arXiv：cs.LG· Milad Yazdani, Shahriar Shalileh, Dena Shahriari·· 13 小时前
RL-Kirigami：用强化学习逆向设计并激光切割平行四边形四重剪纸原型
Reinforcement learning for inverse silhouette design and rapid laser cutting of compact parallelogram quad kirigami prototypes
AI 导读
RL-Kirigami 将最优传输条件流匹配（OT-CFM）与强化学习结合，为紧凑可重构平行四边形四重剪纸生成兼容比例场，预训练 OT-CFM 先验单次采样即达 94.2% sIoU，并将前向模拟器评估从数百次降至 1 次。
正文
Abstract:Kirigami is an increasingly useful fabrication method to produce shape-programmable metamaterial structures. However, inverse design remains difficult because deployment is nonlinear, and feasible cut layouts must satisfy discrete compatibility rules, avoid overlap, and map one target shape to valid designs. We present RL-Kirigami, an inverse design framework that combines optimal-transport conditional flow matching (OT-CFM) with reinforcement learning to generate compatible ratio fields for compact reconfigurable parallelogram quad kirigami. A marching decoder enforces global geometric compatibility, and Group Relative Policy Optimization (GRPO) aligns the generator with nondifferentiable rewards for silhouette matching, feasibility, and ratio-field regularity. Across procedurally generated target shape instances, a single sample from the pretrained OT-CFM prior reached $94.2\%~\mathrm{sIoU}$ and outperformed solver baselines while reducing forward simulator evaluations from hundreds to $1$. GRPO improved accuracy to $94.91\%~\mathrm{sIoU}$ and, with regularity included, reduced $\mathrm{TV}(\mathbf{x})$ from $0.95$ to $0.81$ while maintaining $94.83\%~\mathrm{sIoU}$. Generated layouts were exported to DXF and laser cut in $50~\mu\mathrm{m}$ polymeric sheets to produce deployable prototypes in $8.0\pm 1.0$ minutes per part. These results support a manufacturing-aware inverse design workflow for deployable kirigami metamaterials under geometric feasibility constraints. Code is available at this https URL.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.08098 [cs.LG] |
| (or arXiv:2605.08098v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.08098 arXiv-issued DOI via DataCite |
|
| Journal reference: | Materials & Design 268 (2026), 116545 |
| Related DOI: | https://doi.org/10.1016/j.matdes.2026.116545
DOI(s) linking to related resources |
Submission history
From: Milad Yazdani [view email]
[v1]
Thu, 16 Apr 2026 18:12:45 UTC (2,470 KB)
[v2]
Thu, 8 Oct 2026 22:25:24 UTC (9,432 KB)
来源：arXiv：cs.LG · arxiv.org