Soft helicoid robot precision control improves with data driven model

Data-Driven Precision Control of Soft Helicoid Robots

RoboticsMachine Learning

Summary

Controlling soft robots is tricky because their movements are complex and hard to predict. The authors developed a method that learns a simpler model of a soft helicoid robot's movement using only data collected from the robot itself. They then use this model to guide the robot's movements very precisely in real time, following complicated paths accurately. Their approach works better than some other data-driven or learning methods and can be used for various types of soft robots.

What this means in practice

Authors

Roshan S. Kaundinya, Mark Leone, Roberto Sabella, Hugo Buurmeijer, Luis Pabon, John Irvin Alora, Marco Pavone, George Haller

Abstract

A purely data-driven method grounded in the theory of adiabatic spectral submanifolds (aSSMs) was recently used to model and control nonlinear soft robotic simulators. Here, we extend the methodology to learn aSSM-reduced models from data collected from hardware soft robotic platforms. Specifically, we learn a five dimensional (5D) aSSM-reduced nonlinear ordinary differential equation (ODE) that accurately models the dynamics of a soft-helicoid trunk robot. We then use this ODE in a model predictive control scheme to demonstrate real-time precision control across various challenging closed-loop trajectory-tracking tasks, ranging from 2D to 3D trajectories with static and dynamic constraints. We find that our methodology enhances accuracy and precision across all control tasks compared to available data-driven linear methods and model-free reinforcement learning. While we focus here on a soft-helicoid trunk robot, our methodology relies solely on hardware data and is therefore applicable to a broader class of soft robotic systems.