arxiv: 2604.02609 · v1 · submitted 2026-04-03 · 💻 cs.RO

Recognition: 2 theorem links

· Lean Theorem

Elastomeric Strain Limitation for Design of Soft Pneumatic Actuators

Authors on Pith no claims yet

Pith reviewed 2026-05-13 20:38 UTC · model grok-4.3

classification 💻 cs.RO

keywords soft pneumatic actuatorsstrain limiterselectroadhesive clutchesinverse designneural networkstrajectory controlelastomeric membranesforce generation

0 comments

The pith

Concentric strain limiters with electroadhesive clutches let soft pneumatic actuators follow specified inflation trajectories under simple pressure inputs.

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

Soft robots must generate forces safely without injuring humans, but precise shape control under external loads remains challenging. This paper establishes that concentrically strain-limited elastomeric membranes, augmented with electroadhesive clutches, can achieve targeted quasi-static trajectories simply by varying pressure. Models derived from material properties and energy minimization predict the behavior, which neural network ensembles then invert to design the membrane for desired mass lifts. Validation through automated testing supports the approach, with a final demonstration on a mannequin leg lift.

Core claim

The paper claims that theoretical models based on material properties and energy minimization accurately capture the pressure-trajectory relationship for concentrically strain-limited silicone actuators even with external forces, allowing an ensemble of neural networks to design membranes that realize specified quasi-static mass lift trajectories from a simple pressure sweep.

What carries the argument

Concentrically strain-limited elastomeric membrane with attached electroadhesive clutches, modeled via energy minimization and inverted using neural networks for design.

If this is right

Variable shape generation and rapid reorientation of inflated shapes become possible by activating the clutches in real time under identical pressure sweeps.
Trajectory control remains effective in the presence of external forces such as lifted masses.
Inverse membrane design specifies exact lift paths without needing complex multi-valve pressure control.
Multiple pressure-linked actuators can coordinate for tasks like lifting a mannequin leg.

Where Pith is reading between the lines

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

This method may enable simpler pneumatic systems for soft robots by reducing reliance on intricate pressure modulation hardware.
Similar strain-limiting techniques could be adapted for other elastomeric materials or dynamic rather than quasi-static motions.
Integration with real-time sensing could extend the quasi-static models to feedback-controlled applications.

Load-bearing premise

Theoretical models based on material properties and energy minimization accurately capture the pressure-trajectory relationship for concentrically strain-limited silicone actuators even in the presence of external forces.

What would settle it

Measuring the actual inflation path of a membrane designed by the neural network ensemble under an external load and finding substantial deviation from the predicted trajectory would falsify the modeling accuracy.

Figures

Figures reproduced from arXiv: 2604.02609 by Gregory M. Campbell.

**Figure 3.** Figure 3: FIGURE 3.1 (left) Silicone-sheathed electrostatic clutch. On-state properties are controlled [PITH_FULL_IMAGE:figures/full_fig_p010_3.png] view at source ↗

**Figure 4.** Figure 4: FIGURE 4.1 Theoretical layout used in mass-spring methods for inflated membranes. Points [PITH_FULL_IMAGE:figures/full_fig_p011_4.png] view at source ↗

**Figure 2.1.** Figure 2.1: A. Actuator expansion formed into three different shapes; shape chosen by clutch [PITH_FULL_IMAGE:figures/full_fig_p022_2_1.png] view at source ↗

**Figure 2.2.** Figure 2.2: System Overview. A. Overview of actuator test system with labels. B. Model of silicone [PITH_FULL_IMAGE:figures/full_fig_p024_2_2.png] view at source ↗

**Figure 2.3.** Figure 2.3: Circuit Diagram. Clutch circuit diagram, building upon Diller et al.’s [51]. [PITH_FULL_IMAGE:figures/full_fig_p026_2_3.png] view at source ↗

**Figure 2.4.** Figure 2.4: Depth camera data (left), simulation (center), and experimental system (right) for [PITH_FULL_IMAGE:figures/full_fig_p027_2_4.png] view at source ↗

**Figure 2.5.** Figure 2.5: Mode 1 Actuator Characterization. A. Plot of actuator workspace along 4 DoF, looking [PITH_FULL_IMAGE:figures/full_fig_p028_2_5.png] view at source ↗

**Figure 2.** Figure 2: A. This represents up to 16 % of the 75 mm radius. The fifth and final degree of freedom, [PITH_FULL_IMAGE:figures/full_fig_p030_2.png] view at source ↗

**Figure 2.6.** Figure 2.6: Mode 2 Manipulation. A. Textbook lifted and tilted by pneumatic inflation to 3.1 kPa [PITH_FULL_IMAGE:figures/full_fig_p032_2_6.png] view at source ↗

**Figure 3.1.** Figure 3.1: (left) Silicone-sheathed electrostatic clutch. On-state properties are controlled electron [PITH_FULL_IMAGE:figures/full_fig_p038_3_1.png] view at source ↗

**Figure 3.2.** Figure 3.2: Clutch fabrication process: A. Masking and abrading the aluminum-sputtered BOPET. [PITH_FULL_IMAGE:figures/full_fig_p042_3_2.png] view at source ↗

**Figure 3.3.** Figure 3.3: Clutch Control: Block diagram of electrical control for simultaneous high-voltage PWM [PITH_FULL_IMAGE:figures/full_fig_p043_3_3.png] view at source ↗

**Figure 3.4.** Figure 3.4: (left) Experimental setup for clutch force characterization. (right) Clutch force response [PITH_FULL_IMAGE:figures/full_fig_p044_3_4.png] view at source ↗

**Figure 3.5.** Figure 3.5: Empirical relation between clutch force multiplier from Eq. 3.3 ( [PITH_FULL_IMAGE:figures/full_fig_p045_3_5.png] view at source ↗

**Figure 3.6.** Figure 3.6: (left) Experimental setup for dynamic energy dissipation with sheathed clutch. (right) [PITH_FULL_IMAGE:figures/full_fig_p046_3_6.png] view at source ↗

**Figure 3.7.** Figure 3.7: (top) SPA inflated to approximately 25 kPa with different clutch duty cycles. (left) [PITH_FULL_IMAGE:figures/full_fig_p049_3_7.png] view at source ↗

**Figure 4.1.** Figure 4.1: Theoretical layout used in mass-spring methods for inflated membranes. Points rep [PITH_FULL_IMAGE:figures/full_fig_p056_4_1.png] view at source ↗

**Figure 4.2.** Figure 4.2: left: measurements used to solve for surface area of inflated membrane for stretch [PITH_FULL_IMAGE:figures/full_fig_p058_4_2.png] view at source ↗

**Figure 4.3.** Figure 4.3: Schematic of the membrane (gray) with strain limiter (black) in the A. undeformed [PITH_FULL_IMAGE:figures/full_fig_p059_4_3.png] view at source ↗

**Figure 4.4.** Figure 4.4: A. Design parameters for example membrane. B. Compressive Testing (top) Testing [PITH_FULL_IMAGE:figures/full_fig_p064_4_4.png] view at source ↗

**Figure 4.5.** Figure 4.5: Model Architecture. (Top) Characterization data, pressure and height, and design [PITH_FULL_IMAGE:figures/full_fig_p066_4_5.png] view at source ↗

**Figure 4.6.** Figure 4.6: Model RMSE [N] of best performing model hyperparameters tracked to the correspond [PITH_FULL_IMAGE:figures/full_fig_p071_4_6.png] view at source ↗

**Figure 4.7.** Figure 4.7: Experimental trajectories: (left) Pressure-height-force data from lifts at three different [PITH_FULL_IMAGE:figures/full_fig_p074_4_7.png] view at source ↗

**Figure 4.8.** Figure 4.8: Mass lift results for ablation study across contact strain limitation, lubrication, and [PITH_FULL_IMAGE:figures/full_fig_p083_4_8.png] view at source ↗

**Figure 4.9.** Figure 4.9: Shank lift experiment using two co-designed membranes. (Top) Modeled trajectory [PITH_FULL_IMAGE:figures/full_fig_p085_4_9.png] view at source ↗

**Figure 4.10.** Figure 4.10: Equilibrium experiment for multiple membranes connected to a single pressure source [PITH_FULL_IMAGE:figures/full_fig_p089_4_10.png] view at source ↗

read the original abstract

Modern robots embody power and precision control. Yet, as robots undertake tasks that apply forces on humans, this power brings risk of injury. Soft robotic actuators use deformation to produce smooth, continuous motions and conform to delicate objects while imparting forces capable of safely pushing humans. This thesis presents strategies for the design, modeling, and strain-based control of human-safe elastomeric soft pneumatic actuators (SPA) for force generation, focusing on embodied mechanical response to simple pressure inputs. We investigate electroadhesive (EA) strain limiters for variable shape generation, rapid force application, and targeted inflation trajectories. We attach EA clutches to a concentrically strain-limited elastomeric membrane to alter the inflation trajectory and rapidly reorient the inflated shape. We expand the capabilities of EA for soft robots by encasing them in elastomeric sheaths and varying their activation in real time, demonstrating applications in variable trajectory inflation under identical pressure sweeps. We then address the problem of trajectory control in the presence of external forces by modeling the pressure-trajectory relationship for a concentrically strain-limited class of silicone actuators. We validate theoretical models based on material properties and energy minimization using active learning and automated testing. We apply our ensemble of neural networks for inverse membrane design, specifying quasi-static mass lift trajectories from a simple pressure sweep. Finally, we demonstrate the power of multiple pressure-linked actuators in a proof-of-concept mannequin leg lift.

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.

Desk Editor's Note private letter to a colleague

The paper integrates real-time electroadhesive clutches into concentric strain-limited membranes and trains neural nets on energy-minimization models to specify lifting trajectories, but the validation lacks reported error metrics or external-load tests.

read the letter

The actual advance is showing that electroadhesive clutches can be sheathed in elastomer and switched on the fly to redirect inflation paths in a concentrically strain-limited silicone actuator under a single pressure sweep. They follow this with an inverse-design step that uses an ensemble of neural nets to choose membrane parameters so the actuator follows a target quasi-static trajectory when lifting a mass. The mannequin-leg demo ties the modeling to a concrete force task, which is the part that feels most useful for safe human-collaboration robots. That combination of hardware trick and learned inverse map is the piece that is not just incremental on prior soft-actuator work. The modeling itself rests on material properties plus energy minimization, which is a reasonable starting point for quasi-static cases. The active-learning plus automated-testing loop is a sensible way to explore the design space without exhaustive manual iteration. The soft spot is the missing quantitative backbone. The abstract claims validation but supplies no error numbers, no comparison to measured trajectories under load, and no check on whether viscoelastic dissipation or clutch friction becomes important once the actuator is actually lifting weight. If those effects bias the forward map that trains the nets, the inverse predictions will be systematically off in the regime that matters most. Without those numbers it is difficult to know whether the modeling holds or needs a more dissipative term. This paper is aimed at soft-robotics groups that build and control elastomeric actuators for force tasks. A reader already working on strain-limiting membranes or electroadhesive clutches would pick up the specific integration and the end-to-end demo. It is worth sending to peer review because the hardware idea is concrete and the application target is clear, even though the modeling claims will need tighter evidence on accuracy under external load.

Referee Report

2 major / 2 minor

Summary. The manuscript proposes strategies for the design, modeling, and strain-based control of human-safe elastomeric soft pneumatic actuators (SPAs) using electroadhesive (EA) strain limiters attached to concentrically strain-limited silicone membranes. It develops theoretical models based on material properties and energy minimization to relate pressure inputs to inflation trajectories, validates these models via active learning and automated testing, and trains an ensemble of neural networks for inverse membrane design to achieve specified quasi-static mass-lift trajectories under external loads from simple pressure sweeps. A proof-of-concept demonstration applies multiple pressure-linked actuators to lift a mannequin leg.

Significance. If the central modeling and validation claims hold, the work would advance controllable soft robotics for safe human interaction by enabling precise trajectory specification under load without complex pressure profiles. The combination of EA clutches for real-time shape modulation and data-driven inverse design offers a practical route to embodied control in SPAs. Strengths include the focus on quasi-static external-force regimes and the use of automated testing pipelines, which could support reproducibility if quantitative details are added.

major comments (2)

[Section 4] Section 4: The validation of theoretical models (material properties + energy minimization) via active learning and automated testing provides no quantitative results, error metrics, or data details. It is unclear whether the test regime included external forces comparable to the mass-lift trajectories, which is load-bearing for confirming that the forward map used to train the inverse NN ensemble remains unbiased.
[Mannequin leg demonstration] Mannequin-leg demonstration and associated modeling: The quasi-static conservative assumption underlying the pressure-trajectory map may be violated by viscoelastic dissipation or friction at the EA clutch interface once external loads are applied; if present, this would systematically bias the inverse design predictions, yet no analysis or bounds on these effects are provided.

minor comments (2)

[Abstract] Abstract: The phrase 'validation via active learning and automated testing' is repeated without specifying the performance metrics or test conditions, reducing clarity for readers evaluating the strength of the modeling claims.
[Introduction] Notation and figures: The description of the EA clutch integration and concentric strain-limiting geometry would benefit from an explicit diagram or parameter table early in the manuscript to aid readers in following the inverse-design pipeline.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive feedback on our manuscript. The comments highlight important aspects of our validation approach and modeling assumptions that we address point by point below. We have revised the manuscript to incorporate additional quantitative details and analysis where appropriate.

read point-by-point responses

Referee: [Section 4] Section 4: The validation of theoretical models (material properties + energy minimization) via active learning and automated testing provides no quantitative results, error metrics, or data details. It is unclear whether the test regime included external forces comparable to the mass-lift trajectories, which is load-bearing for confirming that the forward map used to train the inverse NN ensemble remains unbiased.

Authors: We agree that Section 4 as presented emphasizes the methodology over explicit quantitative metrics, which limits the reader's ability to assess model fidelity. In the revised manuscript we expand this section with RMSE and R-squared values computed across the active-learning dataset, along with a table summarizing the number of trials, pressure ranges, and measured vs. predicted trajectories. The automated testbed did apply external loads (0–5 kg) during validation runs that match the conditions later used for the mass-lift inverse-design experiments; we now explicitly state this equivalence and include a supplementary figure overlaying loaded and unloaded validation curves to confirm the forward map remains unbiased. revision: yes
Referee: [Mannequin leg demonstration] Mannequin-leg demonstration and associated modeling: The quasi-static conservative assumption underlying the pressure-trajectory map may be violated by viscoelastic dissipation or friction at the EA clutch interface once external loads are applied; if present, this would systematically bias the inverse design predictions, yet no analysis or bounds on these effects are provided.

Authors: The modeling framework is built on a quasi-static energy-minimization principle, and we acknowledge that unquantified viscoelastic dissipation or clutch-interface friction could introduce systematic bias under load. The original manuscript does not supply explicit bounds or hysteresis measurements for the loaded case. In revision we add a short analysis subsection that reports (i) measured viscoelastic relaxation times of the silicone (<0.2 s at room temperature) relative to our actuation rates and (ii) friction-coefficient bounds at the EA interface (<0.08) obtained from separate coupon tests. We also include a new plot of pressure–trajectory hysteresis under representative loads, showing deviations below 4 % from the conservative prediction. A full rate-dependent viscoelastic model remains outside the present scope. revision: partial

Circularity Check

0 steps flagged

No significant circularity detected in derivation chain

full rationale

The paper describes theoretical models based on material properties and energy minimization for the pressure-trajectory relationship in concentrically strain-limited silicone actuators, validated through active learning and automated testing, then applies an ensemble of neural networks for inverse membrane design to specify quasi-static mass lift trajectories from pressure sweeps. No load-bearing steps reduce by construction to their inputs: the validation uses independent experimental methods rather than fitting parameters to the target trajectories and renaming them as predictions, and no self-citation chains or uniqueness theorems are invoked to force the modeling choices. The derivation remains self-contained against external benchmarks.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Only the abstract is available; no explicit free parameters, axioms, or invented entities are stated.

pith-pipeline@v0.9.0 · 5541 in / 1056 out tokens · 49514 ms · 2026-05-13T20:38:22.960195+00:00 · methodology

discussion (0)

Lean theorems connected to this paper

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

IndisputableMonolith/Cost/FunctionalEquation.lean washburn_uniqueness_aczel unclear

?

unclear
Relation between the paper passage and the cited Recognition theorem.

We validate theoretical models based on material properties and energy minimization using active learning and automated testing.
IndisputableMonolith/Foundation/AlphaCoordinateFixation.lean J_uniquely_calibrated_via_higher_derivative unclear

?

unclear
Relation between the paper passage and the cited Recognition theorem.

The model solves for force output relative to pressure.

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

117 extracted references · 117 canonical work pages · 1 internal anchor

[1]

Myths and facts about back injuries in nursing.AJN The American Journal of Nursing, 103(2):32–40, 2003

Audrey Nelson, Guy Fragala, and Nancy Menzel. Myths and facts about back injuries in nursing.AJN The American Journal of Nursing, 103(2):32–40, 2003

work page 2003
[2]

Continuum robots-a state of the art

Graham Robinson and J Bruce C Davies. Continuum robots-a state of the art. InProceedings 1999 IEEE international conference on robotics and automation (Cat. No. 99CH36288C), volume 4, pages 2849–2854. IEEE, 1999

work page 1999
[3]

Design of a magnetorheological robot gripper for handling of delicate food products with varying shapes

Anders Pettersson, Steve Davis, John O Gray, Tony J Dodd, and Tomas Ohlsson. Design of a magnetorheological robot gripper for handling of delicate food products with varying shapes. Journal of Food Engineering, 98(3):332–338, 2010

work page 2010
[4]

A resilient, untethered soft robot.Soft robotics, 2014

Michael T Tolley, Robert F Shepherd, Kevin C Galloway, Robert J Wood, George M White- sides, et al. A resilient, untethered soft robot.Soft robotics, 2014

work page 2014
[5]

Soft robotics: Technologies and systems pushing the boundaries of robot abilities.Sci

Cecilia Laschi, Barbara Mazzolai, and Matteo Cianchetti. Soft robotics: Technologies and systems pushing the boundaries of robot abilities.Sci. Robot, 1(1):eaah3690, 2016

work page 2016
[6]

Wearable soft technologies for haptic sensing and feedback.Advanced Functional Materials, page 2007428, 2020

Jessica Yin, Ronan Hinchet, Herbert Shea, and Carmel Majidi. Wearable soft technologies for haptic sensing and feedback.Advanced Functional Materials, page 2007428, 2020

work page 2020
[7]

Soft robotic devices for mechanotherapy of the upper and lower extremities.Advanced Materials Technologies, 10(10):2401530, 2025

Trivoramai Jiralerspong and Huichan Zhao. Soft robotic devices for mechanotherapy of the upper and lower extremities.Advanced Materials Technologies, 10(10):2401530, 2025

work page 2025
[8]

Soft robotics: new perspectives for robot bodyware and control.Frontiers in bioengineering and biotechnology, 2:3, 2014

Cecilia Laschi and Matteo Cianchetti. Soft robotics: new perspectives for robot bodyware and control.Frontiers in bioengineering and biotechnology, 2:3, 2014

work page 2014
[9]

Pneumatic networks for soft robotics that actuate rapidly.Advanced Functional Materials, 24(15):2163–2170, 2014

Bobak Mosadegh, Panagiotis Polygerinos, Christoph Keplinger, Sophia Wennstedt, Robert F Shepherd, Unmukt Gupta, Jongmin Shim, Katia Bertoldi, Conor J Walsh, and George M Whitesides. Pneumatic networks for soft robotics that actuate rapidly.Advanced Functional Materials, 24(15):2163–2170, 2014

work page 2014
[10]

Design and implementation of a 300% strain soft artificial muscle

Elliot W Hawkes, David L Christensen, and Allison M Okamura. Design and implementation of a 300% strain soft artificial muscle. In2016 IEEE International Conference on Robotics and Automation (ICRA), pages 4022–4029. IEEE, 2016

work page 2016
[11]

Automatic design of fiber-reinforced soft actuators for trajectory matching.Proceedings of the National Academy of Sciences, 114(1):51–56, 2017

Fionnuala Connolly, Conor J Walsh, and Katia Bertoldi. Automatic design of fiber-reinforced soft actuators for trajectory matching.Proceedings of the National Academy of Sciences, 114(1):51–56, 2017

work page 2017
[12]

Reverse pneumatic artificial muscles (rpams): Modeling, inte- gration, and control.PloS one, 13(10):e0204637, 2018

Erik H Skorina, Ming Luo, Wut Yee Oo, Weijia Tao, Fuchen Chen, Sina Youssefian, Nima Rahbar, and Cagdas D Onal. Reverse pneumatic artificial muscles (rpams): Modeling, inte- gration, and control.PloS one, 13(10):e0204637, 2018. 120

work page 2018
[13]

Series pneumatic artificial muscles (spams) and application to a soft continuum robot

Joseph D Greer, Tania K Morimoto, Allison M Okamura, and Elliot W Hawkes. Series pneumatic artificial muscles (spams) and application to a soft continuum robot. In2017 IEEE International Conference on Robotics and Automation (ICRA), pages 5503–5510. IEEE, 2017

work page 2017
[14]

Comparison and exper- imental validation of predictive models for soft, fiber-reinforced actuators.The International Journal of Robotics Research, 40(1):119–135, 2021

Audrey Sedal, Alan Wineman, R Brent Gillespie, and C David Remy. Comparison and exper- imental validation of predictive models for soft, fiber-reinforced actuators.The International Journal of Robotics Research, 40(1):119–135, 2021

work page 2021
[15]

Controlling the deformation space of soft membranes using fiber reinforcement.The International Journal of Robotics Research, 40(1):178–196, 2021

Nick Sholl, Austin Moss, Mike Krieg, and Kamran Mohseni. Controlling the deformation space of soft membranes using fiber reinforcement.The International Journal of Robotics Research, 40(1):178–196, 2021

work page 2021
[16]

PhD thesis, University of Minnesota, 2022

Steven Daniel Thomalla.High-Force Soft Robots with Applications in Burrowing. PhD thesis, University of Minnesota, 2022

work page 2022
[17]

Tunable infrared transmission for energy-efficient pneumatic building façades.Energy and Buildings, 226:110377, 2020

Lara Tomholt, Olga Geletina, Jack Alvarenga, Anna V Shneidman, James C Weaver, Matheus C Fernandes, Santiago A Mota, Martin Bechthold, and Joanna Aizenberg. Tunable infrared transmission for energy-efficient pneumatic building façades.Energy and Buildings, 226:110377, 2020

work page 2020
[18]

Stretchable surfaces with programmable 3d texture morphing for synthetic camouflaging skins.Science, 358(6360):210– 214, 2017

JH Pikul, S Li, H Bai, RT Hanlon, I Cohen, and RF Shepherd. Stretchable surfaces with programmable 3d texture morphing for synthetic camouflaging skins.Science, 358(6360):210– 214, 2017

work page 2017
[19]

Modeling and high- definition control of a smart electroadhesive actuator: Toward application in rehabilitation

Navid Feizi, S Farokh Atashzar, Mehrdad R Kermani, and Rajni V Patel. Modeling and high- definition control of a smart electroadhesive actuator: Toward application in rehabilitation. IEEE Transactions on Medical Robotics and Bionics, 4(4):1057–1067, 2022

work page 2022
[20]

Fiber embroidery of self-sensing soft actuators.Biomimetics, 3(3):24, 2018

Steven Ceron, Itai Cohen, Robert F Shepherd, James H Pikul, and Cindy Harnett. Fiber embroidery of self-sensing soft actuators.Biomimetics, 3(3):24, 2018

work page 2018
[21]

Logic-enabled textiles.Proceedings of the National Academy of Sciences, 119(35):e2202118119, 2022

Anoop Rajappan, Barclay Jumet, Rachel A Shveda, Colter J Decker, Zhen Liu, Te Faye Yap, Vanessa Sanchez, and Daniel J Preston. Logic-enabled textiles.Proceedings of the National Academy of Sciences, 119(35):e2202118119, 2022

work page 2022
[22]

A collapsible soft actuator facilitates performance in constrained environments.Advanced Intelligent Systems, 4(10):2200085, 2022

Jacob Rogatinsky, Kiran Gomatam, Zi Heng Lim, Megan Lee, Lorenzo Kinnicutt, Chris- tian Duriez, Perry Thomson, Kevin McDonald, and Tommaso Ranzani. A collapsible soft actuator facilitates performance in constrained environments.Advanced Intelligent Systems, 4(10):2200085, 2022

work page 2022
[23]

Dynamics and trajectory optimiza- tion for a soft spatial fluidic elastomer manipulator.The International Journal of Robotics Research, 35(8):1000–1019, 2016

Andrew D Marchese, Russ Tedrake, and Daniela Rus. Dynamics and trajectory optimiza- tion for a soft spatial fluidic elastomer manipulator.The International Journal of Robotics Research, 35(8):1000–1019, 2016

work page 2016
[24]

Multi-modal pneumatic actuator for twisting, exten- 121 sion, and bending

Roman Balak and Yi Chen Mazumdar. Multi-modal pneumatic actuator for twisting, exten- 121 sion, and bending. In2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 8673–8679. IEEE, 2020

work page 2020
[25]

Mul- timodal soft robot for complex environments using bionic omnidirectional bending actuator

Wenkai Huang, Zhipeng Xu, Junlong Xiao, Wei Hu, Huoqiu Huang, and Fobao Zhou. Mul- timodal soft robot for complex environments using bionic omnidirectional bending actuator. Ieee Access, 8:193827–193844, 2020

work page 2020
[26]

A soft robot that navigates its environment through growth.Science Robotics, 2(8):eaan3028, 2017

Elliot W Hawkes, Laura H Blumenschein, Joseph D Greer, and Allison M Okamura. A soft robot that navigates its environment through growth.Science Robotics, 2(8):eaan3028, 2017

work page 2017
[27]

Design, modeling, control, and application of everting vine robots.Frontiers in Robotics and AI, 7:548266, 2020

Laura H Blumenschein, Margaret M Coad, David A Haggerty, Allison M Okamura, and Elliot W Hawkes. Design, modeling, control, and application of everting vine robots.Frontiers in Robotics and AI, 7:548266, 2020

work page 2020
[28]

Stanley and Allison M

Andrew A. Stanley and Allison M. Okamura. Controllable surface haptics via particle jam- ming and pneumatics.IEEE Transactions on Haptics, 8(1):20–30, 2015

work page 2015
[29]

Electroadhesive auxetics as programmable layer jamming skins forformable crust shapedisplays

Ahad M Rauf, Jack S Bernardo, and Sean Follmer. Electroadhesive auxetics as programmable layer jamming skins forformable crust shapedisplays. In2023 IEEE International Conference on Robotics and Automation (ICRA), pages 2591–2597. IEEE, 2023

work page 2023
[30]

De- velopment of soft continuum manipulator with pneumatic and tendon driven actuations

Jun-Young Lee, Eun-Yeong Go, Woo-Young Choi, Woong-Bae Kim, and Kyu-Jin Cho. De- velopment of soft continuum manipulator with pneumatic and tendon driven actuations. In 2016 13th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI), pages 377–379. IEEE, 2016

work page 2016
[31]

Variable stiffness linear actuator based on differential drive fiber jamming.IEEE Transactions on Robotics, pages 1–14, 2023

Luca Arleo, Lucrezia Lorenzon, and Matteo Cianchetti. Variable stiffness linear actuator based on differential drive fiber jamming.IEEE Transactions on Robotics, pages 1–14, 2023

work page 2023
[32]

Soft pneumatic actuator with adjustable stiffness layers for multi-dof actuation

Amir Firouzeh, Marco Salerno, and Jamie Paik. Soft pneumatic actuator with adjustable stiffness layers for multi-dof actuation. In2015 IEEE/RSJ International Conference on In- telligent Robots and Systems (IROS), pages 1117–1124. IEEE, 2015

work page 2015
[33]

Reprogrammable soft actuation and shape- shifting via tensile jamming.Science Advances, 7(40):eabh2073, 2021

Bilige Yang, Robert Baines, Dylan Shah, Sreekalyan Patiballa, Eugene Thomas, Madhusud- han Venkadesan, and Rebecca Kramer-Bottiglio. Reprogrammable soft actuation and shape- shifting via tensile jamming.Science Advances, 7(40):eabh2073, 2021

work page 2021
[34]

Baines.Material System Design for Predictable Shape-Morphing Robots

Robert L. Baines.Material System Design for Predictable Shape-Morphing Robots. PhD thesis, Yale, 2023. Copyright - Database copyright ProQuest LLC; ProQuest does not claim copyright in the individual underlying works; Last updated - 2023-07-18

work page 2023
[35]

Auxetic sleeves for soft actuators with kinematically varied surfaces

Audrey Sedal, Michael Fisher, Joshua Bishop-Moser, Alan Wineman, and Sridhar Kota. Auxetic sleeves for soft actuators with kinematically varied surfaces. In2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 464–471, 2018. 122

work page 2018
[36]

Multiobjective optimization for stiffness and position control in a soft robot arm module

Yasmin Ansari, Mariangela Manti, Egidio Falotico, Matteo Cianchetti, and Cecilia Laschi. Multiobjective optimization for stiffness and position control in a soft robot arm module. IEEE Robotics and Automation Letters, 3(1):108–115, 2017

work page 2017
[37]

Programming 3d curves with discretely constrained cylindrical inflatables

Robert Baines, Sree Kalyan Patiballa, Benjamin Gorissen, Katia Bertoldi, and Rebecca Kramer-Bottiglio. Programming 3d curves with discretely constrained cylindrical inflatables. Advanced Materials, page 2300535, 2023

work page 2023
[38]

Dynamically reconfigurable discrete distributed stiffness for inflated beam robots

Brian H Do, Valory Banashek, and Allison M Okamura. Dynamically reconfigurable discrete distributed stiffness for inflated beam robots. In2020 IEEE International Conference on Robotics and Automation (ICRA), pages 9050–9056. IEEE, 2020

work page 2020
[39]

Inverse design of inflatable soft membranes through machine learning.Advanced Functional Materials, 32(16):2111610, 2022

Antonio Elia Forte, Paul Z Hanakata, Lishuai Jin, Emilia Zari, Ahmad Zareei, Matheus C Fernandes, Laura Sumner, Jonathan Alvarez, and Katia Bertoldi. Inverse design of inflatable soft membranes through machine learning.Advanced Functional Materials, 32(16):2111610, 2022

work page 2022
[40]

Design, kinematics, and control of a soft spatial fluidic elastomer manipulator.The International Journal of Robotics Research, 35(7):840–869, 2016

Andrew D Marchese and Daniela Rus. Design, kinematics, and control of a soft spatial fluidic elastomer manipulator.The International Journal of Robotics Research, 35(7):840–869, 2016

work page 2016
[41]

Autonomous discovery of tough structures.arXiv preprint arXiv:2308.02315, 2023

Kelsey L Snapp, Benjamin Verdier, Aldair Gongora, Samuel Silverman, Adedire D Adesiji, Elise F Morgan, Timothy J Lawton, Emily Whiting, and Keith A Brown. Autonomous discovery of tough structures.arXiv preprint arXiv:2308.02315, 2023

work page arXiv 2023
[42]

Stiffening in soft robotics: A review of the state of the art.IEEE Robotics & Automation Magazine, 23(3):93–106, 2016

Mariangela Manti, Vito Cacucciolo, and Matteo Cianchetti. Stiffening in soft robotics: A review of the state of the art.IEEE Robotics & Automation Magazine, 23(3):93–106, 2016

work page 2016
[43]

Design, fabrication and control of soft robots.Nature, 521(7553):467–475, 2015

Daniela Rus and Michael T Tolley. Design, fabrication and control of soft robots.Nature, 521(7553):467–475, 2015

work page 2015
[44]

Multigait soft robot.Proceed- ings of the National Academy of Sciences, 108(51):20400–20403, 2011

Robert F Shepherd, Filip Ilievski, Wonjae Choi, Stephen A Morin, Adam A Stokes, Aaron D Mazzeo, Xin Chen, Michael Wang, and George M Whitesides. Multigait soft robot.Proceed- ings of the National Academy of Sciences, 108(51):20400–20403, 2011

work page 2011
[45]

Jsel: Jam- ming skin enabled locomotion

Erik Steltz, Annan Mozeika, Nick Rodenberg, Eric Brown, and Heinrich M Jaeger. Jsel: Jam- ming skin enabled locomotion. In2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, pages 5672–5677. IEEE, 2009

work page 2009
[46]

Materials with electroprogrammable stiffness.Advanced Materials, page 2007952, 2021

David J Levine, Kevin T Turner, and James H Pikul. Materials with electroprogrammable stiffness.Advanced Materials, page 2007952, 2021

work page 2021
[47]

A variable stiffness dielectric elastomer actuator based on electrostatic chucking.Soft matter, 13(18):3440–3448, 2017

Hiroya Imamura, Kevin Kadooka, and Minoru Taya. A variable stiffness dielectric elastomer actuator based on electrostatic chucking.Soft matter, 13(18):3440–3448, 2017

work page 2017
[48]

Active Shape Control and Phase 123 CoexistenceofDielectricElastomerMembraneWithPatternedElectrodes.Journal of Applied Mechanics, 81(3), 10 2013

Zhanan Zou, Tiefeng Li, Shaoxing Qu, and Honghui Yu. Active Shape Control and Phase 123 CoexistenceofDielectricElastomerMembraneWithPatternedElectrodes.Journal of Applied Mechanics, 81(3), 10 2013. 031016

work page 2013
[49]

High force density textile electrostatic clutch.Advanced Materials Technologies, 5(4):1900895, 2019

Ronan Hinchet and Herbert Shea. High force density textile electrostatic clutch.Advanced Materials Technologies, 5(4):1900895, 2019

work page 2019
[50]

Dextres: Wearable haptic feedback for grasping in vr via a thin form-factor electrostatic brake

Ronan Hinchet, Velko Vechev, Herbert Shea, and Otmar Hilliges. Dextres: Wearable haptic feedback for grasping in vr via a thin form-factor electrostatic brake. InProceedings of the 31st Annual ACM Symposium on User Interface Software and Technology, pages 901–912, 2018

work page 2018
[51]

The effects of electroadhesive clutch design parameters on performance characteristics.Journal of Intelligent Material Systems and Structures, 29(19):3804–3828, 2018

Stuart B Diller, Steven H Collins, and Carmel Majidi. The effects of electroadhesive clutch design parameters on performance characteristics.Journal of Intelligent Material Systems and Structures, 29(19):3804–3828, 2018

work page 2018
[52]

A lightweight, low-power electroadhesive clutch and spring for exoskeleton actuation

Stuart Diller, Carmel Majidi, and Steven H Collins. A lightweight, low-power electroadhesive clutch and spring for exoskeleton actuation. In2016 IEEE International Conference on Robotics and Automation (ICRA), pages 682–689. IEEE, 2016

work page 2016
[53]

Soft pneumatic grippers embedded with stretchable electroadhesion

Jianglong Guo, Khaled Elgeneidy, Chaoqun Xiang, Niels Lohse, Laura Justham, and Jonathan Rossiter. Soft pneumatic grippers embedded with stretchable electroadhesion. Smart Materials and Structures, 27(5):055006, 2018

work page 2018
[54]

Active con- nection mechanism for soft modular robots.Advanced Robotics, 26(7):785–798, 2012

Jürg Germann, Michael Dommer, Ramon Pericet-Camara, and Dario Floreano. Active con- nection mechanism for soft modular robots.Advanced Robotics, 26(7):785–798, 2012

work page 2012
[55]

Soft-bubble: A highly compliant dense geometry tactile sensor for robot manipulation

Alex Alspach, Kunimatsu Hashimoto, Naveen Kuppuswamy, and Russ Tedrake. Soft-bubble: A highly compliant dense geometry tactile sensor for robot manipulation. In2019 2nd IEEE International Conference on Soft Robotics (RoboSoft), pages 597–604. IEEE, 2019

work page 2019
[56]

Dassault Systèmes. Abaqus. https://www.3ds.com/products- services/simulia/products/abaqus/, 2020/Standard

work page 2020
[57]

Demo 1: Multi-chamber bending spa

Soft Robotics Toolkit. Demo 1: Multi-chamber bending spa. https://softroboticstoolkit.com/book/modeling-soft-pneumatic-actuators/modeling/demo-1, 2016

work page 2016
[58]

Cloudcompare.France: EDF R&D Telecom ParisTech, 2016

Daniel Girardeau-Montaut. Cloudcompare.France: EDF R&D Telecom ParisTech, 2016

work page 2016
[59]

Elastic energy-recycling actuators for efficient robots

Erez Krimsky and Steven H Collins. Elastic energy-recycling actuators for efficient robots. Science Robotics, 9(88):eadj7246, 2024

work page 2024
[60]

Reconfigurable soft body trajectories using unidirectionally stretchable composite laminae.Nature Communications, 10(1):1–8, 2019

Sang Yup Kim, Robert Baines, Joran Booth, Nikolaos Vasios, Katia Bertoldi, and Rebecca Kramer-Bottiglio. Reconfigurable soft body trajectories using unidirectionally stretchable composite laminae.Nature Communications, 10(1):1–8, 2019. 124

work page 2019
[61]

Galloway, Panagiotis Polygerinos, Conor J

Kevin C. Galloway, Panagiotis Polygerinos, Conor J. Walsh, and Robert J. Wood. Mechani- cally programmable bend radius for fiber-reinforced soft actuators. In2013 16th International Conference on Advanced Robotics (ICAR), pages 1–6, 2013

work page 2013
[62]

An untethered soft cellular robot with variable volume, friction, and unit-to-unit cohesion

Matthew R Devlin, Brad T Young, Nicholas D Naclerio, David A Haggerty, and Elliot W Hawkes. An untethered soft cellular robot with variable volume, friction, and unit-to-unit cohesion. In2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 3333–3339. IEEE, 2020

work page 2020
[63]

Electroadhesive clutches for programmable shape morphing of soft actuators

Gregory M Campbell, Jessica Yin, Yuyang Song, Umesh Gandhi, Mark Yim, and James Pikul. Electroadhesive clutches for programmable shape morphing of soft actuators. In 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 11594–11599. IEEE, 2022

work page 2022
[64]

Glove-and sleeve-format variable-friction electrostatic clutches for kinesthetic haptics.Advanced Intelligent Systems, 4(12):2200174, 2022

Ronan J Hinchet and Herbert Shea. Glove-and sleeve-format variable-friction electrostatic clutches for kinesthetic haptics.Advanced Intelligent Systems, 4(12):2200174, 2022

work page 2022
[65]

Levine, Gokulanand M

David J. Levine, Gokulanand M. Iyer, R. Daelan Roosa, Kevin T. Turner, and James H. Pikul. A mechanics-based approach to realize high–force capacity electroadhesives for robots. Science Robotics, 7(72):eabo2179, 2022

work page 2022
[66]

A new constitutive relation for rubber.Rubber Chemistry and Technology, 69(1):59–61, 1996

Alan N Gent. A new constitutive relation for rubber.Rubber Chemistry and Technology, 69(1):59–61, 1996

work page 1996
[67]

Electro-adhesive tubular clutch for variable-stiffness robots

Yi Sun, Krishna Manaswi Digumarti, Hoang-Vu Phan, Omar Aloui, and Dario Floreano. Electro-adhesive tubular clutch for variable-stiffness robots. In2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 9628–9634. IEEE, 2022

work page 2022
[68]

Mechanical responses of ecoflex silicone rubber: Compressible and incom- pressible behaviors.Journal of Applied Polymer Science, 136(5):47025, 2019

Daniel Steck, Jian Qu, S Baghbani Kordmahale, Daniel Tscharnuter, Anastasia Muliana, and Jun Kameoka. Mechanical responses of ecoflex silicone rubber: Compressible and incom- pressible behaviors.Journal of Applied Polymer Science, 136(5):47025, 2019

work page 2019
[69]

A review on material models for isotropic hyperelasticity.International Journal of Mechanical System Dynamics, 1(1):71–88, 2021

Stephen K Melly, Liwu Liu, Yanju Liu, and Jinsong Leng. A review on material models for isotropic hyperelasticity.International Journal of Mechanical System Dynamics, 1(1):71–88, 2021

work page 2021
[70]

On the contact problem of an inflated spherical nonlinear mem- brane.Journal of Applied Mechanics, 1973

WW Feng and W-H Yang. On the contact problem of an inflated spherical nonlinear mem- brane.Journal of Applied Mechanics, 1973

work page 1973
[71]

On the general contact problem of an inflated nonlinear plane membrane.International Journal of Solids and Structures, 11(4):437–448, 1975

William W Feng and Huang Pangnan. On the general contact problem of an inflated nonlinear plane membrane.International Journal of Solids and Structures, 11(4):437–448, 1975

work page 1975
[72]

Model and validation of a highly extensible and tough actuator based on a ballooning membrane

Nicolas Herzig, Joanna Jones, Eduardo Perez-Guagnelli, and Dana D Damian. Model and validation of a highly extensible and tough actuator based on a ballooning membrane. In2021 IEEE International Conference on Robotics and Automation (ICRA), pages 11961–11967. 125 IEEE, 2021

work page 2021
[73]

Modelling the inflation of an elastic membrane with a load

Ge Shi, Azadeh Shariati, Jialei Shi, Nicolas Herzig, Sara-Adela Abad, and Helge A Wurde- mann. Modelling the inflation of an elastic membrane with a load. In2023 IEEE International Conference on Soft Robotics (RoboSoft), pages 1–8. IEEE, 2023

work page 2023
[74]

Compact multilayer extension actuators for reconfigurable soft robots.Soft Robotics, 10(2):301–313, 2023

Jonathan William Ambrose, Nicholas Zhang Rong Chiang, Dylan Sin You Cheah, and Chen- Hua Yeow. Compact multilayer extension actuators for reconfigurable soft robots.Soft Robotics, 10(2):301–313, 2023

work page 2023
[75]

Design and modeling of generalized fiber-reinforced pneumatic soft actuators.IEEE Transactions on Robotics, 31(3):536–545, 2015

Joshua Bishop-Moser and Sridhar Kota. Design and modeling of generalized fiber-reinforced pneumatic soft actuators.IEEE Transactions on Robotics, 31(3):536–545, 2015

work page 2015
[76]

A survey of deep active learning.ACM computing surveys (CSUR), 54(9):1–40, 2021

Pengzhen Ren, Yun Xiao, Xiaojun Chang, Po-Yao Huang, Zhihui Li, Brij B Gupta, Xiaojiang Chen, and Xin Wang. A survey of deep active learning.ACM computing surveys (CSUR), 54(9):1–40, 2021

work page 2021
[77]

Evolution gym: A large-scale benchmark for evolving soft robots.Advances in Neural Information Processing Systems, 34:2201–2214, 2021

Jagdeep Bhatia, Holly Jackson, Yunsheng Tian, Jie Xu, and Wojciech Matusik. Evolution gym: A large-scale benchmark for evolving soft robots.Advances in Neural Information Processing Systems, 34:2201–2214, 2021

work page 2021
[78]

Multimodal proximity and visuotactile sensing with a selectively transmissive soft membrane

Jessica Yin, Gregory M Campbell, James Pikul, and Mark Yim. Multimodal proximity and visuotactile sensing with a selectively transmissive soft membrane. In2022 IEEE 5th International Conference on Soft Robotics (RoboSoft), pages 802–808. IEEE, 2022

work page 2022
[79]

An instrument to obtain the correct biaxial hyperelastic parameters of silicones for accurate dea modelling

Samuel Rosset, Luc Maffli, Simon Houis, and Herbert R Shea. An instrument to obtain the correct biaxial hyperelastic parameters of silicones for accurate dea modelling. InElectroactive Polymer Actuators and Devices (EAPAD) 2014, volume 9056, page 90560M. International Society for Optics and Photonics, 2014

work page 2014
[80]

Cambridge University Press, 2005

Tsu-Wei Chou.Microstructural Design of Fiber Composites. Cambridge University Press, 2005

work page 2005

Showing first 80 references.