Infinite-Dimensional Closed-Loop Inverse Kinematics for Soft Robots Via Neural Operators

Journal Article (2026)
Author(s)

Carina Veil (Stanford University)

Moritz Flaschel (Friedrich-Alexander-Universität Erlangen-Nürnberg)

Ellen Kuhl (Stanford University)

Cosimo Della Santina (TU Delft - Mechanical Engineering)

Research Group
Learning & Autonomous Control
DOI related publication
https://doi.org/10.1109/LRA.2026.3739023 Final published version
More Info
expand_more
Publication Year
2026
Language
English
Research Group
Learning & Autonomous Control
Journal title
IEEE Robotics and Automation Letters
Issue number
11
Volume number
11
Pages (from-to)
13319-13326
Page Views
31
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

For fully actuated rigid robots, kinematic inversion is a purely geometric problem, efficiently solved by closed-loop inverse kinematics (CLIK) schemes that compute joint velocities to position the robot body in space. For underactuated soft robots, however, not all configurations are attainable through control action, making kinematic inversion extremely ill-posed. Extensions of CLIK address this by introducing end-to-end mappings from actuation to task space for the controller to operate on, but typically assume finite dimensions of the underlying virtual configuration space. In this work, we formulate CLIK in the infinite-dimensional domain to reason about the entire soft robot shape while solving tasks, thereby skipping intermediate approximation steps. We do this by composing an actuation-to-shape map with a shape-to-task map, deriving the differential end-to-end kinematics via an infinite-dimensional chain rule, and thereby obtaining a Jacobian-based CLIK algorithm. Since complex soft-robot models are rarely available in closed form, and neither the actuation-to-shape mapping nor its Jacobian can typically be obtained analytically, we propose to learn it using differentiable neural operator networks. We first present an analytical study on a constant-curvature segment, and then apply the neural version of the algorithm to a three-fiber soft robotic arm whose underlying model relies on morphoelasticity and active filament theory.

Files

– Personal use only – Dutch Copyright Act (Article 25fa)
warning

File under embargo until 30-03-2027