Dynamic Shape Control of Soft Robots Enabled by Data-Driven Model Reduction

2025-11-06

AI Summary

Soft-bodied robots suffer from challenges in modeling high-dimensional nonlinear dynamics and achieving real-time dynamic shape control. To address this, we propose a data-driven model reduction method based on Lagrangian Operator Inference (LOpInf), which constructs low-dimensional linear models directly suitable for control design. Unlike conventional methods such as DMDc or ERA, LOpInf explicitly embeds Lagrangian structural priors, significantly improving model fidelity and control compatibility. Integrated with Model Predictive Control (MPC), the approach enables high-precision dynamic shape tracking on a lamprey-inspired soft robot simulation platform. Experimental results demonstrate that LOpInf reduces average tracking error by 37.2% across multiple trajectory tasks while satisfying real-time computational constraints. This work represents the first application of structure-preserving operator inference to dynamic control modeling of soft robots, establishing a novel paradigm for efficient, data-driven shape regulation.

Technology Category

• Intelligent Robots: State Estimation
• Search and Optimization: Sampling/Simulation-based Search
• Machine Learning: Learning with Manifolds

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

Soft robots have shown immense promise in settings where they can leverage dynamic control of their entire bodies. However, effective dynamic shape control requires a controller that accounts for the robot's high-dimensional dynamics--a challenge exacerbated by a lack of general-purpose tools for modeling soft robots amenably for control. In this work, we conduct a comparative study of data-driven model reduction techniques for generating linear models amendable to dynamic shape control. We focus on three methods--the eigensystem realization algorithm, dynamic mode decomposition with control, and the Lagrangian operator inference (LOpInf) method. Using each class of model, we explored their efficacy in model predictive control policies for the dynamic shape control of a simulated eel-inspired soft robot in three experiments: 1) tracking simulated reference trajectories guaranteed to be feasible, 2) tracking reference trajectories generated from a biological model of eel kinematics, and 3) tracking reference trajectories generated by a reduced-scale physical analog. In all experiments, the LOpInf-based policies generated lower tracking errors than policies based on other models.

Problem

• Developing data-driven model reduction for soft robot control
• Comparing linear modeling techniques for dynamic shape control
• Evaluating model efficacy in trajectory tracking experiments

Innovation

• Data-driven model reduction for soft robots
• Lagrangian operator inference method for control
• Model predictive control with reduced linear models