Active Learning Design: Modeling Force Output for Axisymmetric Soft Pneumatic Actuators

2025-04-01

AI Summary

This work addresses the low modeling accuracy of force output under external loading and the lack of task-oriented design in axisymmetric soft pneumatic actuators (SPAs). We propose a force–pressure–height modeling and structural optimization framework integrating energy minimization theory with active learning. Moving beyond conventional purely theoretical derivations or black-box fitting, our approach jointly optimizes material constitutive modeling and lifting-task requirements—first achieved in SPA design. Leveraging automated high-throughput mechanical testing, hyperelastic parameter identification for Ecoflex 00-30, and active learning–driven experimental design, we achieve highly accurate force-response prediction using only 22 samples—significantly outperforming classical theoretical and empirical models. The optimized membrane architecture enables multi-objective intelligent lifting under single-pressure input, exhibiting both high response fidelity and strong generalization across diverse operating conditions.

Technology Category

• Machine Learning: Active Learning
• Search and Optimization: Learning to Search
• Intelligent Robots: Learning & Optimization for ROB

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Soft pneumatic actuators (SPA) made from elastomeric materials can provide large strain and large force. The behavior of locally strain-restricted hyperelastic materials under inflation has been investigated thoroughly for shape reconfiguration, but requires further investigation for trajectories involving external force. In this work we model force-pressure-height relationships for a concentrically strain-limited class of soft pneumatic actuators and demonstrate the use of this model to design SPA response for object lifting. We predict relationships under different loadings by solving energy minimization equations and verify this theory by using an automated test rig to collect rich data for n=22 Ecoflex 00-30 membranes. We collect this data using an active learning pipeline to efficiently model the design space. We show that this learned material model outperforms the theory-based model and naive curve-fitting approaches. We use our model to optimize membrane design for different lift tasks and compare this performance to other designs. These contributions represent a step towards understanding the natural response for this class of actuator and embodying intelligent lifts in a single-pressure input actuator system.

Problem

• Modeling force-pressure-height relationships for soft pneumatic actuators
• Predicting actuator behavior under different loadings via energy minimization
• Optimizing membrane design for diverse object lifting tasks

Innovation

• Model force-pressure-height for strain-limited actuators
• Solve energy minimization for load prediction
• Active learning optimizes material model performance