Software toolkit for modeling, simulation, and control of soft robots

Computational synthesis of locomotive soft robots by topology optimization

Locomotive soft robots (SoRos) have gained prominence due to their adaptability. Traditional locomotive SoRo design is based on limb structures inspired by biological organisms and requires human intervention. Evolutionary robotics, designed using evolutionary algorithms (EAs), have shown potential for automatic design. However, EA-based methods face the challenge of high computational cost when considering multiphysics in locomotion, including materials, actuations, and interactions with environments. Here, we present a design approach for pneumatic SoRos that integrates gradient-based topology optimization with multiphysics material point method (MPM) simulations. This approach starts with a simple initial shape (a cube with a central cavity). The topology optimization with MPM then automatically and iteratively designs the SoRo shape. We design two SoRos, one for walking and one for climbing. These SoRos are 3D printed and exhibit the same locomotion features as in the simulations. This study presents an efficient strategy for designing SoRos, demonstrating that a purely mathematical process can produce limb-like structures seen in biological organisms.

Soft robotics for farm to fork: applications in agriculture & farming

Agricultural tasks and environments range from harsh field conditions with semi-structured produce or animals, through to post-processing tasks in food-processing environments. From farm to fork, the development and application of soft robotics offers a plethora of potential uses. Robust yet compliant interactions between farm produce and machines will enable new capabilities and optimize existing processes. There is also an opportunity to explore how modeling tools used in soft robotics can be applied to improve our representation and understanding of the soft and compliant structures common in agriculture. In this review, we seek to highlight the potential for soft robotics technologies within the food system, and also the unique challenges that must be addressed when developing soft robotics systems for this problem domain. We conclude with an outlook on potential directions for meaningful and sustainable impact, and also how our outlook on both soft robotics and agriculture must evolve in order to achieve the required paradigm shift.

Modeling multi-contact point physical interaction between the anthropomorphic finger and soft robotic exo-digit for wearable rehabilitation robotics applications

Introduction: Effective control of rehabilitation robots requires considering the distributed and multi-contact point physical human-robot interaction and users' biomechanical variation. This paper presents a quasi-static model for the motion of a soft robotic exo-digit while physically interacting with an anthropomorphic finger model for physical therapy. Methods: Quasi-static analytical models were developed for modeling the motion of the soft robot, the anthropomorphic finger, and their coupled physical interaction. An intertwining of kinematics and quasi-static motion was studied to model the distributed (multiple contact points) interaction between the robot and a human finger model. The anthropomorphic finger was modeled as an articulated multi-rigid body structure with multi-contact point interaction. The soft robot was modeled as an articulated hybrid soft-and-rigid model with a constant bending curvature and a constant length for each soft segment. A hyperelastic constitute model based on Yeoh's 3rdorder material model was used for modeling the soft elastomer. The developed models were experimentally evaluated for 1) free motion of individual soft actuators and 2) constrained motion of the soft robotic exo-digit and anthropomorphic finger model. Results and Discussion: Simulation and experimental results were compared for performance evaluations. The theoretical and experimental results were in agreement for free motion, and the deviation from the constrained motion was in the range of the experimental errors. The outcomes also provided an insight into the importance of considering lengthening for the soft actuators.

Kinetostatic Modeling of Soft Robots: Energy-Minimization Approach and 99-Line MATLAB Implementation

Soft robots have received a great deal of attention from both academia and industry due to their unprecedented adaptability in unstructured environment and extreme dexterity for complicated operations. Due to the strong coupling between the material nonlinearity due to hyperelasticity and the geometric nonlinearity due to large deflections, modeling of soft robots is highly dependent on commercial finite element software packages. An approach that is accurate and fast, and whose implementation is open to designers, is in great need. Considering that the constitutive relation of the hyperelastic materials is commonly expressed by its energy density function, we present an energy-based kinetostatic modeling approach in which the deflection of a soft robot is formulated as a minimization problem of its total potential energy. A fixed Hessian matrix of strain energy is proposed and adopted in the limited memory Broyden-Fletcher-Goldfarb-Shanno (BFGS) algorithm, which significantly improves its efficiency for solving the minimization problem of soft robots without sacrificing prediction accuracy. The simplicity of the approach leads to an implementation of MATLAB with only 99-line codes, which provides an easy-to-use tool for designers who are designing and optimizing the structures of soft robots. The efficiency of the proposed approach for predicting kinetostatic behaviors of soft robots is demonstrated by seven pneumatic-driven and cable-driven soft robots. The capability of the approach for capturing buckling behaviors in soft robots is also demonstrated. The energy-minimization approach, as well as the MATLAB implementation, could be easily tailored to fulfill various tasks, including design, optimization, and control of soft robots.

Reduced order modeling and model order reduction for continuum manipulators: an overview

Soft robot's natural dynamics calls for the development of tailored modeling techniques for control. However, the high-dimensional configuration space of the geometrically exact modeling approaches for soft robots, i.e., Cosserat rod and Finite Element Methods (FEM), has been identified as a key obstacle in controller design. To address this challenge, Reduced Order Modeling (ROM), i.e., the approximation of the full-order models, and Model Order Reduction (MOR), i.e., reducing the state space dimension of a high fidelity FEM-based model, are enjoying extensive research. Although both techniques serve a similar purpose and their terms have been used interchangeably in the literature, they are different in their assumptions and implementation. This review paper provides the first in-depth survey of ROM and MOR techniques in the continuum and soft robotics landscape to aid Soft Robotics researchers in selecting computationally efficient models for their specific tasks.

Control-Oriented Models for Hyperelastic Soft Robots Through Differential Geometry of Curves

The motion complexity and use of exotic materials in soft robotics call for accurate and computationally efficient models intended for control. To reduce the gap between material and control-oriented research, we build upon the existing piece-wise constant curvature framework by incorporating hyperelastic and viscoelastic material behavior. In this work, the continuum dynamics of the soft robot are derived through the differential geometry of spatial curves, which are then related to finite-element data to capture the intrinsic geometric and material nonlinearities. To enable fast simulations, a reduced-order integration scheme is introduced to compute the dynamic Lagrangian matrices efficiently, which in turn allows for real-time (multilink) models with sufficient numerical precision. By exploring the passivity and using the parameterization of the hyperelastic model, we propose a passivity-based adaptive controller that enhances robustness toward material uncertainty and unmodeled dynamics-slowly improving their estimates online. As a study-case, a soft robot manipulator is developed through additive manufacturing, which shows good correspondence with the dynamic model under various conditions, for example, natural oscillations, forced inputs, and under tip-loads. The solidity of the approach is demonstrated through extensive simulations, numerical benchmarks, and experimental validations.

SofaGym: An Open Platform for Reinforcement Learning Based on Soft Robot Simulations

OpenAI Gym is one of the standard interfaces used to train Reinforcement Learning (RL) Algorithms. The Simulation Open Framework Architecture (SOFA) is a physics-based engine that is used for soft robotics simulation and control based on real-time models of deformation. The aim of this article is to present SofaGym, an open-source software to create OpenAI Gym interfaces, called environments, out of soft robot digital twins. The link between soft robotics and RL offers new challenges for both fields: representation of the soft robot in an RL context, complex interactions with the environment, use of specific mechanical tools to control soft robots, transfer of policies learned in simulation to the real world, etc. The article presents the large possible uses of SofaGym to tackle these challenges by using RL and planning algorithms. This publication contains neither new algorithms nor new models but proposes a new platform, open to the community, that offers non existing possibilities of coupling RL to physics-based simulation of soft robots. We present 11 environments, representing a wide variety of soft robots and applications; we highlight the challenges showcased by each environment. We propose methods of solving the task using traditional control, RL, and planning and point out research perspectives using the platform.

Characterization of continuum robot arms under reinforcement learning and derived improvements

In robotics, soft continuum robot arms are a promising prospect owing to their redundancy and passivity; however, no comprehensive study exists that examines their characteristics compared to rigid manipulators. In this study, we examined the advantages of a continuum robot arm as compared to a typical and rigid seven-degree-of-freedom (7-DoF) robot manipulator in terms of performing various tasks through reinforcement learning. We conducted simulations for tasks with different characteristics that require control over position and force. Common tasks in robot manipulators, such as reaching, crank rotation, object throwing, and peg-in-hole were considered. The initial conditions of the robot and environment were randomized, aiming for evaluations including robustness. The results indicate that the continuum robot arm excels in the crank-rotation task, which is characterized by uncertainty in environmental conditions and cumulative rewards. However, the rigid robot arm learned better motions for the peg-in-hole task than the other tasks, which requires fine motion control of the end-effector. In the throwing task, the continuum robot arm scored well owing to its good handling of anisotropy. Moreover, we developed a reinforcement-learning method based on the comprehensive experimental results. The proposed method successfully improved the motion learning of a continuum robot arm by adding a technique to regulate the initial state of the robot. To the best of our knowledge, ours is the first reinforcement-learning experiment with multiple tasks on a single continuum robot arm and is the first report of a comparison between a single continuum robot arm and rigid manipulator on a wide range of tasks. This simulation study can make a significant contribution to the design of continuum arms and specification of their applications, and development of control and reinforcement learning methods.

Touchless interactive teaching of soft robots through flexible bimodal sensory interfaces

In this paper, we propose a multimodal flexible sensory interface for interactively teaching soft robots to perform skilled locomotion using bare human hands. First, we develop a flexible bimodal smart skin (FBSS) based on triboelectric nanogenerator and liquid metal sensing that can perform simultaneous tactile and touchless sensing and distinguish these two modes in real time. With the FBSS, soft robots can react on their own to tactile and touchless stimuli. We then propose a distance control method that enabled humans to teach soft robots movements via bare hand-eye coordination. The results showed that participants can effectively teach a self-reacting soft continuum manipulator complex motions in three-dimensional space through a "shifting sensors and teaching" method within just a few minutes. The soft manipulator can repeat the human-taught motions and replay them at different speeds. Finally, we demonstrate that humans can easily teach the soft manipulator to complete specific tasks such as completing a pen-and-paper maze, taking a throat swab, and crossing a barrier to grasp an object. We envision that this user-friendly, non-programmable teaching method based on flexible multimodal sensory interfaces could broadly expand the domains in which humans interact with and utilize soft robots.

Review on generic methods for mechanical modeling, simulation and control of soft robots

In this review paper, we are interested in the models and algorithms that allow generic simulation and control of a soft robot. First, we start with a quick overview of modeling approaches for soft robots and available methods for calculating the mechanical compliance, and in particular numerical methods, like real-time Finite Element Method (FEM). We also show how these models can be updated based on sensor data. Then, we are interested in the problem of inverse kinematics, under constraints, with generic solutions without assumption on the robot shape, the type, the placement or the redundancy of the actuators, the material behavior… We are also interested by the use of these models and algorithms in case of contact with the environment. Moreover, we refer to dynamic control algorithms based on mechanical models, allowing for robust control of the positioning of the robot. For each of these aspects, this paper gives a quick overview of the existing methods and a focus on the use of FEM. Finally, we discuss the implementation and our contribution in the field for an open soft robotics research.

Tensegrity Robotics

Numerous recent advances in robotics have been inspired by the biological principle of tensile integrity-or "tensegrity"-to achieve remarkable feats of dexterity and resilience. Tensegrity robots contain compliant networks of rigid struts and soft cables, allowing them to change their shape by adjusting their internal tension. Local rigidity along the struts provides support to carry electronics and scientific payloads, while global compliance enabled by the flexible interconnections of struts and cables allows a tensegrity to distribute impacts and prevent damage. Numerous techniques have been proposed for designing and simulating tensegrity robots, giving rise to a wide range of locomotion modes, including rolling, vibrating, hopping, and crawling. In this study, we review progress in the burgeoning field of tensegrity robotics, highlighting several emerging challenges, including automated design, state sensing, and kinodynamic motion planning.

Biology and bioinspiration of soft robotics: Actuation, sensing, and system integration

Organisms in nature grow with senses, nervous, and actuation systems coordinated in ingenious ways to sustain metabolism and other essential life activities. The understanding of biological structures and functions guide the construction of soft robotics with unprecedented performances. However, despite the progress in soft robotics, there still remains a big gap between man-made soft robotics and natural lives in terms of autonomy, adaptability, self-repair, durability, energy efficiency, etc. Here, the actuation and sensing strategies in the natural biological world are summarized along with their man-made counterparts applied in soft robotics. The development trends of bioinspired soft robotics toward closed loop and embodiment are proposed. Challenges for obtaining autonomous soft robotics similar to natural organisms are outlined to provide a perspective in this field.

Advanced soft robot modeling in ChainQueen

We present extensions to ChainQueen, an open source, fully differentiable material point method simulator for soft robotics. Previous work established ChainQueen as a powerful tool for inference, control, and co-design for soft robotics. We detail enhancements to ChainQueen, allowing for more efficient simulation and optimization and expressive co-optimization over material properties and geometric parameters. We package our simulator extensions in an easy-to-use, modular application programming interface (API) with predefined observation models, controllers, actuators, optimizers, and geometric processing tools, making it simple to prototype complex experiments in 50 lines or fewer. We demonstrate the power of our simulator extensions in over nine simulated experiments.

Robotic Home-Based Rehabilitation Systems Design: From a Literature Review to a Conceptual Framework for Community-Based Remote Therapy During COVID-19 Pandemic

During the COVID-19 pandemic, the higher susceptibility of post-stroke patients to infection calls for extra safety precautions. Despite the imposed restrictions, early neurorehabilitation cannot be postponed due to its paramount importance for improving motor and functional recovery chances. Utilizing accessible state-of-the-art technologies, home-based rehabilitation devices are proposed as a sustainable solution in the current crisis. In this paper, a comprehensive review on developed home-based rehabilitation technologies of the last 10 years (2011-2020), categorizing them into upper and lower limb devices and considering both commercialized and state-of-the-art realms. Mechatronic, control, and software aspects of the system are discussed to provide a classified roadmap for home-based systems development. Subsequently, a conceptual framework on the development of smart and intelligent community-based home rehabilitation systems based on novel mechatronic technologies is proposed. In this framework, each rehabilitation device acts as an agent in the network, using the internet of things (IoT) technologies, which facilitates learning from the recorded data of the other agents, as well as the tele-supervision of the treatment by an expert. The presented design paradigm based on the above-mentioned leading technologies could lead to the development of promising home rehabilitation systems, which encourage stroke survivors to engage in under-supervised or unsupervised therapeutic activities.

Computational Design of Skinned Quad-Robots

We present a computational design system that assists users to model, optimize, and fabricate quad-robots with soft skins. Our system addresses the challenging task of predicting their physical behavior by fully integrating the multibody dynamics of the mechanical skeleton and the elastic behavior of the soft skin. The developed motion control strategy uses an alternating optimization scheme to avoid expensive full space time-optimization, interleaving space-time optimization for the skeleton, and frame-by-frame optimization for the full dynamics. The output are motor torques to drive the robot to achieve a user prescribed motion trajectory. We also provide a collection of convenient engineering tools and empirical manufacturing guidance to support the fabrication of the designed quad-robot. We validate the feasibility of designs generated with our system through physics simulations and with a physically-fabricated prototype.

Characterizing Continuous Manipulation Families for Dexterous Soft Robot Hands

There has been an explosion of ideas in soft robotics over the past decade, resulting in unprecedented opportunities for end effector design. Soft robot hands offer benefits of low-cost, compliance, and customized design, with the promise of dexterity and robustness. The space of opportunities is vast and exciting. However, new tools are needed to understand the capabilities of such manipulators and to facilitate manipulation planning with soft manipulators that exhibit free-form deformations. To address this challenge, we introduce a sampling based approach to discover and model continuous families of manipulations for soft robot hands. We give an overview of the soft foam robots in production in our lab and describe novel algorithms developed to characterize manipulation families for such robots. Our approach consists of sampling a space of manipulation actions, constructing Gaussian Mixture Model representations covering successful regions, and refining the results to create continuous successful regions representing the manipulation family. The space of manipulation actions is very high dimensional; we consider models with and without dimensionality reduction and provide a rigorous approach to compare models across different dimensions by comparing coverage of an unbiased test dataset in the full dimensional parameter space. Results show that some dimensionality reduction is typically useful in populating the models, but without our technique, the amount of dimensionality reduction to use is difficult to predict ahead of time and can depend on the hand and task. The models we produce can be used to plan and carry out successful, robust manipulation actions and to compare competing robot hand designs.

3D Printing Materials for Soft Robotics

Soft robotics is a growing field of research, focusing on constructing motor-less robots from highly compliant materials, some are similar to those found in living organisms. Soft robotics has a high potential for applications in various fields such as soft grippers, actuators, and biomedical devices. 3D printing of soft robotics presents a novel and promising approach to form objects with complex structures, directly from a digital design. Here, recent developments in the field of materials for 3D printing of soft robotics are summarized, including high-performance flexible and stretchable materials, hydrogels, self-healing materials, and shape memory polymers, as well as fabrication of all-printed robots (multi-material printing, embedded electronics, untethered and autonomous robotics). The current challenges in the fabrication of 3D printed soft robotics, including the materials available and printing abilities, are presented and the recent activities addressing these challenges are also surveyed.

Procedural Telementoring in Rural, Underdeveloped, and Austere Settings: Origins, Present Challenges, and Future Perspectives

Telemedicine is perhaps the most rapidly growing area in health care. Approximately 15 million Americans receive medical assistance remotely every year. Yet rural communities face significant challenges in securing subspecialist care. In the United States, 25% of the population resides in rural areas, where less than 15% of physicians work. Current surgery residency programs do not adequately prepare surgeons for rural practice. Telementoring, wherein a remote expert guides a less experienced caregiver, has been proposed to address this challenge. Nonetheless, existing mentoring technologies are not widely available to rural communities, due to a lack of infrastructure and mentor availability. For this reason, some clinicians prefer simpler and more reliable technologies. This article presents past and current telementoring systems, with a focus on rural settings, and proposes aset of requirements for such systems. We conclude with a perspective on the future of telementoring systems and the integration of artificial intelligence within those systems.

Compliant gripper design, prototyping, and modeling using screw theory formulation

This article investigates some aspects related to the design, modeling, prototyping, and testing of soft–rigid tendon-driven grippers. As a case study, we present the design and development of a two-finger soft gripper and exploit it as an example to demonstrate the application scenario of our mathematical model based on screw theory. A mathematical formulation based on screw theory is then presented to model gripper dynamics. The proposed formulation is the extension of a model previously introduced including the mechanical system dynamics. In this type of gripper, it is possible to achieve different behaviors, e.g., different fingertip trajectories, equivalent fingertip stiffness ellipsoids, etc., while keeping the same kinematic structure of the gripper and varying the properties of its passive deformable joints. These properties can be varied in the prototype by properly regulating some manufacturing parameters, such as percentage of printing infill density in a 3D printing process. We performed experiments with the prototype of the gripper and an optical tracking system to validate the proposed mathematical formulation, and to compare its results with other simplified formulations. We furthermore identified the main performance of the gripper in terms of payload and maximum horizontal resisted force, and verified the capabilities of the gripper to grasp objects with different shapes and weights.

Dynamic simulation of articulated soft robots

Soft robots are primarily composed of soft materials that can allow for mechanically robust maneuvers that are not typically possible with conventional rigid robotic systems. However, owing to the current limitations in simulation, design and control of soft robots often involve a painstaking trial. With the ultimate goal of a computational framework for soft robotic engineering, here we introduce a numerical simulation tool for limbed soft robots that draws inspiration from discrete differential geometry based simulation of slender structures. The simulation incorporates an implicit treatment of the elasticity of the limbs, inelastic collision between a soft body and rigid surface, and unilateral contact and Coulombic friction with an uneven surface. The computational efficiency of the numerical method enables it to run faster than real-time on a desktop processor. Our experiments and simulations show quantitative agreement and indicate the potential role of predictive simulations for soft robot design.

Control-Based 4D Printing: Adaptive 4D-Printed Systems

Building on the recent progress of four-dimensional (4D) printing to produce dynamic structures, this study aimed to bring this technology to the next level by introducing control-based 4D printing to develop adaptive 4D-printed systems with highly versatile multi-disciplinary applications, including medicine, in the form of assisted soft robots, smart textiles as wearable electronics and other industries such as agriculture and microfluidics. This study introduced and analysed adaptive 4D-printed systems with an advanced manufacturing approach for developing stimuli-responsive constructs that organically adapted to environmental dynamic situations and uncertainties as nature does. The adaptive 4D-printed systems incorporated synergic integration of three-dimensional (3D)-printed sensors into 4D-printing and control units, which could be assembled and programmed to transform their shapes based on the assigned tasks and environmental stimuli. This paper demonstrates the adaptivity of these systems via a combination of proprioceptive sensory feedback, modeling and controllers, as well as the challenges and future opportunities they present.

Design, implementation, and control of a deformable manipulator robot based on a compliant spine

This article presents the conception, the numerical modeling, and the control of a dexterous, deformable manipulator bio-inspired by the skeletal spine found in vertebrate animals. Through the implementation of this new manipulator, we show a methodology based on numerical models and simulations, that goes from design to control of continuum and soft robots. The manipulator is modeled using a finite element method (FEM), using a set of beam elements that reproduce the lattice structure of the robot. The model is computed and inverted in real-time using optimization methods. A closed-loop control strategy is implemented to account for the disparities between the model and the robot. This control strategy allows for accurate positioning, not only of the tip of the manipulator, but also the positioning of selected middle points along its backbone. In a scenario where the robot is piloted by a human operator, the command of the robot is enhanced by a haptic loop that renders the boundaries of its task space as well as the contact with its environment. The experimental validation of the model and control strategies is also presented in the form of an inspection task use case.

Soft Robotics: A Review of Recent Developments of Pneumatic Soft Actuators

This paper focuses on the recent development of soft pneumatic actuators for soft robotics over the past few years, concentrating on the following four categories: control systems, material and construction, modeling, and sensors. This review work seeks to provide an accelerated entrance to new researchers in the field to encourage research and innovation. Advances in methods to accurately model soft robotic actuators have been researched, optimizing and making numerous soft robotic designs applicable to medical, manufacturing, and electronics applications. Multi-material 3D printed and fiber optic soft pneumatic actuators have been developed, which will allow for more accurate positioning and tactile feedback for soft robotic systems. Also, a variety of research teams have made improvements to soft robot control systems to utilize soft pneumatic actuators to allow for operations to move more effectively. This review work provides an accessible repository of recent information and comparisons between similar works. Future issues facing soft robotic actuators include portable and flexible power supplies, circuit boards, and drive components.

TMTDyn: A Matlab package for modeling and control of hybrid rigid–continuum robots based on discretized lumped systems and reduced-order models

A reliable, accurate, and yet simple dynamic model is important to analyzing, designing, and controlling hybrid rigid–continuum robots. Such models should be fast, as simple as possible, and user-friendly to be widely accepted by the ever-growing robotics research community. In this study, we introduce two new modeling methods for continuum manipulators: a general reduced-order model (ROM) and a discretized model with absolute states and Euler–Bernoulli beam segments (EBA). In addition, a new formulation is presented for a recently introduced discretized model based on Euler–Bernoulli beam segments and relative states (EBR). We implement these models in a Matlab software package, named TMTDyn, to develop a modeling tool for hybrid rigid–continuum systems. The package features a new high-level language (HLL) text-based interface, a CAD-file import module, automatic formation of the system equation of motion (EOM) for different modeling and control tasks, implementing Matlab C-mex functionality for improved performance, and modules for static and linear modal analysis of a hybrid system. The underlying theory and software package are validated for modeling experimental results for (i) dynamics of a continuum appendage, and (ii) general deformation of a fabric sleeve worn by a rigid link pendulum. A comparison shows higher simulation accuracy (8–14% normalized error) and numerical robustness of the ROM model for a system with a small number of states, and computational efficiency of the EBA model with near real-time performances that makes it suitable for large systems. The challenges and necessary modules to further automate the design and analysis of hybrid systems with a large number of states are briefly discussed.

Automatic Generation of Locomotion Patterns for Soft Modular Reconfigurable Robots

In recent years, soft modular robots have become popular among researchers with the development of soft robotics. However, the absence of a visual 3D simulation platform for soft modular robots hold back the development of the field. The three-dimensional simulation platform plays an important role in the field of multi-body robots. It can shorten the design cycle, reduce costs, and verify the effectiveness of the optimization algorithm expediently. Equally importantly, evolutionary computation is a very effective method for designing the controller of multi-body robots and soft robots with hyper redundancy and large parametric design space. In this paper, a tradeoff between the structural complexity of the soft modular robot and computational power of the simulation software is made. A reconfigurable soft modular robot is designed, and the open-source simulation software VOXCAD is re-developed to simulate the actual soft robot. The evolutionary algorithm is also applied to search for the most efficient motion pattern for an established configuration in VOXCAD, and experiments are conducted to validate the results.

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

Successful soft robot modeling approaches appearing in the 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 article, 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.

Deep Reinforcement Learning for Soft, Flexible Robots: Brief Review with Impending Challenges

The increasing trend of studying the innate softness of robotic structures and amalgamating it with the benefits of the extensive developments in the field of embodied intelligence has led to the sprouting of a relatively new yet rewarding sphere of technology in intelligent soft robotics. The fusion of deep reinforcement algorithms with soft bio-inspired structures positively directs to a fruitful prospect of designing completely self-sufficient agents that are capable of learning from observations collected from their environment. For soft robotic structures possessing countless degrees of freedom, it is at times not convenient to formulate mathematical models necessary for training a deep reinforcement learning (DRL) agent. Deploying current imitation learning algorithms on soft robotic systems has provided competent results. This review article posits an overview of various such algorithms along with instances of being applied to real-world scenarios, yielding frontier results. Brief descriptions highlight the various pristine branches of DRL research in soft robotics.