@article{wang2026biologicalcurves,
  author = {Wang, Dixiang and Zha, Minghao and Rahman, Arifur and Qin, Yinhong and Jiang, Yitao and Lu, Shiyang and Mao, Zebing and Chen, Muhao and Zhao, Luyang},
  title = {From Biological Curves to Soft Modular Robots: Learning-Based Inverse Design with Uncertainty-Guided Refinement},
  journal = {Under Submission},
  year = {2026},
  abbr = {biological-curves},
  arxiv = {2610.36681},
  video = {https://www.youtube.com/watch?v=4Xw9c4H2Etk},
  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. 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 method combines learned inverse prediction with targeted candidate exploration and uses a fast forward surrogate to evaluate and select suitable designs. Physical demonstrations with four bioinspired robots illustrate the translation of biological curves into realizable robotic shapes.}
}
