# From Biological Curves to Soft Modular Robots: Learning-Based Inverse Design with Uncertainty-Guided Refinement

DevFeed: [From Biological Curves to Soft Modular Robots: Learning-Based Inverse Design with Uncertainty-Guided Refinement](<https://devfeed.tech/articles/from-biological-curves-to-soft-modular-robots-learning-based-inverse-design-with-uncertainty-guided-refinement-103989.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.36681>)

Author: Dixiang Wang, Minghao Zha, Arifur Rahman, Yinhong Qin, Yitao Jiang, Shiyang Lu, Zebing Mao, Muhao Chen, Luyang Zhao

Published: 2026-10-28T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Robotics Simulation](<https://devfeed.tech/topics/robotics-simulation.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>)

Tags: [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cs-ro](<https://devfeed.tech/tags/cs-ro.md>), [inverse-design](<https://devfeed.tech/tags/inverse-design.md>), [learning](<https://devfeed.tech/tags/learning.md>), [modeling](<https://devfeed.tech/tags/modeling.md>), [modular](<https://devfeed.tech/tags/modular.md>), [modular-robots](<https://devfeed.tech/tags/modular-robots.md>), [prediction](<https://devfeed.tech/tags/prediction.md>), [robotics](<https://devfeed.tech/tags/robotics.md>), [robots](<https://devfeed.tech/tags/robots.md>), [sim-to-real](<https://devfeed.tech/tags/sim-to-real.md>), [uncertainty](<https://devfeed.tech/tags/uncertainty.md>)

## AI overview

The framework maps biological curves to configurations for cable-driven modular soft robots using learned inverse prediction, targeted candidate exploration, and a fast forward surrogate to evaluate designs. It reports reducing deformation prediction time from 153,000 ms to 0.0008 ms and inverse design time from 1,990,000 ms to 4.18 ms. On 5,000 samples with previously unseen threading patterns, it achieved 93% shape reconstruction success under surrogate-based evaluation. Physical demonstrations with four bioinspired robots showed translation of curves into realizable shapes.

## Source excerpt

arXiv:2610.36681v1 Announce Type: cross Abstract: Animals exhibit diverse shape-changing behaviors, from the undulatory swimming of eels to the arching movements of inchworms. Reproducing these biological shapes with modular soft robots offers a promising approach to developing versatile bioinspired robotic systems. However, translating a desired shape into a feasible robotic configuration remains challenging. Existing cable-driven modular soft robots rely on computationally expensive physics-based modeling and combinatorial search for inverse design, making it difficult to efficiently reproduce diverse target shapes. To address this challenge, we present a learning-based real-to-sim-to-real framework that translates biological curves into robotic configurations through surrogate-assisted inverse design and uncertainty-guided refinement. The proposed method combines learned inverse prediction with targeted candidate exploration, using a fast forward surrogate to evaluate and select suitable designs. The learned forward surrogate reduces deformation prediction time from $1.53 \times 10^5$ ms to 0.0008 ms, achieving approximately a $1.9 \times 10^8$-fold speedup. At the same time, the proposed inverse design method reduces design time from $1.99 \times 10^6$ ms to 4.18 ms. On 5,000 test samples generated from previously unseen threading patterns, the method achieves a 93% shape reconstruction success rate under surrogate-based evaluation. Physical demonstrations with four bioinspired robots further illustrate the translation of biological curves into realizable robotic shapes.