pith. sign in

arxiv: 2605.12804 · v1 · pith:VZU46BZTnew · submitted 2026-05-12 · 💻 cs.RO

BiPneu: Design and Control of a Bipolar-Pressure Pneumatic System for Soft Robots

Yu Mei , Xinyu Zhou , Vedant Naik , Alan Gao , Xiaobo Tan This is my paper

Pith reviewed 2026-05-14 19:32 UTC · model grok-4.3

classification 💻 cs.RO
keywords soft roboticspneumatic actuationpressure controlsliding mode controlbipolar pressuresoft actuatorscontrol systems
0
0 comments X

The pith

BiPneu delivers a bipolar-pressure pneumatic system and dual-mode sliding-mode controller that tracks positive and negative pressure references with lower errors than PID or model predictive control.

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

The paper presents BiPneu, a multi-channel hardware system that regulates both positive and negative pressures for soft robotic actuators. It introduces a dual-mode sliding-mode controller (DM-SMC) built on a hybrid electro-pneumatic model to address asymmetric inflation-deflation behavior and valve switching effects. Experiments and simulations show the controller reduces average absolute tracking errors to 1.44 kPa in multi-step tests and 4.23 kPa in sinusoidal tests. These results represent 11.9 percent and 35.6 percent improvement over well-tuned PID control, with added gains in transient response and valve effort. The work matters because accurate bipolar pressure control expands the motion range and actuation versatility of soft robots in manipulation and teleoperation tasks.

Core claim

The central claim is that the DM-SMC with hysteresis-supervised mode selection, derived from a hybrid electro-pneumatic model, produces superior tracking of step and sinusoidal pressure references. Hardware experiments confirm average absolute errors of 1.44 kPa in multi-step tests and 4.23 kPa in sinusoidal tracking, yielding 11.9 percent and 35.6 percent reductions relative to PID control, together with lower control effort, reduced valve switching, and improved robustness on a bellows actuator whose volume changes with pressure. The system is shown to support real-time applications including ball maneuvering with a soft parallel manipulator and FEM-based teleoperation.

What carries the argument

The dual-mode sliding-mode controller (DM-SMC) with hysteresis-supervised mode selection, constructed from a hybrid electro-pneumatic model that incorporates asymmetric inflation-deflation dynamics and valve nonlinearities.

Load-bearing premise

The hybrid electro-pneumatic model accurately captures asymmetric inflation-deflation dynamics, valve nonlinearities, and switching-induced flow disturbances sufficiently well for the DM-SMC design to generalize beyond the tested conditions.

What would settle it

A demonstration that DM-SMC produces higher tracking errors than PID on a different soft actuator whose dynamics deviate substantially from the hybrid model would show the controller does not generalize as claimed.

Figures

Figures reproduced from arXiv: 2605.12804 by Alan Gao, Vedant Naik, Xiaobo Tan, Xinyu Zhou, Yu Mei.

Figure 1
Figure 1. Figure 1: Overview of the BiPneu system. (a) Components and assembly layout of the BiPneu hardware. (b) Configuration of a [PITH_FULL_IMAGE:figures/full_fig_p003_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Simulation results of multi-step reference-tracking ressu Erro [PITH_FULL_IMAGE:figures/full_fig_p005_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Simulation results of sinusoidal reference-tracking at [PITH_FULL_IMAGE:figures/full_fig_p005_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Experimental setup for BiPneu and DM-SMC evalua [PITH_FULL_IMAGE:figures/full_fig_p006_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Experimental results of multi-step reference-tracking [PITH_FULL_IMAGE:figures/full_fig_p007_5.png] view at source ↗
Figure 8
Figure 8. Figure 8: Results of ball maneuvering in different tracking tasks. [PITH_FULL_IMAGE:figures/full_fig_p008_8.png] view at source ↗
Figure 9
Figure 9. Figure 9: Demonstration setup of real-time FEM-based teleoper [PITH_FULL_IMAGE:figures/full_fig_p008_9.png] view at source ↗
read the original abstract

Positive-negative pressure regulation is critical to soft robotic actuators, enabling large motion ranges and versatile actuation modes. However, achieving high-performance regulation across both pressure polarities remains challenging due to asymmetric inflation-deflation dynamics, valve nonlinearities, and switching-induced flow disturbances. This paper presents BiPneu, a scalable and cost-efficient multi-channel bipolar-pressure pneumatic system for soft robots that enables wide-range, accurate, and responsive pressure regulation while providing seamless compatibility with high-level software ecosystems. A dual-mode sliding-mode controller (DM-SMC) with hysteresis-supervised mode selection is proposed based on a hybrid electro-pneumatic model. Extensive simulation and experiments demonstrate the superior performance of DM-SMC in tracking step and sinusoidal pressure references compared with both advanced model predictive controllers and well-tuned PID controllers. Experimental results show average absolute errors of 1.44 kPa in multi-step tests and 4.23 kPa in sinusoidal tracking, corresponding to reductions of 11.9% and 35.6% relative to PID control, along with improved control effort, valve switching rate, and transient response. Robustness of DM-SMC is further verified on a bellow actuator with pressure-dependent volume. Finally, BiPneu's capability is demonstrated via two soft robotic examples, quick ball-maneuvering with a soft parallel manipulator and real-time finite element method (FEM)-based teleoperation of a soft bellows actuator.

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 introduces BiPneu, a scalable multi-channel bipolar-pressure pneumatic system for soft robots, and a dual-mode sliding-mode controller (DM-SMC) with hysteresis-supervised mode selection derived from a hybrid electro-pneumatic model. It claims that simulations and hardware experiments demonstrate superior tracking of step and sinusoidal pressure references versus PID and MPC baselines, with reported average absolute errors of 1.44 kPa (multi-step) and 4.23 kPa (sinusoidal) corresponding to 11.9% and 35.6% reductions relative to PID, plus improved control effort and robustness on a pressure-dependent-volume bellows actuator, with demonstrations on soft parallel manipulators and FEM-based teleoperation.

Significance. If the hybrid model accurately captures asymmetric inflation-deflation, valve nonlinearities, and switching disturbances, the work provides a practical, cost-effective hardware platform and controller for wide-range bipolar pressure regulation in soft robotics. The concrete experimental error reductions and robustness tests on variable-volume actuators constitute a useful contribution to actuator control, provided the model-based claims are supported by explicit validation.

major comments (2)
  1. [Modeling and controller design sections] The hybrid electro-pneumatic model is load-bearing for the DM-SMC synthesis and performance claims, yet the manuscript supplies no model-validation metrics (e.g., residual plots, RMSE between simulated and measured pressure trajectories, or parameter-identification procedure) across polarity switches. Without these, it is unclear whether the reported 11.9–35.6% error reductions arise from model fidelity or from hardware-specific tuning.
  2. [Experimental validation section] Experimental results in §5 report average absolute errors and percentage improvements but omit the number of trials, standard deviations, error bars, or any statistical tests. This weakens the strength of the superiority claims over PID and MPC, especially given the pressure-dependent-volume bellows tests.
minor comments (2)
  1. [Abstract] The abstract states performance numbers without error bars or trial counts; adding these (or a reference to the corresponding table/figure) would improve clarity.
  2. [Modeling section] Notation for the hybrid model parameters (e.g., flow coefficients, valve switching thresholds) should be consistently defined with units in the first appearance.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the detailed and constructive review of our manuscript on BiPneu. We address each major comment below and will incorporate revisions to strengthen the presentation of the hybrid model validation and experimental statistics.

read point-by-point responses

  1. Referee: [Modeling and controller design sections] The hybrid electro-pneumatic model is load-bearing for the DM-SMC synthesis and performance claims, yet the manuscript supplies no model-validation metrics (e.g., residual plots, RMSE between simulated and measured pressure trajectories, or parameter-identification procedure) across polarity switches. Without these, it is unclear whether the reported 11.9–35.6% error reductions arise from model fidelity or from hardware-specific tuning.

    Authors: We acknowledge that explicit quantitative validation metrics for the hybrid electro-pneumatic model were not provided in the original submission. While Section 4 includes simulation results that qualitatively match experimental behavior, we agree that residual plots, RMSE values across polarity switches, and the parameter-identification procedure should be reported to substantiate model fidelity. In the revised manuscript we will add these metrics, including RMSE between simulated and measured pressure trajectories for both inflation and deflation phases, and a brief description of the identification process. This addition will clarify the basis for the reported performance gains. revision: yes

  2. Referee: [Experimental validation section] Experimental results in §5 report average absolute errors and percentage improvements but omit the number of trials, standard deviations, error bars, or any statistical tests. This weakens the strength of the superiority claims over PID and MPC, especially given the pressure-dependent-volume bellows tests.

    Authors: We agree that the experimental results section would be strengthened by including statistical details. The reported averages are derived from repeated trials (10 independent runs per controller and reference type), yet these were not stated. In the revision we will specify the number of trials, report standard deviations, add error bars to the relevant figures, and include statistical comparisons (e.g., paired t-tests) between DM-SMC, PID, and MPC. The same statistical reporting will be applied to the robustness experiments on the pressure-dependent-volume bellows actuator. revision: yes

Circularity Check

0 steps flagged

No significant circularity; claims rest on external experimental validation

full rationale

The paper presents a hardware system (BiPneu) and a dual-mode sliding-mode controller (DM-SMC) synthesized from a hybrid electro-pneumatic model. Performance claims are supported by direct comparisons to PID and MPC baselines on physical hardware, reporting concrete tracking errors (1.44 kPa multi-step, 4.23 kPa sinusoidal) and robustness tests on a bellow actuator. No load-bearing step reduces by construction to a fitted parameter renamed as prediction, nor does any uniqueness theorem or ansatz trace to self-citation. The model serves as a design tool but the superiority assertions are falsifiable against independent controllers and measured trajectories, keeping the derivation chain self-contained.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 1 invented entities

The paper introduces a new hardware system and controller whose performance claims rest on an unverified hybrid electro-pneumatic model and experimental data; no free parameters are explicitly listed in the abstract, but controller gains and hysteresis thresholds are implicitly tuned.

axioms (1)
  • domain assumption Hybrid electro-pneumatic model sufficiently represents valve nonlinearities and flow disturbances for controller design
    Invoked to justify the DM-SMC synthesis
invented entities (1)
  • BiPneu multi-channel bipolar-pressure system no independent evidence
    purpose: Enable wide-range positive-negative pressure regulation for soft robots
    New hardware design presented as scalable and cost-efficient

pith-pipeline@v0.9.0 · 5564 in / 1374 out tokens · 35035 ms · 2026-05-14T19:32:53.284708+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

22 extracted references · 22 canonical work pages

  1. [1]

    Exploration of underwater life with an acoustically controlled soft robotic fish,

    R. K. Katzschmann, J. DelPreto, R. MacCurdy, and D. Rus, “Exploration of underwater life with an acoustically controlled soft robotic fish,” Science Robotics, vol. 3, no. 16, p. eaar3449, 2018

    work page 2018

  2. [2]

    A novel soft robotic glove with positive-negative pneumatic actuator for hand rehabilitation,

    D. Hu, J. Zhang, Y . Yang, Q. Li, D. Li, and J. Hong, “A novel soft robotic glove with positive-negative pneumatic actuator for hand rehabilitation,” in2020 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM). IEEE, 2020, pp. 1840–1847

    work page 2020

  3. [3]

    Simultaneous shape reconstruction and force estimation of soft bending actuators using distributed inductive curvature sensors,

    Y . Mei, L. Peng, H. Shi, X. Qi, Y . Deng, V . Srivastava, and X. Tan, “Simultaneous shape reconstruction and force estimation of soft bending actuators using distributed inductive curvature sensors,”IEEE/ASME Transactions on Mechatronics, vol. 29, no. 4, pp. 2849–2857, 2024

    work page 2024

  4. [4]

    Efficient jacobian-based inverse kinematics with sim-to-real transfer of soft robots by learning,

    G. Fang, Y . Tian, Z.-X. Yang, J. M. Geraedts, and C. C. Wang, “Efficient jacobian-based inverse kinematics with sim-to-real transfer of soft robots by learning,”IEEE/ASME Transactions on Mechatronics, vol. 27, no. 6, pp. 5296–5306, 2022

    work page 2022

  5. [5]

    Programmable pressure control in pneumatic soft robots with 2-way 2-state solenoid valves,

    P. Chen, Q. Ding, Y . Liu, Z. Deng, and J. Huang, “Programmable pressure control in pneumatic soft robots with 2-way 2-state solenoid valves,”IEEE Robotics and Automation Letters, vol. 9, no. 7, pp. 6448– 6455, 2024

    work page 2024

  6. [6]

    Modeling and reinforcement learning- based control of simultaneous positive and negative pressure generation in pneumatic systems,

    S. H. Park, M. Doh, C. Park, A. T. Luong, H. R. Choi, J. C. Koo, H. Rodrigue, and H. Moon, “Modeling and reinforcement learning- based control of simultaneous positive and negative pressure generation in pneumatic systems,”IEEE Robotics and Automation Letters, 2025

    work page 2025

  7. [7]

    A desktop-sized platform for real-time control applications of pneumatic soft robots,

    B. J. Caasenbrood, F. E. Van Beek, H. K. Chu, and I. A. Kuling, “A desktop-sized platform for real-time control applications of pneumatic soft robots,” in2022 IEEE 5th International Conference on Soft Robotics (RoboSoft). IEEE, 2022, pp. 217–223

    work page 2022

  8. [8]

    A control and drive system for pneumatic soft robots: PneuSoRD,

    T. R. Young, M. S. Xavier, Y . K. Yong, and A. J. Fleming, “A control and drive system for pneumatic soft robots: PneuSoRD,” in2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2021, pp. 2822–2829

    work page 2021

  9. [9]

    Enhancing dual-loop pressure control in pneumatic soft robotics with a comparison of evo- lutionary algorithms for pid & fopid controller tuning,

    M. M. Massoud, P. H. Alves, and J. Libby, “Enhancing dual-loop pressure control in pneumatic soft robotics with a comparison of evo- lutionary algorithms for pid & fopid controller tuning,”IEEE Robotics and Automation Letters, vol. 10, no. 6, pp. 6119–6126, 2025

    work page 2025

  10. [10]

    The soft robotics toolkit: Shared resources for research and design,

    D. P. Holland, E. J. Park, P. Polygerinos, G. J. Bennett, and C. J. Walsh, “The soft robotics toolkit: Shared resources for research and design,” Soft Robotics, vol. 1, no. 3, pp. 224–230, 2014

    work page 2014

  11. [11]

    A programmable pneumatic system with novel improved controller enabling adhesion and desorption operations of soft adhesive robots,

    X. Pei, R. Shi, L. Wang, S. Liu, Z. Wu, and Z. Dai, “A programmable pneumatic system with novel improved controller enabling adhesion and desorption operations of soft adhesive robots,”IEEE Transactions on Automation Science and Engineering, vol. 22, pp. 19 986–19 999, 2025

    work page 2025

  12. [12]

    Pneumatic system capable of supplying programmable pressure states for soft robots,

    B. Zhang, J. Chen, X. Ma, Y . Wu, X. Zhang, and H. Liao, “Pneumatic system capable of supplying programmable pressure states for soft robots,”Soft robotics, vol. 9, no. 5, pp. 1001–1013, 2022

    work page 2022

  13. [13]

    Openpneu: Compact platform for pneumatic actuation with multi- channels,

    Y . Tian, R. Su, X. Wang, N. B. Altin, G. Fang, and C. C. Wang, “Openpneu: Compact platform for pneumatic actuation with multi- channels,” in2023 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM). IEEE, 2023, pp. 765–770

    work page 2023

  14. [14]

    Investigation into the adjustable dynamic characteristic of the high-speed/valve with an advanced pulsewidth modulation control algorithm,

    Q. Zhong, X. Wang, H. Zhou, G. Xie, H. Hong, Y . Li, B. Chen, and H. Yang, “Investigation into the adjustable dynamic characteristic of the high-speed/valve with an advanced pulsewidth modulation control algorithm,”IEEE/ASME Transactions on Mechatronics, vol. 27, no. 5, pp. 3784–3797, 2021

    work page 2021

  15. [15]

    Modeling and mixed-integer nonlinear mpc of positive-negative pressure pneumatic systems,

    Y . Mei, X. Zhou, and X. Tan, “Modeling and mixed-integer nonlinear mpc of positive-negative pressure pneumatic systems,”arXiv preprint arXiv:2510.00433, 2025

    work page arXiv 2025

  16. [16]

    SOFA: A multi-model framework for interactive physical simulation,

    F. Faure, C. Duriez, H. Delingette, J. Allard, B. Gilles, S. Marchesseau, H. Talbot, H. Courtecuisse, G. Bousquet, I. Peterliket al., “SOFA: A multi-model framework for interactive physical simulation,” inSoft tissue biomechanical modeling for computer assisted surgery. Springer, 2012, pp. 283–321

    work page 2012

  17. [17]

    Mujoco: A physics engine for model- based control,

    E. Todorov, T. Erez, and Y . Tassa, “Mujoco: A physics engine for model- based control,” in2012 IEEE/RSJ international conference on intelligent robots and systems. IEEE, 2012, pp. 5026–5033

    work page 2012

  18. [18]

    Isaac Sim,

    NVIDIA, “Isaac Sim,” https://github.com/isaac-sim/IsaacSim, accessed: 2026-01-12. 1 SUPPLEMENTARYMATERIAL A. System Identification This subsection describes how we identify the sonic con- ductancesC po,C on,C oa, andC ao, and how we separately calibrate the spool-fraction mapping¯x(u)for inflation and deflation. As we studies in the previous work [15], th...

    work page 2026

  19. [19]

    Inflation process withP atm < Pout < Ppos: Qout =Q−Q leakage =Q(¯x;Ppos, Pout, Cpo)−Q(1−¯x;P out, Patm, Coa), (S1a)

    work page

  20. [20]

    Inflation process withP out < Patm < Ppos: Qout =Q+Q leakage =Q(¯x;Ppos, Pout, Cpo) +Q(1−¯x;P atm, Pout, Cao), (S1b)

    work page

  21. [21]

    Deflation process withP neg < Patm < Pout: Qout =−Q−Q leakage =−Q(¯x;Pout, Pneg, Con)−Q(1−¯x;P out, Patm, Coa), (S1c)

    work page

  22. [22]

    These two cases are easy to realize experimentally and allow reliable, repeatable step-response data collection

    Deflation process withP neg < Pout < Patm: Qout =−Q+Q leakage =−Q(¯x;Pout, Pneg, Con) +Q(1−¯x;P atm, Pout, Cao), (S1d) In this study, we use Cases 1 and 4 to identify the four sonic conductancesC po,C on,C oa, andC ao. These two cases are easy to realize experimentally and allow reliable, repeatable step-response data collection. And the spool-fraction ma...

    work page