Model-Free Co-Optimization of Manufacturable Sensor Layouts and Deformation Proprioception
IEEE Transactions on Robotics · 2026 · 1-18
DOI: 10.1109/tro.2026.3677076 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Robotics, 2026. Verfasst von Yingjun Tian und 7 weiteren Autor:innen. Die Arbeit nennt 61 Literaturangaben.
Abstract (Originalsprache)
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.
Zitieren
APA
Tian, Y., Fang, G., Lyu, A., Wang, X., Shi, Z., Guo, Y., Wang, W., & Wang, C. C. (2026). Model-Free Co-Optimization of Manufacturable Sensor Layouts and Deformation Proprioception. IEEE Transactions on Robotics, 1-18. https://doi.org/10.1109/tro.2026.3677076
Vancouver
Tian Y, Fang G, Lyu A, Wang X, Shi Z, Guo Y, et al. Model-Free Co-Optimization of Manufacturable Sensor Layouts and Deformation Proprioception. IEEE Transactions on Robotics. 2026:1-18. doi:10.1109/tro.2026.3677076
BibTeX
@article{Tian2026,
author = {Tian, Yingjun and Fang, Guoxin and Lyu, Aoran and Wang, Xilong and Shi, Zikang and Guo, Yuhu and Wang, Weiming and Wang, Charlie C.L.},
title = {Model-Free Co-Optimization of Manufacturable Sensor Layouts and Deformation Proprioception},
journal = {IEEE Transactions on Robotics},
year = {2026},
pages = {1--18},
doi = {10.1109/tro.2026.3677076}
}
EUVIMED