Learning Soft Robot Dynamics using Differentiable Kalman Filters and Spatio-Temporal Embeddings

TL;DR

This paper presents a differentiable filter-based method with spatio-temporal embeddings for accurately modeling soft robot dynamics, demonstrating robustness and improved accuracy over existing methods on a tensegrity robot arm.

Contribution

It introduces a novel end-to-end trainable framework combining differentiable filters and spatio-temporal embeddings for soft robot dynamics modeling.

Findings

At least 24% reduction in mean absolute error compared to state-of-the-art methods.

Average end-effector position MAE of 25.77mm from ground truth.

Robustness against missing modalities, sensor placement variations, and sampling rates.

Abstract

This paper introduces a novel approach for modeling the dynamics of soft robots, utilizing a differentiable filter architecture. The proposed approach enables end-to-end training to learn system dynamics, noise characteristics, and temporal behavior of the robot. A novel spatio-temporal embedding process is discussed to handle observations with varying sensor placements and sampling frequencies. The efficacy of this approach is demonstrated on a tensegrity robot arm by learning end-effector dynamics from demonstrations with complex bending motions. The model is proven to be robust against missing modalities, diverse sensor placement, and varying sampling rates. Additionally, the proposed framework is shown to identify physical interactions with humans during motion. The utilization of a differentiable filter presents a novel solution to the difficulties of modeling soft robot dynamics. Our approach shows substantial improvement in accuracy compared to state-of-the-art filtering methods, with at least a 24% reduction in mean absolute error (MAE) observed. Furthermore, the predicted end-effector positions show an average MAE of 25.77mm from the ground truth, highlighting the advantage of our approach. The code is available at https://github.com/ir-lab/soft_robot_DEnKF.