Soft Pneumatic Actuators for Robotics: From Motion Generation to Performance Optimization
Listen
Radio episode about this paper
Transcript
Introduction to the show: ident: Robotics Radio. Generated commentary on the latest robotics and control papers.
Rosa: I'm Rosa.
Dev: And I'm Dev, here with Taro.
Rosa: We're looking at the paper: "Soft Pneumatic Actuators for Robotics".
Dev: Here's the gist of the paper. Soft pneumatic actuators are widely used in soft robotics because they can produce large motions while remaining compliant enough to interact safely with objects, environments, and the human body.
Rosa: The performance of these actuators is not solely determined by pressure but depends on structural features like chamber shape, reinforcements, folds, material stiffness, and constraints.
Dev: This review examines soft pneumatic actuators according to the design strategies used to generate four motion classes: linear, bending, twisting, and omnidirectional actuation.
Rosa: It analyzes structural features that define the deformation path for each class, including braid angle, fold geometry, fiber orientation, chamber arrangement, structural asymmetry, and internal constraint layers.
Title and authors: Rosa: The paper, "Soft Pneumatic Actuators for Robotics: From Motion Generation to Performance Optimization," is essentially taking a broad review of soft pneumatic actuators and making it much more practical for engineers building actual robots.
Dev: They aren't just reviewing the mechanisms; they are focusing on the trade-offs involved when you choose one design over another, especially when you have to consider real-world conditions.
Taro: I mean, it seems like they’re trying to give us a clearer way to think about what makes an actuator useful in practice, not just theoretically interesting.
Rosa: That’s right. They emphasize that the best design isn't the one with the biggest stroke or the sharpest bend; it's the one that gives you enough constraint to do what you need while keeping that necessary compliance.
Dev: It shifts our focus from just achieving a certain motion output to optimizing things like air demand and durability, which are crucial for any real-time system.
Taro: So, instead of asking "Can this move this far?", we’re being asked to ask "How reliably and efficiently can this do it under load?"
Rosa: Precisely. It sets the stage for a much more rigorous evaluation process when selecting actuators for a project.
The paper's summary: Dev: Now they get into the core analysis of how different structural features—like fiber orientation or chamber arrangement—directly influence the deformation path for each motion class.
Rosa: For linear actuators, they look at things like Pneumatic Artificial Muscles, Bellows actuators, and Fiber-reinforced soft actuators, showing how their specific internal mechanisms control axial extension or shortening.
Taro: I’m interested in what they say about the constraints that guide the deformation path for those linear types.
Dev: They point out that for things like Linear soft sleeve actuators, you need internal tie-restraining layers specifically to stop radial instability and make sure it moves straight.
Rosa: And they don't just stop there; they look at how design choices affect force generation, air demand, repeatability, and fabrication difficulty.
Dev: They argue that motion output by itself is insufficient because we need to consider the pressure range, the loading condition, and how much air you actually have to pump in.
The paper's improvements: Rosa: What the authors suggest for improvement is a move away from just reporting motion metrics and toward reporting what you actually need to do with that motion.
Dev: They push us to prioritize things like pressure range, loading condition, air volume, hysteresis, durability, and fabrication quality instead of just the bending angle or twist range.
Taro: That makes sense because if we only report the angle of a bend without saying how much force it takes or how long it lasts under cycling, that information is pretty useless for testing.
Rosa: They suggest a better reporting practice overall, something that will enable more reliable comparisons between different actuator designs and help us design systems that actually work.
Dev: So the main suggestion is to report conditions like pressure range and hysteresis because those factors are what really change the performance under real operating conditions.
Conclusion: Rosa: So, to wrap up, the paper on "Soft Pneumatic Actuators for Robotics: From Motion Generation to Performance Optimization" concludes that actuator performance isn't about one motion type alone; it's about how the structure manages the conversion of pressure into useful deformation while strictly limiting unwanted deformation.
Dev: They stress that we need to move past just reporting peak motion numbers and start reporting on conditions like pressure range, loading condition, air volume, hysteresis, durability and fabrication quality for any comparison to be meaningful.
Taro: I just want to add that the best design is the one that gives you enough constraint to produce the intended motion while preserving useful compliance for whatever task you have in mind.
Rosa: That’s a solid way of putting it, Taro. So, moving forward, we should be asking what conditions are needed to achieve a certain outcome rather than just measuring the outcome itself.
Dev: Right. And that brings us back to how we test these things on the ground—we need those comprehensive metrics before we even think about putting them into a control loop or testing them in a real environment.
cs.RO
Submitted: 2026-05-24
Updated: 2026-11-11
DOI: 10.2174/0122127976503800260922074606
License: http://creativecommons.org/licenses/by/4.0/
Importance score: 76/100
The gist: Soft pneumatic actuators are widely used in soft robotics because they can produce large motions while remaining compliant enough to interact safely with objects, environments, and the human body.
Key concepts
- Motion Classes
- Soft actuators are categorized into four types: linear (straight movement), bending (curvature), twisting (rotation), and omnidirectional (multi-directional movement). Each class requires different structural designs, such as specific chamber arrangements or internal constraints, to achieve that particular type of motion.
- Structural Features
- The physical makeup of the actuator—including fold geometry, fiber orientation, braid angle, and chamber shape—is crucial. These features determine how much pressure creates deformation and how well the structure limits uncontrolled expansion or unwanted movement during operation.
- Performance Metrics
- Evaluating an actuator requires more than just measuring motion output. Key metrics include pressure range, force generation under load, air demand (volume needed), repeatability, durability, and fabrication difficulty. These factors determine the practical utility of a design in a real robotic system.
Terminology
Summary
Soft pneumatic actuators are widely used in soft robotics because they can produce large motions while remaining compliant enough to interact safely with objects, environments, and the human body. p. 0 1
Review ARTICLE
Soft Pneumatic Actuators for Soft Robotics: A Motion-Based Review
of Actuation Mechanisms and Performance Trade-offs
Mohammed Abboodi; https://orcid. org/0009-0002-4645-0026
Abstract: Soft pneumatic actuators are widely used in soft robotics because they can produce large
motions while remaining compliant enough to interact safely with objects, environments, and the human
body. However, their performance is not solely determined by pressure. Instead, the response depends
on the way the actuator is built, including the shape of its chambers, the placement of reinforcements,
the use of folds, material stiffness, and the constraints that guide its deformation. However, their performance is not solely determined by pressure. Instead, the response depends
on the way the actuator is built, including the shape of its chambers, the placement of reinforcements,
the use of folds, material stiffness, and the constraints that guide its deformation. As the literature has
expanded, it has become more difficult to determine which mechanism is most suitable for a given
application and which reported results can be compared across studies. This review examines soft
pneumatic actuators according to the design strategies used to generate four motion classes: linear,
bending, twisting, and omnidirectional actuation. As the literature has
expanded, it has become more difficult to determine which mechanism is most suitable for a given
application and which reported results can be compared across studies. This review examines soft
pneumatic actuators according to the design strategies used to generate four motion classes: linear,
bending, twisting, and omnidirectional actuation. This review examines soft
pneumatic actuators according to the design strategies used to generate four motion classes: linear,
bending, twisting, and omnidirectional actuation. For each class, it analyzes the structural features that
define the deformation path, including braid angle, fold geometry, fiber orientation, chamber
arrangement, structural asymmetry, and internal constraint layers. This review examines soft
pneumatic actuators according to the design strategies used to generate four motion classes: linear,
bending, twisting, and omnidirectional actuation. For each class, it analyzes the structural features that
define the deformation path, including braid angle, fold geometry, fiber orientation, chamber
arrangement, structural asymmetry, and internal constraint layers. It then discusses how the design
choice affect motion output, force generation, air demand, repeatability, durability, fabrication
difficulty, and robotic integration. The review further identifies key conditions that must be considered
when selecting or comparing actuators, including pressure, loading condition, actuator size, pneumatic
supply, and hysteresis This approach helps explain why actuators with similar motion outputs may differ
substantially in design requirements, pneumatic demand, and practical suitability. It then discusses how the design
choice affect motion output, force generation, air demand, repeatability, durability, fabrication
difficulty, and robotic integration. The review further identifies key conditions that must be considered
when selecting or comparing actuators, including pressure, loading condition, actuator size, pneumatic
supply, and hysteresis This approach helps explain why actuators with similar motion outputs may differ
substantially in design requirements, pneumatic demand, and practical suitability.Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Motion Class Analysis
The paper categorizes soft pneumatic actuators into four primary motion classes: linear, bending, twisting, and omnidirectional actuation. For linear actuators, the review analyzes different mechanisms such as Pneumatic Artificial Muscles (PAMs), Bellows actuators, Fiber-reinforced soft actuators (FREEs), and Linear soft sleeve actuators (LSSAs). p. 1 The growing number of soft pneumatic actuator
designs has made mechanism selection more difficult. Similar motions can be produced by very different
architectures, including pneumatic muscles, bellows,
PneuNets, fiber-reinforced chambers, textile actuators,
and sleeve-based mechanisms. In these actuators, pressure
first expands a compliant chamber, while a braided,
pleated, netted, or embedded constraint redirects that
expansion into axial shortening and tensile force [13]. The McKibben muscle shows this mechanism clearly:
an elastomeric bladder inflates inside a helical braided
sleeve, the sleeve angle changes as the diameter
increases, and the muscle contracts along its length
[13], [14]. Bellows reduce this problem by adding geometry that
constrains the wall. Corrugations, convolutions, or
prescribed folds guide the deformation path, increase
resistance to uncontrolled radial expansion, and make
axial motion more repeatable [9], [10]. 3 Fiber-reinforced soft actuators for linear
motion (FREEs)
Fiber-reinforced soft actuators use anisotropic
reinforcement to control how a pressurized
elastomeric tube deforms. The fibers prevent the tube
from expanding freely outward and guide the
deformation according to the reinforcement layout
[40]. 4 Linear soft sleeve actuators for axial motion
(LSSAs)
Linear soft sleeve actuators (LSSA) represent a new
approach for generating linear motion. In this actuator,
linear motion does not come from the free expansion
of a large chamber, but from the controlled folding and
unfolding of a thin sleeve-like structure [23].Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Design Trade-offs in Actuation
The review emphasizes that motion output alone is insufficient for performance evaluation, as it must be judged by factors like force, stroke, air demand, repeatability, durability, fabrication method, and integration. For linear actuators like PAMs, the comparison requires considering pressure range and load condition because the pressure–force relation is nonlinear and history-dependent. p. 1 The same coupling,
however, makes their response difficult to predict. The
pressure–force relation changes with braid geometry,
interfacial friction, viscoelasticity, and end-region
deformation, so the measured behavior is nonlinear
and often history dependent [15]. These examples show that bellows design
is mainly a compromise between stroke, stiffness,
stability, and fatigue resistance. In conventional bellows, the most important design
variables are effective area, wall thickness,
convolution height, pitch, and number of convolutions
[32], [33]These parameters control axial compliance,
volume change per unit stroke, and stability under
external load. The second uses multiple
chambers, where differential pressure generates the
bending moment. Both strategies aim to convert radial
inflation into useful curvature while limiting
uncontrolled expansion. Too little constraint allows parasitic radial
deformation; too much constraint reduces compliance
and stroke. This makes LSSAs a useful example of a
broader principle in soft pneumatic actuator design:
the best geometry is not necessarily the most flexible
one, but the one that provides enough constraint to
preserve the intended motion
(a) (b) (c)
(d) (e) (f)
Figure1: Linear actuator: (a) Pleated PAM [46], (b) Netted muscles [47], (c) Linear bellows [48], (d) Origami linear actuator [34] , (e) Fiberreinforced linear actuators [41], (f) LSSA [23]Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Constraints and Complexity in Bending and Twisting
Bending actuators are analyzed through Pneumatic network actuators (PneuNets), fiber-reinforced bending soft actuators, and fabric-based pneumatic bending actuators. PneuNets generate bending through asymmetric expansion of patterned chambers, where chamber architecture controls air demand, strain level, response speed, and durability. p. 6 This result is
important because it shows that chamber architecture
controls not only curvature, but also air demand, strain
level, response speed, and durability. The pressure-volume results from the same study are
more informative than bending angle alone. Fiber-reinforced bending soft actuators show that
bending can be programmed effectively through
reinforcement-mediated anisotropy, but they also
illustrate the limits of relying on nominal geometry
alone as a predictor of performance. Their main
advantage lies in the ability to direct strain
mechanically and to suppress undesired radial
deformation more effectively than many
unconstrained designs. Weave or knit direction, seam compliance, sealing
quality, and bonding all affect the pressure–curvature
response. This makes fabric actuators easier to adapt,
but harder to reproduce consistently than many
monolithic silicone actuators. This can improve structural
consistency, but it also increases process complexity
and introduces additional sources of variability,
including layer alignment, encapsulation quality, and
interface defects. Fiber-reinforced bending soft actuators show that
bending can be programmed effectively through
reinforcement-mediated anisotropy, but they also
illustrate the limits of relying on nominal geometry
alone as a predictor of performance.Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Omnidirectional Actuator Architectures
Omnidirectional soft pneumatic actuators are divided into parallel configurations, which trade compactness for modularity and load sharing, and monolithic single-structure configurations, which offer integration but are sensitive to ballooning. Parallel configurations utilize multiple linear elements arranged around a central axis, where the strength lies in modularity and redundancy rather than compactness. Monolithic designs minimize parts but are susceptible to ballooning, and recent research shifts toward parameterized design to make the pressure–shape relationship predictable. Sleeve-based omnidirectional actuators, like OSSA, combine multidirectional bending and extension in one compact sleeve by using internal constraints to reduce radial expansion. p. 9 Their persistent
limitations lie in variability and durability mechanisms
associated with textiles and seams, including
anisotropy drift, stitch fatigue, delamination, leakage,
and dependence on fabrication quality [12]. 4 Bending soft sleeve actuators (BSSAs)
Bending soft sleeve actuators (BSSAs) are a class of
pneumatic bending actuators that are implemented in
a sleeve architecture with internal constraints that
intentionally create an asymmetry in the pneumatic
expansion that produces the desired bending [23].Where the paper says it
Conclusion on Design Principles
The main finding is that actuator performance is not defined by motion type alone but by how the structure converts pressure into useful deformation while limiting unwanted deformation. The reviewed literature shows that peak motion metrics are insufficient for comparison, and future studies must report conditions like pressure range, loading condition, air volume, hysteresis, durability and fabrication quality. p. 3 Waterbomb-derived and
related folded patterns allow contraction and force to
be tuned through fold geometry, but comparison
remains difficult when studies report only
displacement. Blocked force, pressure range,
hysteresis, repeatability, cycle life, and loading
condition are needed to judge whether the reported
performance comes from the actuator design itself or
from the test conditions [35]
Bellows-based linear actuators therefore show that
axial motion is not difficult to produce; the harder
problem is controlling where the structure deforms and
how stable that deformation remains under load. Waterbomb-derived and
related folded patterns allow contraction and force to
be tuned through fold geometry, but comparison
remains difficult when studies report only
displacement. Blocked force, pressure range,
hysteresis, repeatability, cycle life, and loading
condition are needed to judge whether the reported
performance comes from the actuator design itself or
from the test conditions [35]
Bellows-based linear actuators therefore show that
axial motion is not difficult to produce; the harder
problem is controlling where the structure deforms and
how stable that deformation remains under load. Waterbomb-derived and
related folded patterns allow contraction and force to
be tuned through fold geometry, but comparison
remains difficult when studies report only
displacement. Blocked force, pressure range,
hysteresis, repeatability, cycle life, and loading
condition are needed to judge whether the reported
performance comes from the actuator design itself or
from the test conditions [35]
Bellows-based linear actuators therefore show that
axial motion is not difficult to produce; the harder
problem is controlling where the structure deforms and
how stable that deformation remains under load. The review further identifies key conditions that must be considered
when selecting or comparing actuators, including pressure, loading condition, actuator size, pneumatic
supply, and hysteresis This approach helps explain why actuators with similar motion outputs may differ
substantially in design requirements, pneumatic demand, and practical suitability. It also highlights the
design priorities needed for compact, efficient, repeatable, and deployable soft pneumatic systems in
wearable, biomedical, and mobile robotic applications. The review further identifies key conditions that must be considered
when selecting or comparing actuators, including pressure, loading condition, actuator size, pneumatic
supply, and hysteresis This approach helps explain why actuators with similar motion outputs may differ
substantially in design requirements, pneumatic demand, and practical suitability. It also highlights the
design priorities needed for compact, efficient, repeatable, and deployable soft pneumatic systems in
wearable, biomedical, and mobile robotic applications. The review further identifies key conditions that must be considered
when selecting or comparing actuators, including pressure, loading condition, actuator size, pneumatic
supply, and hysteresis This approach helps explain why actuators with similar motion outputs may differ
substantially in design requirements, pneumatic demand, and practical suitability. It also highlights the
design priorities needed for compact, efficient, repeatable, and deployable soft pneumatic systems in
wearable, biomedical, and mobile robotic applications. Too little constraint allows parasitic radial
deformation; too much constraint reduces compliance
and stroke. This makes LSSAs a useful example of a
broader principle in soft pneumatic actuator design:
the best geometry is not necessarily the most flexible
one, but the one that provides enough constraint to
preserve the intended motion
(a) (b) (c)
(d) (e) (f)
Figure1: Linear actuator: (a) Pleated PAM [46], (b) Netted muscles [47], (c) Linear bellows [48], (d) Origami linear actuator [34] , (e) Fiberreinforced linear actuators [41], (f) LSSA [23] Too little constraint allows parasitic radial
deformation; too much constraint reduces compliance
and stroke. This makes LSSAs a useful example of a
broader principle in soft pneumatic actuator design:
the best geometry is not necessarily the most flexible
one, but the one that provides enough constraint to
preserve the intended motion
(a) (b) (c)
(d) (e) (f)
Figure1: Linear actuator: (a) Pleated PAM [46], (b) Netted muscles [47], (c) Linear bellows [48], (d) Origami linear actuator [34] , (e) Fiberreinforced linear actuators [41], (f) LSSA [23] Too little constraint allows parasitic radial
deformation; too much constraint reduces compliance
and stroke. This makes LSSAs a useful example of a
broader principle in soft pneumatic actuator design:
the best geometry is not necessarily the most flexible
one, but the one that provides enough constraint to
preserve the intended motion
(a) (b) (c)
(d) (e) (f)
Figure1: Linear actuator: (a) Pleated PAM [46], (b) Netted muscles [47], (c) Linear bellows [48], (d) Origami linear actuator [34] , (e) Fiberreinforced linear actuators [41], (f) LSSA [23]Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Future Research Directions
Future research should transition away from reporting motion and focus on what should be done to produce the motion. For linear actuators, there is a need to increase force and stroke while decreasing pneumatic volume requirement and axial stiffness, hysteresis. p. 5 The
importance of this progression is not only the increase
in stroke, but the improved balance between axial
compliance and structural stability. LSSAs offer three practical advantages over other
linear soft pneumatic actuators. The
importance of this progression is not only the increase
in stroke, but the improved balance between axial
compliance and structural stability. LSSAs offer three practical advantages over other
linear soft pneumatic actuators. For this reason, peak displacement
alone is not a sufficient performance measure. Pressure range, external load, blocked force or loaddependent stroke, repeatability, hysteresis, and
durability should be reported before bellows actuators
from different studies are compared. For this reason, peak displacement
alone is not a sufficient performance measure. Pressure range, external load, blocked force or loaddependent stroke, repeatability, hysteresis, and
durability should be reported before bellows actuators
from different studies are compared. Waterbomb-derived and
related folded patterns allow contraction and force to
be tuned through fold geometry, but comparison
remains difficult when studies report only
displacement. Blocked force, pressure range,
hysteresis, repeatability, cycle life, and loading
condition are needed to judge whether the reported
performance comes from the actuator design itself or
from the test conditions [35]
Bellows-based linear actuators therefore show that
axial motion is not difficult to produce; the harder
problem is controlling where the structure deforms and
how stable that deformation remains under load. Waterbomb-derived and
related folded patterns allow contraction and force to
be tuned through fold geometry, but comparison
remains difficult when studies report only
displacement. Blocked force, pressure range,
hysteresis, repeatability, cycle life, and loading
condition are needed to judge whether the reported
performance comes from the actuator design itself or
from the test conditions [35]
Bellows-based linear actuators therefore show that
axial motion is not difficult to produce; the harder
problem is controlling where the structure deforms and
how stable that deformation remains under load. Similar motions can be produced by very different
architectures, including pneumatic muscles, bellows,
PneuNets, fiber-reinforced chambers, textile actuators,
and sleeve-based mechanisms. These designs may
appear comparable when judged only by stroke,
bending angle, twisting range, or workspace, but their
performance can change substantially with actuator
size, pressure range, loading condition, flow capacity,
fabrication method, and test setup. Similar motions can be produced by very different
architectures, including pneumatic muscles, bellows,
PneuNets, fiber-reinforced chambers, textile actuators,
and sleeve-based mechanisms. These designs may
appear comparable when judged only by stroke,
bending angle, twisting range, or workspace, but their
performance can change substantially with actuator
size, pressure range, loading condition, flow capacity,
fabrication method, and test setup. This gives fabric
actuators a wide design space, but it also makes the
design harder to describe with a few simple
parameters. Two actuators with the same nominal
pattern may behave differently if the textile stiffness,
seam quality, or bonding changes. This gives fabric
actuators a wide design space, but it also makes the
design harder to describe with a few simple
parameters. Two actuators with the same nominal
pattern may behave differently if the textile stiffness,
seam quality, or bonding changes.Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Final Summary Statement
The main finding is that actuator performance is not defined by motion type alone but by how the structure converts pressure into useful deformation while limiting unwanted deformation. The reviewed literature shows that peak motion metrics are insufficient for comparison, and future studies must report conditions like pressure range, loading condition, air volume, hysteresis, durability and fabrication quality. A better reporting practice is needed to enable more reliable comparisons between actuators and help design efficient systems. The best actuator design provides enough constraint to produce the intended motion while preserving useful compliance. A better reporting practice would enable more reliable comparisons between actuators and help design efficient, repeatable and practical soft pneumatic systems for wearable, biomedical and mobile robotic applications. p. 0 The review further identifies key conditions that must be considered
when selecting or comparing actuators, including pressure, loading condition, actuator size, pneumatic
supply, and hysteresis This approach helps explain why actuators with similar motion outputs may differ
substantially in design requirements, pneumatic demand, and practical suitability. It also highlights the
design priorities needed for compact, efficient, repeatable, and deployable soft pneumatic systems in
wearable, biomedical, and mobile robotic applications. The review further identifies key conditions that must be considered
when selecting or comparing actuators, including pressure, loading condition, actuator size, pneumatic
supply, and hysteresis This approach helps explain why actuators with similar motion outputs may differ
substantially in design requirements, pneumatic demand, and practical suitability. It also highlights the
design priorities needed for compact, efficient, repeatable, and deployable soft pneumatic systems in
wearable, biomedical, and mobile robotic applications.Where the paper says it
Where the paper says it
--- Page 1 ---
Soft pneumatic actuators are widely used in soft robotics because they can produce large motions while remaining compliant enough to interact safely with objects, environments, and the human body. The performance of these actuators is not solely determined by pressure but depends on structural features like chamber shape, reinforcements, folds, material stiffness, and constraints. This review examines soft pneumatic actuators according to the design strategies used to generate four motion classes: linear, bending, twisting, and omnidirectional actuation. It analyzes structural features that define the deformation path for each class, including braid angle, fold geometry, fiber orientation, chamber arrangement, structural asymmetry, and internal constraint layers. The review discusses how design choices affect motion output, force generation, air demand, repeatability, durability, fabrication difficulty, and robotic integration.
The main finding is that actuator performance is not defined by motion type alone but by how the structure converts pressure into useful deformation while limiting unwanted deformation. The reviewed literature shows that peak motion metrics are insufficient for comparison, and future studies must report conditions like pressure range, loading condition, air volume, hysteresis, durability and fabrication quality. A better reporting practice is needed to enable more reliable comparisons between actuators and help design efficient systems. The best actuator design provides enough constraint to produce the intended motion while preserving useful compliance. A better reporting practice would enable more reliable comparisons between actuators and help design efficient, repeatable and practical soft pneumatic systems for wearable, biomedical and mobile robotic applications.
Future research should transition away from reporting motion to focusing on what should be done to produce the motion. For linear actuators, there is a need to increase force and stroke while decreasing pneumatic volume requirement and axial stiffness, hysteresis. For bending actuators, pressure-volume behavior, force under load, actuation rate, hysteresis and cyclic durability should be prioritized over bending angle alone. For twisting and rotary actuators, studies must report torque and coupling with other motions. Further research is needed for sleeve-based twisting actuators to explore their potential for bidirectional rotation and consistent torque production. The focus should also be on manufacturing variability, such as fiber placement, seam stiffness, performance of the bonding, leakage and textile anisotropy in fabric actuators.">
Green — the paper says it, and the page is printed. Red — no passage carries it, so treat that sentence as unverified. The same check runs on your own text: check a summary against its source, $5.
Improvements for AI systems
-
Precision Actuator Selection based on Constraints: The AI system can select actuators by analyzing how constraints guide deformation, rather than just motion class alone. This allows it to choose a design that produces
useful motion while limiting unwanted deformation
based on the specific application needs of the soft robotic system. -
Performance Comparison using Comprehensive Metrics: The AI can compare actuators by moving beyond simple metrics like
stroke or bending angle alone.
It can assess performance by reportingpressure range, loading condition, air volume, hysteresis, durability and fabrication quality
to ensure reliable comparisons between studies. -
Design Optimization for Linear Actuators: For linear actuators like PAMs and LSSAs, the AI can optimize design parameters based on trade-offs such as
axial stiffness and force-displacement response.
It can specifically investigate theinfluence of tie-restraining layers, fold geometry, wall thickness and manufacturing quality on axial stiffness and force–displacement response.
-
Bending Actuator Performance Assessment: The system can evaluate bending actuators by considering the pneumatic cost alongside the motion. It can distinguish between designs by analyzing
pressure, air volume, force output, and fabrication effort
to determine if a design is superior for a specific task. -
Twisting Actuator Analysis: For twisting actuators, the AI can assess reliability by looking beyond just the generated twist angle. It should report on
torque, hysteresis, repeatability and coupling with bending or axial motion
to understand the practical performance under cyclic loading. -
Omnidirectional Actuator Robustness Check: When evaluating omnidirectional systems, the AI can assess their stability by focusing on
ballooning, chamber coupling, and geometry-dependent control errors.
This ensures that the chosen architecture provides astable pressure-shape response while limiting radial growth and maintaining durability.
Abstract
Soft pneumatic actuators are widely used in soft robotics because they can produce large motions while remaining compliant enough to interact safely with objects, environments, and the human body. However, their performance is not solely determined by pressure. Instead, the response depends on the way the actuator is built, including the shape of its chambers, the placement of reinforcements, the use of folds, material stiffness, and the constraints that guide its deformation. As the literature has expanded, it has become more difficult to determine which mechanism is most suitable for a given application and which reported results can be compared across studies. This review examines soft pneumatic actuators according to the design strategies used to generate four motion classes: linear, bending, twisting, and omnidirectional actuation. For each class, it analyzes the structural features that define the deformation path, including braid angle, fold geometry, fiber orientation, chamber arrangement, structural asymmetry, and internal constraint layers. It then discusses how the design choice affect motion output, force generation, air demand, repeatability, durability, fabrication difficulty, and robotic integration. The review further identifies key conditions that must be considered when selecting or comparing actuators, including pressure, loading condition, actuator size, pneumatic supply, and hysteresis This approach helps explain why actuators with similar motion outputs may differ substantially in design requirements, pneumatic demand, and practical suitability. It also highlights the design priorities needed for compact, efficient, repeatable, and deployable soft pneumatic systems in wearable, biomedical, and mobile robotic applications.
Related papers
- Rethinking Actions: Continuity-Aware Priors for World-Model Planning
- MOSAIC: Modular Obstacle and Spatial-Aware Framework for Manipulation In Cluttered Scenes
- SAGAS: Semantic-Aware Graph-Assisted Stitching for Offline Temporal Logic Planning
- DexSeed: Expanding Human Hand-Object Interactions into Robot Demonstrations for Dexterous Policy Learning
- LaST0.5: A Generalist World Action Model with Interaction-Centric Latent Reasoning
- CIALLO: Learning Shared Intent Representations for Cross-Embodiment Manipulation