Physics-Embedded Neural ODEs for Learning Antagonistic Pneumatic Artificial Muscle Dynamics

2026-02-27

AI Summary

This work addresses the challenge of accurately modeling and controlling antagonistic pneumatic artificial muscle (PAM) systems, which exhibit strong coupling, nonlinear dynamics, and rate-dependent hysteresis. To this end, the authors propose a physics-informed neural differential equation framework that unifies parameterized joint dynamics, pneumatic state evolution, and a neural network-based force module to explicitly capture mechano-pneumatic coupling and hysteresis effects. This approach is the first to jointly represent the mechanical, pneumatic, and hysteretic behaviors of PAMs within a single forward model while enabling inverse generation of pressure commands that achieve desired trajectories and stiffness profiles. Experimental results demonstrate that the forward model achieves an average R² of 0.88 across 225 co-contraction conditions, and closed-loop control reliably modulates stiffness within 126–176 N/mm while maintaining consistent impedance performance across varying motion speeds, significantly outperforming static models.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning
• Intelligent Robots: Behavior Learning & Control

Application Category

• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Pneumatic artificial muscles (PAMs) enable compliant actuation for soft wearable, assistive, and interactive robots. When arranged antagonistically, PAMs can provide variable impedance through co-contraction but exhibit coupled, nonlinear, and hysteretic dynamics that challenge modeling and control. This paper presents a hybrid neural ordinary differential equation (Neural ODE) framework that embeds physical structure into a learned model of antagonistic PAM dynamics. The formulation combines parametric joint mechanics and pneumatic state dynamics with a neural network force component that captures antagonistic coupling and rate-dependent hysteresis. The forward model predicts joint motion and chamber pressures with a mean R$^2$ of 0.88 across 225 co-contraction conditions. An inverse formulation, derived from the learned dynamics, computes pressure commands offline for desired motion and stiffness profiles, tracked in closed loop during execution. Experimental validation demonstrates reliable stiffness control across 126-176 N/mm and consistent impedance behavior across operating velocities, in contrast to a static model, which shows degraded stiffness consistency at higher velocities.

Problem

• Pneumatic artificial muscles
• antagonistic actuation
• nonlinear dynamics
• hysteresis
• modeling and control

Innovation

• Physics-Embedded Neural ODE
• Antagonistic Pneumatic Artificial Muscles
• Rate-Dependent Hysteresis
• Hybrid Dynamics Modeling
• Variable Impedance Control