Search for: All records

The heterogeneous micromechanical properties of biological tissues have profound implications across diverse medical and engineering domains. However, identifying full‐field heterogeneous elastic properties of soft materials using traditional engineering approaches is fundamentally challenging due to difficulties in estimating local stress fields. Recently, there has been a growing interest in data‐driven models for learning full‐field mechanical responses, such as displacement and strain, from experimental or synthetic data. However, research studies on inferring full‐field elastic properties of materials, a more challenging problem, are scarce, particularly for large deformation, hyperelastic materials. Here, a physics‐informed machine learning approach is proposed to identify the elasticity map in nonlinear, large deformation hyperelastic materials. This study reports the prediction accuracies and computational efficiency of physics‐informed neural networks (PINNs) in inferring the heterogeneous elasticity maps across materials with structural complexity that closely resemble real tissue microstructure, such as brain, tricuspid valve, and breast cancer tissues. Further, the improved architecture is applied to three hyperelastic constitutive models: Neo‐Hookean, Mooney Rivlin, and Gent. The improved network architecture consistently produces accurate estimations of heterogeneous elasticity maps, even when there is up to 10% noise present in the training data. 

A minimal number of rigid constraints makes soft robots versatile, but many of these robots use soft pneumatic actuators (SPAs) designed to inflate through a single trajectory. In an unloaded actuator, this trajectory is dictated by the arrangement of in-extensible and elastic materials. External strain limiters can be added post-fabrication to SPAs, but these are passive devices. In this paper, we offer design and control techniques for an electrically active strain limiter that is easily adhered to existing SPAs to provide signal-controlled force output. These sheathed electroadhesive (EA) clutches apply antagonistic forces through the constitutive properties of their silicone sheathing and through the variable friction of the clutch itself. We are able to design the sheathing to passively support loads or minimize passive stiffness. We control clutch forces via an augmented pulse-width-modulation (PWM) of the high voltage square-wave input. We perform an initial, empirical characterization on the system with tensile material testing. The clutch system resists motion with sustained forces ranging from 0.5N to 22N. We then demonstrate its ability to apply predictable nonconservative work in a dynamic catching task, where it can limit catching height from 15cm to 1cm. Finally, we attach it to an inverse pneumatic artificial muscle (IPAM) to show that variable strain limitation can control position of the SPA endpoint.