Use of Finite Elements in the Training of a Neural Network for the Modeling of a Soft Robot

Terrile, Silvia; López, Andrea; Barrientos, Antonio

doi:10.3390/biomimetics8010056

Cited by 10 publications

(9 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, the ability to adjust the stiffness of the soft robot during manipulation is of high clinical importance and could be achieved using the hybrid-driven mode suggested in the current study. Moreover, synthetic data generated by the simulations could later be used to train a neural network to model a hybrid actuated soft robot, similar to the work done by S. Terrile et al [ 65 ]. Finally, to overcome the manufacturing challenges mentioned in the study, advanced fabrication technologies, such as multi-material 3D printing, are promising.…”

Section: Discussionmentioning

confidence: 98%

Design Optimization of a Hybrid-Driven Soft Surgical Robot with Biomimetic Constraints

Roshanfar,

Dargahi,

Hooshiar

2024

Biomimetics

View full text Add to dashboard Cite

The current study investigated the geometry optimization of a hybrid-driven (based on the combination of air pressure and tendon tension) soft robot for use in robot-assisted intra-bronchial intervention. Soft robots, made from compliant materials, have gained popularity for use in surgical interventions due to their dexterity and safety. The current study aimed to design a catheter-like soft robot with an improved performance by minimizing radial expansion during inflation and increasing the force exerted on targeted tissues through geometry optimization. To do so, a finite element analysis (FEA) was employed to optimize the soft robot’s geometry, considering a multi-objective goal function that incorporated factors such as chamber pressures, tendon tensions, and the cross-sectional area. To accomplish this, a cylindrical soft robot with three air chambers, three tendons, and a central working channel was considered. Then, the dimensions of the soft robot, including the length of the air chambers, the diameter of the air chambers, and the offsets of the air chambers and tendon routes, were optimized to minimize the goal function in an in-plane bending scenario. To accurately simulate the behavior of the soft robot, Ecoflex 00-50 samples were tested based on ISO 7743, and a hyperplastic model was fitted on the compression test data. The FEA simulations were performed using the response surface optimization (RSO) module in ANSYS software, which iteratively explored the design space based on defined objectives and constraints. Using RSO, 45 points of experiments were generated based on the geometrical and loading constraints. During the simulations, tendon force was applied to the tip of the soft robot, while simultaneously, air pressure was applied inside the chamber. Following the optimization of the geometry, a prototype of the soft robot with the optimized values was fabricated and tested in a phantom model, mimicking simulated surgical conditions. The decreased actuation effort and radial expansion of the soft robot resulting from the optimization process have the potential to increase the performance of the manipulator. This advancement led to improved control over the soft robot while additionally minimizing unnecessary cross-sectional expansion. The study demonstrates the effectiveness of the optimization methodology for refining the soft robot’s design and highlights its potential for enhancing surgical interventions.

show abstract

Section: Discussionmentioning

confidence: 98%

Design Optimization of a Hybrid-Driven Soft Surgical Robot with Biomimetic Constraints

Roshanfar,

Dargahi,

Hooshiar

2024

Biomimetics

View full text Add to dashboard Cite

show abstract

“…While these models achieve correct results, it may seem of more interest to train from FEM models in order to combine their accuracy with the fast response that a finite element simulation is not able to provide. Thus, in [ 70 ], PCC parameters are extracted from an FEM model and used for training an FFNN and making open-loop control of the robot. In [ 71 ], two FFNNs are placed in series: a first one trained using an FEM model (which requires 4000 points for correctly modelling a soft segment) and a second one trained over the real robot, for which 300 samples are enough; the authors obtained tracking errors of 1

.…”

Section: Related Workmentioning

confidence: 99%

Model-Free Control of a Soft Pneumatic Segment

García-Samartín,

Molina-Gómez,

Barrientos

2024

Biomimetics

Self Cite

View full text Add to dashboard Cite

Soft robotics faces challenges in attaining control methods that ensure precision from hard-to-model actuators and sensors. This study focuses on closed-chain control of a segment of PAUL, a modular pneumatic soft arm, using elastomeric-based resistive sensors with negative piezoresistive behaviour irrespective of ambient temperature. PAUL’s performance relies on bladder inflation and deflation times. The control approach employs two neural networks: the first translates position references into valve inflation times, and the second acts as a state observer to estimate bladder inflation times using sensor data. Following training, the system achieves position errors of 4.59 mm, surpassing the results of other soft robots presented in the literature. The study also explores system modularity by assessing performance under external loads from non-actuated segments.

show abstract

“…Additionally, advances in machine learning (ML) algorithms and computers are improving the precision of soft robots both in actuation and sensing. Researchers are using artificial neural networks (ANN) for modelling soft robots [183], and shape sensing/control [184,185]. A review of ML methods in soft robotics is given in [186], and [102].…”

Section: The Perspectivementioning

confidence: 99%

Soft Medical Robots and Probes: Concise Survey of Current Advances

Sayahkarajy,

Witte

2023

Design, Construction, Maintenance

View full text Add to dashboard Cite

Soft robotics has emerged as a new branch of robotics gaining huge research interest in recent decades. Owning intrinsic advantages such as compliance and safety, soft robots are closely associated with the medical requirements of medical robots. This review is written to overview advances in the medical applications of soft robots, either for readers primarily familiar with traditional medical systems, or for researchers planning to develop soft robots for medical applications. Recent publications related to soft medical robots were reviewed to represent the state’, ’of’, ’the’, ’art advances in this field. The review tends to compress the scope to trunk’, ’shaped soft robots and appraise the status of soft robots and their distance from clinical use. Several papers related to the construction and capabilities of soft robots were referenced. Roughly 190 related articles published in the current period from 2018 to the publication date (representing almost 90% of the references to the theme totally identified) were reviewed. Structure of soft robots, advances in technology, and the aptitudes in medical applications were discussed. The trunk’, ’like soft robots conspicuously are proposed for applications including robot assisted surgery where a probe is inserted into the human body. Such robots are also present in other medical robots as actuators. The literature shows that different methods are used to fabricate soft robots and employ them in different robotics tasks including positioning, grasping, and force exertion. Noticeably, such studies were done in robotics laboratories, dealing with robotics engineering problems. This review suggests that the technology is actively developing, but further focus on specific medical applications is required to fill the gap between soft robotics and its clinical use.

show abstract

Use of Finite Elements in the Training of a Neural Network for the Modeling of a Soft Robot

Cited by 10 publications

References 24 publications

Design Optimization of a Hybrid-Driven Soft Surgical Robot with Biomimetic Constraints

Design Optimization of a Hybrid-Driven Soft Surgical Robot with Biomimetic Constraints

Model-Free Control of a Soft Pneumatic Segment

Soft Medical Robots and Probes: Concise Survey of Current Advances

Contact Info

Product

Resources

About