Design and analysis of coiled fiber reinforced soft pneumatic actuator

Singh, Govindra; Xiao, Chenzhang; Hsiao-Wecksler, Elizabeth T.; Krishnan, Girish

doi:10.1088/1748-3190/aab19c

Cited by 21 publications

(16 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Their attributes mainly stem from the compliant nature of their structural embodiment that is able to conform to different shapes and absorb rather than transmit impact loads. As a result soft robots may find applications in locomotion or navigation of unstructured terrain [2], human assistive or wearable devices [3] and manipulators and end effectors that handle delicate items [4]. However, the flexibility and softness of these robots leads to highly challenging control and modeling problems.…”

Section: Introductionmentioning

confidence: 99%

Open Loop Position Control of Soft Continuum Arm Using Deep Reinforcement Learning

Satheeshbabu

Uppalapati

Chowdhary

et al. 2019

2019 International Conference on Robotics and Automation (ICRA)

Self Cite

View full text Add to dashboard Cite

Soft robots undergo large nonlinear spatial deformations due to both inherent actuation and external loading. The physics underlying these deformations is complex, and often requires intricate analytical and numerical models. The complexity of these models may render traditional modelbased control difficult and unsuitable. Model-free methods offer an alternative for analyzing the behavior of such complex systems without the need for elaborate modeling techniques. In this paper, we present a model-free approach for open loop position control of a soft spatial continuum arm, based on deep reinforcement learning. The continuum arm is pneumatically actuated and attains a spatial workspace by a combination of unidirectional bending and bidirectional torsional deformation. We use Deep-Q Learning with experience replay to train the system in simulation. The efficacy and robustness of the control policy obtained from the system is validated both in simulation and on the continuum arm prototype for varying external loading conditions.

show abstract

Section: Introductionmentioning

confidence: 99%

Open Loop Position Control of Soft Continuum Arm Using Deep Reinforcement Learning

Satheeshbabu

Uppalapati

Chowdhary

et al. 2019

2019 International Conference on Robotics and Automation (ICRA)

Self Cite

View full text Add to dashboard Cite

show abstract

“…The helical pitch of these fibers guides the motion that the tube undergoes when internally pressurized. FREEs are used in several existing systems including exoskeletons (Koller et al, 2016; Park et al, 2014; Polygerinos et al, 2015a; Singh et al, 2018), soft manipulators (McMahan et al, 2006; Pritts and Rahn, 2004), grippers and hands (Deimel and Brock, 2016), vibration isolators (Scarborough et al, 2012), bio-inspired slithering systems (Branyan and Menguc, 2018), and parallel groupings that augment force generation (Robertson et al, 2017).…”

Section: Introductionmentioning

confidence: 99%

Comparison and experimental validation of predictive models for soft, fiber-reinforced actuators

Sedal

Wineman

Gillespie

2019

The International Journal of Robotics Research

View full text Add to dashboard Cite

Successful soft robot modeling approaches appearing in recent literature have been based on a variety of distinct theories, including traditional robotic theory, continuum mechanics, and machine learning. Though specific modeling techniques have been developed for and validated against already realized systems, their strengths and weaknesses have not been explicitly compared against each other. In this paper, we show how three distinct model structures -a lumped-parameter model, a continuum mechanical model, and a neural network-compare in capturing the gross trends and specific features of the force generation of soft robotic actuators. In particular, we study models for Fiber Reinforced Elastomeric Enclosures (FREEs), which are a popular choice of soft actuator and that are used in several soft articulated systems, including soft manipulators, exoskeletons, grippers, and locomoting soft robots. We generated benchmark data by testing eight FREE samples that spanned broad design and kinematic spaces and compared the models on their ability to predict the loading-deformation relationships of these samples. This comparison shows the predictive capabilities of each model on individual actuators and each model's generalizability across the design space. While the neural net achieved the highest peak performance, the first principles-based models generalized best across all actuator design parameters tested. The results highlight the essential roles of mathematical structure and experimental parameter determination in building high-performing, generalizable soft actuator models with varying effort invested in system identification.

show abstract

Section: Pneumatics and Hydraulicsmentioning

confidence: 99%

“…For instance, Takamizawa and co‐workers prepared “18 weave” muscles as an adaptive wearable (Figure 13f) 314. Coiled fiber pneumatic actuators were described by Singh et al as parts of an assistive device for walking with crutches (Figure 13g) 315…”

Section: Pneumatics and Hydraulicsmentioning

confidence: 99%

Materials as Machines

2020

View full text Add to dashboard Cite

of responsive materials as machines is in robotics. The vision, leadership, and research of Bar-Cohen is seminal in both invigorating and focusing current-day research activities to develop responsive materials [2] and implement [3] them as lightweight, dexterous, and gentle (e.g., soft) robotic elements. In this spirit, this review exhaustively details the materials, the nature of their stimuli-response, and discusses considerations for their implementation in robotic systems and subsystems.Robotics is a well-established but growing field of research. Sustained progress in both performance and functionality continue to be realized in commercial robotic systems largely based on conventional materials and their integration with mechanisms. A recent example is the Atlas robot from Boston Dynamics [4] (Figure 1a). The incorporation of stimuli-responsive materials in robotics has largely focused on component-level demonstrations to extend the performance of a subsystem (such as a hand or gripper).Stimuli-responsive materials, spanning nearly all classes of materials and size scales, are currently subject to widespread examination in corporate, government, and academic research laboratories (Figure 1b-d). [5][6][7] In some cases, these materials have already found widespread commercial implementation in end use and are comparatively mature. The materials and fundamentals of their responses are summarized in Figure 2. Shape memory alloys (SMAs) and ceramic piezoelectric materials are distinctive in that they are hard, stimuli-responsive materials. Deformation of these materials can produce large energy densities due to their inherent stiffness. Electroactive polymers (EAPs) remain a topic of considerable interest, particularly dielectric elastomer actuators (DEAs). Engineered systems are rapidly emerging and enabling performance gains in robotics, largely based on pneumatic or fluidic (such as HASEL [8] actuators) transport processes that localize deformation to generate force or produce motion. Soft materials, such as shape memory polymers (SMPs), hydrogels, and liquid crystalline polymer networks (LCNs) and elastomers (LCEs) may offer distinctive functional performance to robotic systems in allowing local control of deformation without the need for complex interfacing with mechanisms. As will be evident, each of these materials has inherent advantages and performance tradeoffs that must be considered in functional implementations. However, responsive material systems have a common obstacle to widespread use: the performance and Machines are systems that harness input power to extend or advance function. Fundamentally, machines are based on the integration of materials with mechanisms to accomplish tasks-such as generating motion or lifting an object. An emerging research paradigm is the design, synthesis, and integration of responsive materials within or as machines. Herein, a particular focus is the integration of responsive materials to enable robotic (machine) functions such as gripping, lifting, or motility (walk...

show abstract

Design and analysis of coiled fiber reinforced soft pneumatic actuator

Cited by 21 publications

References 38 publications

Open Loop Position Control of Soft Continuum Arm Using Deep Reinforcement Learning

Open Loop Position Control of Soft Continuum Arm Using Deep Reinforcement Learning

Comparison and experimental validation of predictive models for soft, fiber-reinforced actuators

Materials as Machines

Contact Info

Product

Resources

About