Data-driven Model Reduction for Soft Robots via Lagrangian Operator Inference
This work addresses the need for efficient real-time control models for soft robots, representing an incremental improvement by leveraging Lagrangian structure to enhance existing data-driven reduction techniques.
The paper tackled the problem of constructing computationally efficient surrogates for real-time control of soft robots by developing structure-preserving linear reduced-order models using Lagrangian Operator Inference, demonstrating that this approach leads to higher predictive accuracy and robustness compared to other methods in a case study with 231,336 degrees of freedom.
Data-driven model reduction methods provide a nonintrusive way of constructing computationally efficient surrogates of high-fidelity models for real-time control of soft robots. This work leverages the Lagrangian nature of the model equations to derive structure-preserving linear reduced-order models via Lagrangian Operator Inference and compares their performance with prominent linear model reduction techniques through an anguilliform swimming soft robot model example with 231,336 degrees of freedom. The case studies demonstrate that preserving the underlying Lagrangian structure leads to learned models with higher predictive accuracy and robustness to unseen inputs.