Model-Free Co-Optimization of Manufacturable Sensor Layouts and Deformation Proprioception

TL;DR

This paper presents a data-driven, model-free method to jointly optimize sensor layouts and shape prediction networks for flexible sensors in soft robotics, improving deformation prediction accuracy without relying on physical models.

Contribution

It introduces a novel pipeline that co-optimizes sensor placement and prediction network parameters solely from deformation datasets, enhancing accuracy and manufacturability.

Findings

Significantly improves deformation prediction accuracy.

Applicable to diverse soft robotic and wearable systems.

Validated through numerical and physical experiments.

Abstract

Flexible sensors are increasingly employed in soft robotics and wearable devices to provide proprioception of freeform deformations.Although supervised learning can train shape predictors from sensor signals, prediction accuracy strongly depends on sensor layout, which is typically determined heuristically or through trial-and-error. This work introduces a model-free, data-driven computational pipeline that jointly optimizes the number, length, and placement of flexible length-measurement sensors together with the parameters of a shape prediction network for large freeform deformations. Unlike model-based approaches, the proposed method relies solely on datasets of deformed shapes, without requiring physical simulation models, and is therefore broadly applicable to diverse robotic sensing tasks. The pipeline incorporates differentiable loss functions that account for both prediction accuracy and manufacturability constraints. By co-optimizing sensor layouts and network parameters, the method significantly improves deformation prediction accuracy over unoptimized layouts while ensuring practical feasibility. The effectiveness and generality of the approach are validated through numerical and physical experiments on multiple soft robotic and wearable systems.