The approach could extend to other contact tasks involving deformable tools such as wiping or polishing surfaces if the adaptation generalizes across different materials.
  • By avoiding explicit physics models, the method might lower the barrier for deploying robots in varied real-world settings where tool properties are hard to model.
  • Integration with additional sensors like cameras could further enhance the estimation of surface coverage beyond tactile data alone.

Load-bearing premise

The Koopman operator and state-adaptive layer can capture the essential variations in the tool's nonlinear dynamics and contact behavior from data without needing a detailed physical description of how the tool deforms against different surfaces.

What would settle it

A test where the controller is applied to a swab tool on a surface with different friction or stiffness than the training data, resulting in loss of stable contact angle or excessive force variation, would show the limits of the linearization.

Figures

Figures reproduced from arXiv: 2503.21491 by Amirreza Davar, Dongyi Wang, Siavash Mahmoudi.

Figure 1
Figure 1. Figure 1: Swab sampling collection model with deformable sponge stick [PITH_FULL_IMAGE:figures/full_fig_p002_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: The robotic system setup consists of two different contact sensors [PITH_FULL_IMAGE:figures/full_fig_p003_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Contact angle alignment task: (a) step 1: initial position of trajectory [PITH_FULL_IMAGE:figures/full_fig_p003_3.png] view at source ↗
Figure 5
Figure 5. Figure 5: Control scheme of the proposed overall framework [PITH_FULL_IMAGE:figures/full_fig_p004_5.png] view at source ↗
Figure 7
Figure 7. Figure 7: Region-Based Koopman Segmentation Along the Zigzag Trajectory: [PITH_FULL_IMAGE:figures/full_fig_p006_7.png] view at source ↗
Figure 6
Figure 6. Figure 6: End-effector rolling angle and Koopman-based force regulation for [PITH_FULL_IMAGE:figures/full_fig_p006_6.png] view at source ↗
Figure 9
Figure 9. Figure 9: Koopman-based prediction of end-effector states, including roll angle [PITH_FULL_IMAGE:figures/full_fig_p008_9.png] view at source ↗
Figure 10
Figure 10. Figure 10: Prediction of sensor output in the wet sponge scenario. [PITH_FULL_IMAGE:figures/full_fig_p008_10.png] view at source ↗
Figure 11
Figure 11. Figure 11: Force tracking performance comparison among SA-KLQR, PID, [PITH_FULL_IMAGE:figures/full_fig_p009_11.png] view at source ↗
Figure 12
Figure 12. Figure 12: Absolute force tracking error comparison for low-frequency (left) [PITH_FULL_IMAGE:figures/full_fig_p009_12.png] view at source ↗
Figure 13
Figure 13. Figure 13: Force tracking performance and absolute error comparison for a [PITH_FULL_IMAGE:figures/full_fig_p010_13.png] view at source ↗
Figure 14
Figure 14. Figure 14: Rolling Angle Error with and Without Centroid Algorithm. The [PITH_FULL_IMAGE:figures/full_fig_p010_14.png] view at source ↗
Figure 15
Figure 15. Figure 15: Effect of Tool Distortion Due to Force Misalignment. (Left) [PITH_FULL_IMAGE:figures/full_fig_p011_15.png] view at source ↗
read the original abstract

Deformable Object Manipulation (DOM) remains a critical challenge in robotics due to the complexities of developing suitable model-based control strategies. Deformable Tool Manipulation (DTM) further complicates this task by introducing additional uncertainties between the robot and its environment. While humans effortlessly manipulate deformable tools using touch and experience, robotic systems struggle to maintain stability and precision. To address these challenges, we present a novel State-Adaptive Koopman LQR (SA-KLQR) control framework for real-time deformable tool manipulation, demonstrated through a case study in environmental swab sampling for food safety. This method leverages Koopman operator-based control to linearize nonlinear dynamics while adapting to state-dependent variations in tool deformation and contact forces. A tactile-based feedback system dynamically estimates and regulates the swab tool's angle, contact pressure, and surface coverage, ensuring compliance with food safety standards. Additionally, a sensor-embedded contact pad monitors force distribution to mitigate tool pivoting and deformation, improving stability during dynamic interactions. Experimental results validate the SA-KLQR approach, demonstrating accurate contact angle estimation, robust trajectory tracking, and reliable force regulation. The proposed framework enhances precision, adaptability, and real-time control in deformable tool manipulation, bridging the gap between data-driven learning and optimal control in robotic interaction 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 / 1 minor

Summary. The manuscript presents a State-Adaptive Koopman LQR (SA-KLQR) framework for real-time deformable tool manipulation, using a case study in environmental swab sampling. It employs a Koopman operator to linearize nonlinear dynamics of the deformable tool, augments this with a state-adaptive layer to handle variations in deformation and contact forces, incorporates tactile feedback to estimate and regulate contact angle, pressure, and surface coverage, and uses a sensor-embedded pad to monitor force distribution and mitigate pivoting. The abstract claims that experiments validate accurate angle estimation, trajectory tracking, and force regulation.

Significance. If the central claims hold with quantitative support, the work would demonstrate a data-driven, model-free approach to contact-aware control of deformable tools that combines Koopman linearization with state adaptation and LQR, offering a practical bridge between learning-based methods and optimal control for hybrid contact-deformation tasks in robotics applications such as food safety.

major comments (2)
  1. [Abstract] Abstract: the claim that 'experimental results validate ... accurate contact angle estimation, robust trajectory tracking, and reliable force regulation' supplies no quantitative metrics (e.g., RMSE, mean error, success rate), error bars, baseline comparisons, or description of Koopman model identification and cross-validation procedure, rendering the performance assertions impossible to evaluate.
  2. [Abstract] Abstract / Methods (Koopman and adaptation sections): the central claim requires that the learned Koopman operator plus state-adaptive layer produces a reliable linear representation of hybrid contact/deformation dynamics; however, no evidence is supplied that the operator was tested for prediction accuracy on unseen contact transitions or that the adaptation mechanism was derived beyond heuristic tuning, leaving the handling of discontinuous modes unverified.
minor comments (1)
  1. [Abstract] The abstract would be strengthened by including at least one concrete performance number (e.g., angle estimation error) to support the validation statement.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive feedback on our manuscript. We address each major comment below and have revised the manuscript to strengthen the presentation of quantitative results and model validation details.

read point-by-point responses

  1. Referee: [Abstract] Abstract: the claim that 'experimental results validate ... accurate contact angle estimation, robust trajectory tracking, and reliable force regulation' supplies no quantitative metrics (e.g., RMSE, mean error, success rate), error bars, baseline comparisons, or description of Koopman model identification and cross-validation procedure, rendering the performance assertions impossible to evaluate.

    Authors: We agree that the abstract would be improved by including quantitative metrics to support the performance claims. The experimental results section of the manuscript reports specific metrics including angle estimation errors, trajectory tracking RMSE, and force regulation accuracy across multiple trials. We have revised the abstract to incorporate these key quantitative results along with a concise description of the Koopman operator identification via dynamic mode decomposition and the associated cross-validation procedure. revision: yes

  2. Referee: [Abstract] Abstract / Methods (Koopman and adaptation sections): the central claim requires that the learned Koopman operator plus state-adaptive layer produces a reliable linear representation of hybrid contact/deformation dynamics; however, no evidence is supplied that the operator was tested for prediction accuracy on unseen contact transitions or that the adaptation mechanism was derived beyond heuristic tuning, leaving the handling of discontinuous modes unverified.

    Authors: The case study experiments include varied contact scenarios that encompass transitions between free motion and surface contact, with the overall closed-loop performance providing indirect validation of the linear representation. We acknowledge the value of explicit prediction tests on held-out transition data. We have added details in the methods section on the state-adaptive layer derivation from collected trajectory data and included prediction accuracy metrics on unseen segments to better verify handling of discontinuous modes. revision: partial

Circularity Check

0 steps flagged

No circularity: derivation relies on external data-driven validation without self-referential reductions

full rationale

The abstract and description present the SA-KLQR framework as a data-driven approach that learns a Koopman operator from experimental data on swab-tool interactions and validates it through real-time control experiments measuring angle estimation, trajectory tracking, and force regulation. No equations, fitted parameters renamed as predictions, self-citations as load-bearing uniqueness theorems, or ansatzes smuggled via prior work are visible in the provided text. The method is described as leveraging Koopman linearization with state adaptation, but the performance claims are tied to empirical results on the target task rather than reducing by construction to the training inputs themselves. This leaves the derivation self-contained against external benchmarks.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Abstract-only review supplies no explicit equations, so free parameters, axioms, and invented entities cannot be enumerated. The central claim implicitly rests on the unstated premise that a finite-dimensional Koopman approximation exists and remains stable under contact variations.

pith-pipeline@v0.9.0 · 5774 in / 1278 out tokens · 36818 ms · 2026-05-22T22:33:33.008701+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

49 extracted references · 49 canonical work pages

  1. [1]

    Challenges and outlook in robotic manipulation of deformable objects,

    J. Zhu, A. Cherubini, C. Dune, D. Navarro-Alarcon, F. Alambeigi, D. Berenson, F. Ficuciello, K. Harada, J. Kober, X. Li, J. Pan, W. Yuan, and M. Gienger, “Challenges and outlook in robotic manipulation of deformable objects,” IEEE Robotics & Automation Magazine , vol. 29, no. 3, pp. 67–77, 2022

    work page 2022

  2. [2]

    Modeling, learning, perception, and control methods for deformable object manipulation,

    H. Yin, A. Varava, and D. Kragic, “Modeling, learning, perception, and control methods for deformable object manipulation,” Science Robotics, vol. 6, no. 54, p. eabd8803, 2021

    work page 2021

  3. [3]

    Quasi-static modeling and controlling for planar pushing of deformable objects,

    L. Han, Y . Liu, and H. Wang, “Quasi-static modeling and controlling for planar pushing of deformable objects,” IEEE Transactions on Robotics , pp. 1–20, 2025

    work page 2025

  4. [4]

    Flexible simulation of deformable models using discontinuous galerkin fem,

    P. Kaufmann, S. Martin, M. Botsch, and M. Gross, “Flexible simulation of deformable models using discontinuous galerkin fem,” Graphical Models, vol. 71, no. 4, pp. 153–167, 2009

    work page 2009

  5. [5]

    Neural network mapping and clustering of elastic behavior from tactile and range imaging for virtualized reality applications,

    A.-M. Cretu, P. Payeur, and E. M. Petriu, “Neural network mapping and clustering of elastic behavior from tactile and range imaging for virtualized reality applications,” IEEE Transactions on Instrumentation and Measurement, vol. 57, no. 9, pp. 1918–1928, 2008

    work page 1918

  6. [6]

    Shape control of deformable linear objects with offline and online learning of local linear deformation models,

    M. Yu, H. Zhong, and X. Li, “Shape control of deformable linear objects with offline and online learning of local linear deformation models,” in 2022 International Conference on Robotics and Automation (ICRA) . IEEE, 2022, pp. 1337–1343

    work page 2022

  7. [7]

    Dexdlo: Learning goal-conditioned dexterous policy for dynamic manipulation of deformable linear objects,

    S. Zhaole, J. Zhu, and R. B. Fisher, “Dexdlo: Learning goal-conditioned dexterous policy for dynamic manipulation of deformable linear objects,” in 2024 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 2024, pp. 16 009–16 015

    work page 2024

  8. [8]

    Learning deformable object manipulation from expert demonstrations,

    G. Salhotra, I.-C. A. Liu, M. Dominguez-Kuhne, and G. S. Sukhatme, “Learning deformable object manipulation from expert demonstrations,” IEEE Robotics and Automation Letters , vol. 7, no. 4, pp. 8775–8782, 2022

    work page 2022

  9. [9]

    Multifingered robot hand compliant manipulation based on vision-based demonstration and adaptive force control,

    C. Zeng, S. Li, Z. Chen, C. Yang, F. Sun, and J. Zhang, “Multifingered robot hand compliant manipulation based on vision-based demonstration and adaptive force control,” IEEE Transactions on Neural Networks and Learning Systems , vol. 34, no. 9, pp. 5452–5463, 2023

    work page 2023

  10. [10]

    Efficient planar fabric repositioning: Deformation-aware rrt* for non-prehensile fabric manipulation,

    Y . Wang, L. Yang, P. Zhou, J. Qi, L. Lu, J. Zhu, and J. Pan, “Efficient planar fabric repositioning: Deformation-aware rrt* for non-prehensile fabric manipulation,” IEEE Robotics and Automation Letters , 2024

    work page 2024

  11. [11]

    A soft, sensorized gripper for delicate harvesting of small fruits,

    F. Visentin, F. Castellini, and R. Muradore, “A soft, sensorized gripper for delicate harvesting of small fruits,” Computers and Electronics in Agriculture, vol. 213, p. 108202, 2023

    work page 2023

  12. [12]

    Factors affecting human hand grasp type in tomato fruit-picking: A statistical investigation for ergonomic development of harvesting robot,

    Z. Li, F. Miao, Z. Yang, P. Chai, and S. Yang, “Factors affecting human hand grasp type in tomato fruit-picking: A statistical investigation for ergonomic development of harvesting robot,” Computers and electronics in agriculture, vol. 157, pp. 90–97, 2019

    work page 2019

  13. [13]

    Real-to-sim registration of deformable soft tissue with position-based dynamics for surgical robot autonomy,

    F. Liu, Z. Li, Y . Han, J. Lu, F. Richter, and M. C. Yip, “Real-to-sim registration of deformable soft tissue with position-based dynamics for surgical robot autonomy,” in 2021 IEEE International Conference on Robotics and Automation (ICRA) . IEEE, 2021, pp. 12 328–12 334

    work page 2021

  14. [14]

    Robotic manipulation of deformable rope-like objects using differentiable compliant position- based dynamics,

    F. Liu, E. Su, J. Lu, M. Li, and M. C. Yip, “Robotic manipulation of deformable rope-like objects using differentiable compliant position- based dynamics,” IEEE Robotics and Automation Letters , vol. 8, no. 7, pp. 3964–3971, 2023

    work page 2023

  15. [15]

    Re- form: A robot learning sandbox for deformable linear object ma- nipulation,

    R. Laezza, R. Gieselmann, F. T. Pokorny, and Y . Karayiannidis, “Re- form: A robot learning sandbox for deformable linear object ma- nipulation,” in 2021 IEEE International Conference on Robotics and Automation (ICRA) . IEEE, 2021, pp. 4717–4723

    work page 2021

  16. [16]

    Robots under covid-19 pandemic: A comprehensive survey,

    Y . Shen, D. Guo, F. Long, L. A. Mateos, H. Ding, Z. Xiu, R. B. Hellman, A. King, S. Chen, C. Zhang et al. , “Robots under covid-19 pandemic: A comprehensive survey,” Ieee Access , vol. 9, pp. 1590–1615, 2020

    work page 2020

  17. [17]

    Leveraging imitation learning in agricultural robotics: a comprehensive survey and comparative analysis,

    S. Mahmoudi, A. Davar, P. Sohrabipour, R. B. Bist, Y . Tao, and D. Wang, “Leveraging imitation learning in agricultural robotics: a comprehensive survey and comparative analysis,” Frontiers in Robotics and AI , vol. 11, p. 1441312, 2024

    work page 2024

  18. [18]

    A survey on deep reinforcement learning algorithms for robotic manipulation,

    D. Han, B. Mulyana, V . Stankovic, and S. Cheng, “A survey on deep reinforcement learning algorithms for robotic manipulation,” Sensors, vol. 23, no. 7, p. 3762, 2023

    work page 2023

  19. [19]

    Imitation learning: Progress, taxonomies and challenges,

    B. Zheng, S. Verma, J. Zhou, I. W. Tsang, and F. Chen, “Imitation learning: Progress, taxonomies and challenges,” IEEE Transactions on Neural Networks and Learning Systems , vol. 35, no. 5, pp. 6322–6337, 2024

    work page 2024

  20. [20]

    Contact force control on soft membrane for an ear surgical device,

    W. Liang, J. Ma, and K. K. Tan, “Contact force control on soft membrane for an ear surgical device,” IEEE Transactions on Industrial Electronics , vol. 65, no. 12, pp. 9593–9603, 2018. JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2021 12

    work page 2018

  21. [21]

    Interaction con- trol for tool manipulation on deformable objects using tactile feedback,

    H. Zhang, Z. Lu, W. Liang, H. Yu, Y . Mao, and Y . Wu, “Interaction con- trol for tool manipulation on deformable objects using tactile feedback,” IEEE Robotics and Automation Letters , vol. 8, no. 5, pp. 2700–2707, 2023

    work page 2023

  22. [22]

    Task-oriented adaptive position/force control for robotic systems under hybrid constraints,

    S. Ding, J. Peng, J. Xin, H. Zhang, and Y . Wang, “Task-oriented adaptive position/force control for robotic systems under hybrid constraints,” IEEE Transactions on Industrial Electronics , 2024

    work page 2024

  23. [23]

    Spherical wrist with hybrid motion-impedance control for enhanced robotic manipula- tions,

    K. Bai, W. Chen, K.-M. Lee, Z. Que, and R. Huang, “Spherical wrist with hybrid motion-impedance control for enhanced robotic manipula- tions,” IEEE Transactions on Robotics , vol. 38, no. 2, pp. 1174–1185, 2021

    work page 2021

  24. [24]

    Model predictive interaction control for robotic manipulation tasks,

    T. Gold, A. V ¨olz, and K. Graichen, “Model predictive interaction control for robotic manipulation tasks,” IEEE Transactions on Robotics , vol. 39, no. 1, pp. 76–89, 2022

    work page 2022

  25. [25]

    A survey on robotic manipulation of deformable objects: Recent advances, open challenges and new frontiers,

    F. Gu, Y . Zhou, Z. Wang, S. Jiang, and B. He, “A survey on robotic manipulation of deformable objects: Recent advances, open challenges and new frontiers,” arXiv preprint arXiv:2312.10419 , 2023

    work page arXiv 2023

  26. [26]

    A kalman– koopman lqr control approach to robotic systems,

    D. Zhao, X. Yang, Y . Li, L. Xu, J. She, and S. Yan, “A kalman– koopman lqr control approach to robotic systems,” IEEE Transactions on Industrial Electronics , 2024

    work page 2024

  27. [27]

    Force-guided high- precision grasping control of fragile and deformable objects using semg- based force prediction,

    R. Wen, K. Yuan, Q. Wang, S. Heng, and Z. Li, “Force-guided high- precision grasping control of fragile and deformable objects using semg- based force prediction,” IEEE Robotics and Automation Letters , vol. 5, no. 2, pp. 2762–2769, 2020

    work page 2020

  28. [28]

    A sliding-mode control al- gorithm to enhance in-hand motion capabilities,

    R. Kumar, J. Mukherjee, and S. Mukherjee, “A sliding-mode control al- gorithm to enhance in-hand motion capabilities,” Journal of Mechanisms and Robotics , vol. 13, no. 3, p. 031013, 2021

    work page 2021

  29. [29]

    Viscoelastic modeling based force control framework for enhancing operation safety of soft tissue for orthopedic surgical robots,

    G. Xia, Z. Jiang, B. Yao, and Y . Dai, “Viscoelastic modeling based force control framework for enhancing operation safety of soft tissue for orthopedic surgical robots,” Computers in Biology and Medicine , vol. 183, p. 109291, 2024

    work page 2024

  30. [30]

    Modern koopman theory for dynamical systems

    S. L. Brunton, M. Budi ˇsi´c, E. Kaiser, and J. N. Kutz, “Modern koopman theory for dynamical systems,” arXiv preprint arXiv:2102.12086 , 2021

    work page arXiv 2021

  31. [31]

    Extending data-driven koopman analysis to actuated systems,

    M. O. Williams, M. S. Hemati, S. T. Dawson, I. G. Kevrekidis, and C. W. Rowley, “Extending data-driven koopman analysis to actuated systems,” IF AC-PapersOnLine, vol. 49, no. 18, pp. 704–709, 2016

    work page 2016

  32. [32]

    Generalizing koopman theory to allow for inputs and control,

    J. L. Proctor, S. L. Brunton, and J. N. Kutz, “Generalizing koopman theory to allow for inputs and control,” SIAM Journal on Applied Dynamical Systems , vol. 17, no. 1, pp. 909–930, 2018

    work page 2018

  33. [33]

    Koop- man invariant subspaces and finite linear representations of nonlinear dynamical systems for control,

    S. L. Brunton, B. W. Brunton, J. L. Proctor, and J. N. Kutz, “Koop- man invariant subspaces and finite linear representations of nonlinear dynamical systems for control,” PloS one , vol. 11, no. 2, p. e0150171, 2016

    work page 2016

  34. [34]

    Koopman operators in robot learning,

    L. Shi, M. Haseli, G. Mamakoukas, D. Bruder, I. Abraham, T. Murphey, J. Cortes, and K. Karydis, “Koopman operators in robot learning,” arXiv preprint arXiv:2408.04200, 2024

    work page arXiv 2024

  35. [35]

    Data-driven control of soft robots using koopman operator theory,

    D. Bruder, X. Fu, R. B. Gillespie, C. D. Remy, and R. Vasudevan, “Data-driven control of soft robots using koopman operator theory,” IEEE Transactions on Robotics , vol. 37, no. 3, pp. 948–961, 2020

    work page 2020

  36. [36]

    Active learning of dynamics for data-driven control using koopman operators,

    I. Abraham and T. D. Murphey, “Active learning of dynamics for data-driven control using koopman operators,” IEEE Transactions on Robotics, vol. 35, no. 5, pp. 1071–1083, 2019

    work page 2019

  37. [37]

    Derivative-based koopman operators for real-time control of robotic systems,

    G. Mamakoukas, M. L. Castano, X. Tan, and T. D. Murphey, “Derivative-based koopman operators for real-time control of robotic systems,” IEEE Transactions on Robotics, vol. 37, no. 6, pp. 2173–2192, 2021

    work page 2021

  38. [38]

    Koopman-operator-based robust data-driven control for wheeled mobile robots,

    C. Ren, H. Jiang, C. Li, W. Sun, and S. Ma, “Koopman-operator-based robust data-driven control for wheeled mobile robots,” IEEE/ASME Transactions on Mechatronics , vol. 28, no. 1, pp. 461–472, 2022

    work page 2022

  39. [39]

    Resolution enhancement method used for force sensing resistor array,

    K. Flores De Jesus, M. H. Cheng, L. Jiang, and E. G. Bakhoum, “Resolution enhancement method used for force sensing resistor array,” Journal of Sensors , vol. 2015, no. 1, p. 647427, 2015

    work page 2015

  40. [40]

    Methods for recovering microorganisms from solid surfaces used in the food industry: a review of the literature,

    R. Isma ¨ıl, F. Aviat, V . Michel, I. Le Bayon, P. Gay-Perret, M. Kutnik, and M. F ´ed´erighi, “Methods for recovering microorganisms from solid surfaces used in the food industry: a review of the literature,” Inter- national journal of environmental research and public health , vol. 10, no. 11, pp. 6169–6183, 2013

    work page 2013

  41. [41]

    Nonlinear system identifi- cation of soft robot dynamics using koopman operator theory,

    D. Bruder, C. D. Remy, and R. Vasudevan, “Nonlinear system identifi- cation of soft robot dynamics using koopman operator theory,” in 2019 International Conference on Robotics and Automation (ICRA) . IEEE, 2019, pp. 6244–6250

    work page 2019

  42. [42]

    Linear identification of nonlinear systems: A lifting technique based on the koopman operator,

    A. Mauroy and J. Goncalves, “Linear identification of nonlinear systems: A lifting technique based on the koopman operator,” in 2016 IEEE 55th Conference on Decision and Control (CDC) . IEEE, 2016, pp. 6500– 6505

    work page 2016

  43. [43]

    A data–driven approximation of the koopman operator: Extending dynamic mode decomposition,

    M. O. Williams, I. G. Kevrekidis, and C. W. Rowley, “A data–driven approximation of the koopman operator: Extending dynamic mode decomposition,” Journal of Nonlinear Science , vol. 25, pp. 1307–1346, 2015

    work page 2015

  44. [44]

    Deep koopman operator with control for nonlinear systems,

    H. Shi and M. Q.-H. Meng, “Deep koopman operator with control for nonlinear systems,” IEEE Robotics and Automation Letters , vol. 7, no. 3, pp. 7700–7707, 2022

    work page 2022

  45. [45]

    Athans and P

    M. Athans and P. L. Falb, Optimal control: an introduction to the theory and its applications . Courier Corporation, 2007

    work page 2007

  46. [46]

    Fuzzy entropy: a brief survey,

    S. Al-Sharhan, F. Karray, W. Gueaieb, and O. Basir, “Fuzzy entropy: a brief survey,” in 10th IEEE international conference on fuzzy sys- tems.(Cat. No. 01CH37297) , vol. 3. IEEE, 2001, pp. 1135–1139

    work page 2001

  47. [47]

    A distributionally robust control strategy for frequency safety based on koopman operator described system model,

    Q. Cao and C. Shen, “A distributionally robust control strategy for frequency safety based on koopman operator described system model,” arXiv preprint arXiv:2411.04467 , 2024

    work page arXiv 2024

  48. [48]

    Discovering governing equations from data by sparse identification of nonlinear dynamical systems,

    S. L. Brunton, J. L. Proctor, and J. N. Kutz, “Discovering governing equations from data by sparse identification of nonlinear dynamical systems,” Proceedings of the national academy of sciences , vol. 113, no. 15, pp. 3932–3937, 2016

    work page 2016

  49. [49]

    Optimum settings for automatic con- trollers,

    J. G. Ziegler and N. B. Nichols, “Optimum settings for automatic con- trollers,” Transactions of the American society of mechanical engineers , vol. 64, no. 8, pp. 759–765, 1942

    work page 1942